| 2026.09.14 | 李文杰 (Agent Skill Evolution) | 《WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution》(arXiv 2026) | |
| 2026.09.07 | 刘昀哲 (Deep Search Agents) | 《DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment》(arXiv 2026) | |
| 2026.07.27 | 杨鑫权 (Region Proposal Network) | 《Prompt-Free Universal Region Proposal Network》(CVPR2026 Oral) | |
| 2026.07.20 | 刘晴老师 (Retinal Disease Screening) | 《Partially Supervised Multiple Retinal Disease Screening》 | |
| 2026.07.13 | 刘翔 (Long Video Understanding) | 《Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding》(CVPR2026) | |
| 2026.07.05 | 李文杰 (Multimodal Agents) | 《XSKILL: Continual Learning from Experience and Skills in Multimodal Agents》(ICML 2026) | |
| 2026.06.29 | 洪程鹏 (Multi-Turn Conversation) | 《LLMs Get Lost In Multi-Turn Conversation》(ICLR 2026) | OpenReview |
| 2026.06.23 | 洪程鹏 (AI-Generated Video Detection) | 《Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale》(ICLR 2026) | |
| 2025.06.15 | 聂正鑫 (Visual Token Pruning) | 《AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models》(ICLR2026) | |
| 2025.06.08 | 郭潇 (Imbalanced MM Learning) | 《Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis》(CVPR2026) | |
| 2025.06.01 | 张骁 (ViT Register & VLM Pruning) | 《OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning》(arxiv2605) | Test-time Register |
| 2025.05.25 | 杨鑫权 (Objective Detection + Diffusion) | 《FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion》(ICLR2026) | OpenReview |
| 2025.05.18 | 刘昀哲 (MM On-Policy Distillation) | 《Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe》(arxiv 2605) | Project |
| 2025.05.11 | 刘翔 (Video Clue Seeking) | 《Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning》(ICML 2026) | Project |
| 2025.04.27 | 张伊男 (Incomplete Multimodal Learning) | 《Anchor-Guided Gradient Alignment for Incomplete Multimodal Learning》(CVPR 2026) | Project |
| 2025.04.20 | 张浩杰 (Token Reduction) | 《Rethinking Token Reduction for Large Vision-Language Models》(CVPR 2026) | |
| 2025.04.13 | 许文卓 (Visual Prompt for Object Detection) | 《DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts》(ICLR 2026) | |
| 2025.03.30 | 聂正鑫 (MIL) | 《ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging》(ICLR 2026) | Project |
| 2025.03.23 | 王培福 (Video Reasoning) | 《Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning》(CVPR 2026) | Project |
| 2025.03.16 | 洪程鹏 (Unified Visual Perception) | 《VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning》(ICLR 2026) | |
| 2025.03.09 | 黄丽娜 (Image Synthesis) | 《PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions》(ICCV 2025) | |
| 2025.03.02 | 李文杰 (Open-Vocabulary Object Detection) | 《WeDetect: Fast Open-Vocabulary Object Detection as Retrieval》(CVPR 2026) | Link |
| 2025.02.02 | 郭力睿 (MLLM + RL) | 《SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning》(NeurIPS 2025) | Openreview |
| 2025.01.26 | 郭潇 (Representation Learning) | 《Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process》(NeurIPS 2025) | OpenReview |
| 2025.01.19 | 刘昀哲 (Visual CoT) | 《Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens》(arxiv 2511) | Project |
| 2025.01.12 | 杨鑫权 (Unified Segmentation Model) | 《SAM 3: Segment Anything with Concepts》(ICCV 2025) | |
| 2025.01.05 | 1. 黄佳隆 (WSI Classification) | 《GMMamba: Group Masking Mamba for Whole Slide Image Classification》(ICCV 2025) | |
| 2025.12.28 | 1. 胡梦云 (Tool-Augmented LLM) | 《Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning》(SIGKDD 2025) | |
| 2025.12.15 | 1. 张灿 (Region Representation) | 《FlexiReg: Flexible Urban Region Representation Learning》(KDD 2025) | |
| 2025.12.08 | 1. 房玮潇 (Segmentation prompt) | 《BioSAM: Generating SAM Prompts From Superpixel Graph for Biological Instance Segmentation》(JBHI 2025) | |
| 2025.12.01 | 1. 刘索妮 (Pathological VLM) | 《Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner》(AAAI 2026) | |
| 2025.11.24 | 1. 刘翔 (Action Detection) | 《Scaling Action Detection: AdaTAD++ with Transformer-Enhanced Temporal-Spatial Adaptation》(ICCV 2025) | |
| 2025.11.17 | 1. 张骁 (Representation Learning) | 《Conditional Representation Learning for Customized Tasks》(NeurIPS2025) | |
| 2025.11.10 | 1. 洪程鹏 (Image Editing) | 《IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout》(TPAMI) | |
| 2025.11.03 | 1. 李文杰 (Visual In-context Reasoning) | 《DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models》(arxiv2503) | |
| 2025.10.27 | 1. 聂正鑫 (Multiple Instance Learning) | 《How Effective Can Dropout Be in Multiple Instance Learning ?》(ICML2025) | |
| 2025.10.20 | 1. 刘昀哲 (Emotion Perception/ Token Purning) | 《Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models》(ICML2025) | |
| 2025.10.13 | 1. 郭潇 (Anomaly Detection) | 《Improving Multimodal Learning Balance and Sufficiency through Data Remixing》(ICML2025) | |
| 2025.09.29 | 1. 郭力睿 (Part-Focused Segmentation) | 《SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment》(ACM MM 2025) | |
| 2025.09.22 | 1. 胡梦云 (Vision-Language Comprehension) | 《ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension》(ACM MM 2025) | |
| 2025.09.15 | 1. 张灿 (Part-Focused Segmentation) | 《CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models》(CVPR 2025) | |
| 2025.09.01 | 1. 房玮潇 (Foreground Segmentation) | 《FOCUS: Towards Universal Foreground Segmentation》 (AAAI 2025) | |
| 2025.08.04 | 1. 刘索妮 (GigaPixel WSI) | 《Learning Heterogeneous Tissues with Mixture of Experts for Gigapixel Whole Slide Images》 (CVPR 2025) | |
| 2025.07.21 | 1. 张骁 (Biomedical Contrastive Learning) | 《BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models》 (CVPR 2025) | |
| 2025.07.07 | 1. 张灿 (Spatial-Temperal Vedio Grounding) | 《Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding》 (ICLR 2025) | |
| 2025.07.07 | 2. 胡梦云 (ViT for Segmentation) | 《Your ViT is Secretly an Image Segmentation Model》 (CVPR 2025) | |
| 2025.06.30 | 1. 李文杰 (Object Detection with MLLM) | 《Open-Det: An Efficient Learning Framework for Open-Ended Detection》 (ICML 2025) | |
| 2025.06.30 | 2. 聂正鑫 (Hierarchical MIL for WSI) | 《Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling》 (NeurIPS 2505) | |
| 2025.06.23 | 1. 房玮潇 (Amodal Instance Segmentation) | 《Segment Anything, Even Occluded》 (CVPR 2025) | |
| 2025.06.23 | 2. 郭力睿 (Knowledge-Based VQA) | 《Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering》 (CVPR 2025) | |
| 2025.06.09 | 1. 张骁 (LLM Inter-representation) | 《Layer by Layer: Uncovering Hidden Representations in Language Models》 (ICML 2025) | |
| 2025.06.09 | 2. 刘索妮 (Fast WSI) | 《Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning》 (CVPR 2025) | |
| 2025.05.30 | 1. 胡梦云 (OV Semantic Segmentation) | 《DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation》 (CVPR 2025) | |
| 2025.05.30 | 2. 郭力睿 (Pre-training for VLM) | 《FLAME:Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training》 (CVPR 2025) | |
| 2025.05.23 | 1. 许文卓 (Object Detection) | 《MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism》 (CVPR 2025) | |
| 2025.05.23 | 2. 张灿 (Prompt Learning for VLM) | 《NLPrompt: Noise-Label Prompt Learning for Vision-Language Models》 (CVPR 2025) | |
| 2025.05.16 | 1. 胡逸琛 (Multi-modal Vision Pre-training) | 《Multi-modal Vision Pre-training for Medical Image Analysis》 (CVPR 2025) | |
| 2025.05.16 | 2. 房玮潇 (Weakly Supervised Semantic Segmentation) | 《Exploring CLIP’s Dense Knowledge for Weakly Supervised Semantic Segmentation》 (CVPR 2025) | |
| 2025.05.09 | 1. 黄佳隆 (WSI) | 《MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification》 (CVPR 2025) | |
| 2025.05.09 | 2. 张骁 (VLM) | 《PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models》 (CVPR 2025) | |
| 2025.05.02 | 1. 黄丽娜 (OW Object Counting) | 《SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Counting》 (arXiv 2504) | |
| 2025.05.02 | 2. 张伊男 (Multimodal Learning) | 《Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition》 (CVPR 2025) | |
| 2025.04.25 | 1. 张灿 (Video MLLM) | 《VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos》 (CVPR 2025) | |
| 2025.04.25 | 2. 胡梦云 (OV Semantic Segmentation) | 《Exploring Simple Open-Vocabulary Semantic Segmentation》 (CVPR 2025) | |
| 2025.04.19 | 1. 张浩杰 (MLLM) | 《From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs》 (arXiv 2502) | |
| 2025.04.19 | 2. 刘索妮 (WSI) | 《FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification》 (CVPR 2025) | |
| 2025.04.11 | 1. 王培福 (LMM) | 《F-LMM:Grounding Frozen Large Multimodal Models》 (CVPR 2025) | |
| 2025.04.11 | 2. 郭力睿 (VLM) | 《DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment》 (CVPR 2025) | |
| 2025.04.04 | 1. 胡逸琛 (KD for VLMs) | 《MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders》 (CVPR 2025) | |
| 2025.04.04 | 2. 房玮潇 (Object Detection) | 《DEIM: DETR with Improved Matching for Fast Convergence》 (CVPR 2025) | |
| 2025.03.28 | 1. 黄佳隆 (VLM for WSI) | 《SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding》 (CVPR 2025) | |
| 2025.03.28 | 2. 许文卓 (OVOD) | 《LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models》 (CVPR 2025) | |
| 2025.03.21 | 1. 王培福 (Spatial-Temporal Understanding) | 《LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding》 (CVPR 2025) | |
| 2025.03.21 | 2. 胡梦云 (Visual Grounding) | 《SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion》 (NeurIPS 2024) | |
| 2025.03.14 | 1. 黄丽娜 (LMM) | 《LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning》 (arXiv 2503) | |
| 2025.03.14 | 2. 刘索妮 (Medical Report Generation) | 《PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation》 (AAAI 2024) | |
| 2025.03.07 | 1. 张灿 (Image Segmentation) | 《A_Simple_Image_Segmentation_Framework_via_In-Context_Examples》 (NeurlPS 2024) | |
| 2025.03.07 | 2. 张骁 (Visual RFT) | 《Visual RFT: Visual Reinforcement Fine Tuning》 (ICCV 2025) | |
| 2025.02.28 | 1. 张伊男 (MML) | 《Balance-aware Sequence Sampling Makes Multi-modal Learning Better》 (arXiv 2501) | |
| 2025.02.28 | 2. 郭力睿 (LLM) | 《DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning》 (arXiv 2501) | |
| 2025.02.17 | 1. 张浩杰 (Pretraining for LLM) | 《Not All Tokens Are What You Need for Pretraining》 (NeurIPS 2024) | |
| 2025.02.17 | 2. 房玮潇 (OV Semantic Segmentation) | 《Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation》 (CVPR 2024) | |
| 2025.02.10 | 1. 胡逸琛 (Multimodal Classification) | 《Facilitating Multimodal Classification via Dynamically Learning Modality Gap》 (NeurIPS 2024) | |
| 2025.02.10 | 2. 许文卓 (Open-Ended Object Detection) | 《Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts》 (NeurIPS 2024) | |
| 2025.01.20 | 1. 黄佳隆 (PATHOLOGY Dataset) | 《PATHGEN-1.6M: 1.6 MILLION PATHOLOGY IMAGETEXT PAIRS GENERATION THROUGH MULTI-AGENT COLLABORATION》 (arXiv 2407) | |
| 2025.01.20 | 2. 张骁 (Foundational Pretraining) | 《MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise》 (MICCAI 2024) | |
| 2025.01.13 | 1. 张浩杰 (PEFT) | 《Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?》 (arXiv 2410) | |
| 2025.01.13 | 2. 王培福 (MLLM) | 《LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token》 (arXiv 2501) | |
| 2025.01.06 | 1. 刘索妮 (Unsupervised WSI Representation Learning) | 《Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology》 (CVPR 2024) | |
| 2025.01.06 | 2. 李文杰 (OVD) | 《SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection》 (ACM MM 2024) | |
| 2024.12.30 | 1. 张灿 (Multi-Modality Models) | 《G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models》 (NeurIPS 2024) | |
| 2024.12.30 | 2. 胡梦云 (Generalized Referring Expression Segmentation) | 《CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation》 (arXiv 2405) | |
| 2024.12.23 | 1. 张伊男 (Zero-Shot Visual Recognition) | 《Grounding Descriptions in Images informs Zero-Shot Visual Recognition》 (arXiv 2412) | |
| 2024.12.23 | 2. 虞昊泽 (Missing Modality) | 《Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models》 (ECCV 2024) | |
| 2024.12.16 | 1. 黄丽娜 (One-Shot SAM) | 《Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain》 (arXiv 2411) | |
| 2024.12.16 | 2. 房玮潇 (Object Counting) | 《Point, Segment and Count: A Generalized Framework for Object Counting》 (CVPR 2024) | |
| 2024.12.9 | 1. 胡逸琛 (Missing Modality) | 《Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness》 (NeurIPS 2024) | |
| 2024.12.9 | 2. 许文卓 (DI-MaskDINO) | 《DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model》 (NeurIPS 2024) | |
| 2024.12.2 | 1. 黄佳隆 (WSI Analysis) | 《Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis》 (NeurIPS 2024) | |
| 2024.12.2 | 2. 张骁 (RL for SAM) | 《AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning》 (CVPR 2024) | |
| 2024.11.25 | 1. 张浩杰 (Safety of VLM) | 《Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment》 (arXiv 2411) | |
| 2024.11.25 | 2. 王培福 (Streaming Video) | 《VideoLLM-online: Online Video Large Language Model for Streaming Video》 (CVPR 2024) | |
| 2024.11.18 | 1. 张灿 (Large Multimodal Model) | 《PixelLM: Pixel Reasoning with Large Multimodal Model》 (CVPR 2024) | |
| 2024.11.18 | 2. 胡梦云 (Generalized Referring Expression Segmentation) | 《Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation》 (arXiv 2405) | |
| 2024.11.11 | 1. 张伊男 (Missing Modality) | 《Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts》 (NeurIPS 2024 Spotlight) | |
| 2024.11.11 | 2. 虞昊泽 (Missing Modality) | 《Leveraging Knowledge of Modality Experts for Incomplete Multimodal Learning》 (ACM MM 2024) | |
| 2024.11.4 | 1. 黄丽娜 (Open-World Instance Segmentation) | 《SOS: Segment Object System for Open-World Instance Segmentation With Object Priors》 (ECCV 2024) | |
| 2024.11.4 | 2. 房玮潇 (Foundation Models) | 《Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models》 (NeurIPS 2024) | |
| 2024.10.28 | 1. 胡逸琛 (Multimodal Learning) | 《Robust Multimodal Learning via Representation Decoupling》 (ECCV 2024) | |
| 2024.10.28 | 2. 许文卓 (LMM) | 《LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models》 (ECCV 2024) | |
| 2024.10.21 | 1. 黄佳隆 (Few-Shot Learning) | 《FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification》 (NeurIPS 2024) | |
| 2024.10.21 | 2. 张骁 (LMM) | 《AVG-LLaVA: A Large Multimodal Model with Adaptive Visual Granularity》 (arxiv 2410) | |
| 2024.10.14 | 1. 张浩杰 (Continual Learning) | 《InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning》 (CVPR 2024) | |
| 2024.10.14 | 2. 王培福 (Video Moment Retrieval) | 《Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval》 (ACM MM 2024 Oral) | |
| 2024.10.7 | 1. 虞昊泽 (Multimodal Classification) | 《Multimodal Classification via Modal-Aware Interactive Enhancement》 (arxiv 2407) | |
| 2024.10.7 | 2. 房玮潇 (Generalist Vision Transformer) | 《GiT: Towards Generalist Vision Transformer through Universal Language Interface》 (ECCV 2024) | |
| 2024.9.30 | 1. 黄丽娜 (Medical Foundation Models) | 《Low-Rank Knowledge Decomposition for Medical Foundation Models》 (CVPR 2024) | |
| 2024.9.30 | 2. 许文卓 (Generic Object Detection) | 《T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy》 (ECCV 2024) | |
| 2024.9.23 | 1. 胡逸琛 (Multimodal Learning) | 《Multimodal Representation Learning by Alternating Unimodal Adaptation》 (CVPR 2024) | |
| 2024.9.23 | 2. 黄佳隆 (Vision-Language Models) | 《PromptKD: Unsupervised Prompt Distillation for Vision-Language Models》 (CVPR 2024) | |
| 2024.9.16 | 1. 张伊男 (Multimodal Learning) | 《Detached and Interactive Multimodal Learning》 (ACM MM 2024) | |
| 2024.9.16 | 2. 张骁 (Unified Foundation Model) | 《VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation》 (arxiv 2409) | |
| 2024.9.9 | 1. 张浩杰 (Visual Language Model) | 《CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding》 (ICLR 2024) | |
| 2024.9.9 | 2. 王培福 (Video Temporal Grounding) | 《Training-free Video Temporal Grounding using Large-scale Pre-trained Models》 (ECCV 2024) | |
| 2024.9.2 | 1. 黄丽娜 (Semantic Segmentation) | 《MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment》 (ECCV 2024) | |
| 2024.9.2 | 2. 黄佳隆 (Low-Shot Image Classification) | 《Large Language Models are Good Prompt Learners for Low-Shot Image Classification》 (CVPR 2024) | |
| 2024.8.26 | 1. 胡逸琛 (Multimodal Learning) | 《Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity》 (ICML 2024) | |
| 2024.8.26 | 2. 许文卓 (Ultrasound Image Segmentation) | 《CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation》 (ECCV 2024) | |
| 2024.8.19 | 1. 张浩杰 (Scaling MLLM) | 《SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models》 (ICML 2024) | |
| 2024.8.19 | 2. 王培福 (Action Localization) | 《HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization》 (ECCV2024) | |
| 2024.8.12 | 1. 张伊男 (High-Resolution VLM) | 《FlexAttention for Efficient High-Resolution Vision-Language Models》 (ECCV 2024) | |
| 2024.8.12 | 2. 张骁 (Vision-Language Pretraining) | 《Modeling Caption Diversity in Contrastive Vision-Language Pretraining》 (ICML 2024) | |
| 2024.7.29 | 1. 黄丽娜 (Domain Generalized Segmentation) | 《Textual Query-Driven Mask Transformer for Domain Generalized Segmentation》 (ECCV 2024) | |
| 2024.7.29 | 2. 许文卓 (Vision-Language Model) | 《Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models》 (ICML 2024) | |
| 2024.7.22 | 1. Luming Liang (NeRF) | [Motion Representations & CaesarNeRF] | |
| 2024.7.15 | 1. 胡逸琛 (Knowledge Distillation) | 《Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities》 (CVPR 2024) | |
| 2024.7.15 | 2. 黄佳隆 (Prompt Learning) | 《Prompting Vision Foundation Models for Pathology Image Analysis》 (CVPR 2024) | |
| 2024.7.8 | 1. 张浩杰 (Report Generation) | 《InVERGe: Intelligent Visual Encoder for Bridging Modalities in Report Generation》 (CVPR 2024) | |
| 2024.7.8 | 2. 王培福 (VideoLLM) | 《KeyVideoLLM: Towards Large-scale Video Keyframe Selection》 (arxiv 2407) | |
| 2024.7.1 | 1. 张伊男 (MLLM) | 《Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts》 (arxiv 2405) | |
| 2024.6.24 | 1. 许文卓 (Zero-Shot Classification) | 《CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification》 (CVPR 2024) | |
| 2024.6.24 | 2. 张骁 (Model Pruning) | 《mlp can be a good transformer learner》 (CVPR 2024) | |
| 2024.6.17 | 1. 范筱峰 (Object Pose Estimation) | 《CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge》 (TCSVT 2024) | |
| 2024.6.17 | 2. 胡逸琛 (FairCLIP) | 《FairCLIP: Harnessing Fairness in Vision-Language Learning》 (CVPR 2024) | |
| 2024.6.10 | 1. 刘宇帆 (Continual Learning) | 《Convolutional Prompting meets Language Models for Continual Learning》 (CVPR 2024) | |
| 2024.6.10 | 2. 黄佳隆 (Slide Representation Learning) | 《Transcriptomics-guided Slide Representation Learning in Computational Pathology》 (CVPR 2024 Oral) | |
| 2024.6.3 | 1. 郭杰 (Multimodal Reasoning) | 《Question Aware Vision Transformer for Multimodal Reasoning》 (arxiv 2402) | |
| 2024.6.3 | 2. 黄丽娜 (Visual Representation Learning) | 《Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning》 (arxiv 2405) | |
| 2024.5.27 | 1. 张浩杰 (MLLM) | 《Libra: Building Decoupled Vision System on Large Language Models》 (ICML 2024) | |
| 2024.5.27 | 2. 王培福 (Video Understanding) | 《OmniVid: A Generative Framework for Universal Video Understanding》 (CVPR 2024) | |
| 2024.5.20 | 1. 丁梓原 (Grounding MLLM) | 《GROUNDHOG: Grounding Large Language Models to Holistic Segmentation》 (CVPR 2024) | |
| 2024.5.20 | 2. 张伊男 (Self-Supervised Pre-Training) | 《MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis》 (arxiv 2404) | |
| 2024.5.13 | 1. 范筱峰 (Open-Vocabulary 9D Pose Estimation) | 《OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation》 (arxiv 2403) | |
| 2024.5.13 | 2. 胡逸琛 (Contrastive Learning) | 《VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis》 (CVPR 2024) | |
| 2024.5.6 | 1. 李高杰 (WSI Classification) | 《Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction》 (CVPR 2024) | |
| 2024.5.6 | 2. 刘宇帆 (Continual Learning Panoptic Segmentation) | 《ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning》 (CVPR 2024) | |
| 2024.4.29 | 1. 张浩杰 (Contrastive Learning) | 《MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning》 (arxiv 2402) | |
| 2024.4.29 | 2. 王培福 (MLLM Segmentation) | 《GSVA: Generalized Segmentation via Multimodal Large Language Models》 (CVPR 2024) | |
| 2024.4.22 | 1. 黄佳隆 (Vision-Language Pre-training) | 《Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework》 (CVPR 2024) | |
| 2024.4.22 | 2. 许文卓 (Open-Vocabulary Object Detection) | 《YOLO-World: Real-Time Open-Vocabulary Object Detection》 (CVPR 2024) | |
| 2024.4.15 | 1. 丁梓原 (Domain Generalized Semantic Segmentation) | 《Collaborating Foundation Models for Domain Generalized Semantic Segmentation》 (CVPR 2024) | |
| 2024.4.15 | 2. 黄丽娜 (Long-Tailed Transformer) | 《DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets》 (CVPR 2024) | |
| 2024.4.8 | 1. 郭杰 (Whole Slide Image) | 《Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis》 (CVPR 2024) | |
| 2024.4.8 | 2. 张伊男 (Multi-Task LoRA) | 《MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning》 (CVPR 2024) | |
| 2024.4.1 | 1. 范筱峰 (Multi-Task & Depth Estimation) | 《Depth anything: Unleashing the power of large-scale unlabeled data》 (arxiv 2401) | |
| 2024.4.1 | 2. 胡逸琛 (Vision Mamba) | 《Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model》 (arxiv 2401) | |
| 2024.3.25 | 1. 张浩杰 (MLLM) | 《Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections》 (arxiv 2402) | |
| 2024.3.25 | 2. 王培福 (MLLM) | 《UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All》 (CVPR 2024) | |
| 2024.3.18 | 1. 刘宇帆 (Continual Segmentation) | 《Continual Segmentation with Disentangled Objectness Learning and Class Recognition》 (CVPR 2024) | |
| 2024.3.18 | 2. 许文卓 (Open-Vocabulary Segmentation) | 《Open-Vocabulary Segmentation with Semantic-Assisted Calibration》 (CVPR 2024) | |
| 2024.3.11 | 1. 丁梓原 (VFM-based DG semantic segmentation) | 《Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation》 (CVPR 2024) | |
| 2024.3.11 | 2. 黄佳隆 (Universe Segmentation) | 《OMG-Seg: Is One Model Good Enough For All Segmentation?》 (CVPR 2024) | |
| 2024.3.4 | 1. 李高杰 (SAM-like) | 《EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything》 (CVPR 2024) | |
| 2024.3.4 | 2. 黄丽娜 (WSI Classification) | 《Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology》 (CVPR 2024) | |
| 2024.2.26 | 1. 郭杰 (Open-Vocabulary Classification) | 《TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training》 (AAAI 2024) | |
| 2024.2.26 | 2. 张伊男 (MLLM-based Clinical Prediction) | 《Multimodal Clinical Trial Outcome Prediction with Large Language Models》 (arxiv 2402) | |
| 2024.2.5 | 1. 范筱峰 (NeRF / Reconstruction Model) | 《PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction》 (ICLR 2024) | |
| 2024.2.5 | 2. 胡逸琛 (Contrast Learning Regression) | 《Rank-N-Contrast: Learning Continuous Representations for Regression》 (NeurIPS 2023) | |
| 2024.1.29 | 1. 王培福 (Multi-Modal Video Action Recognition) | 《M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition》 (AAAI 2024) | |
| 2024.1.29 | 2. 张浩杰 (Multi-Modal Ensemble Learning) | 《Multimodal Pathway:Improve Transformers with Irrelevant Data from Other Modalities》 (arxiv 2401) | |
| 2024.1.22 | 1. 李高杰 (Open-World Segmentation) | 《UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding》 (arxiv 2401) | |
| 2024.1.22 | 2. 许文卓 (Open-Vocabulary Segmentation) | 《Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively》 (arxiv 2401) | |
| 2024.1.15 | 1. 刘宇帆 (Incremental Learning) | 《Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning》 (AAAI 2024) | |
| 2024.1.15 | 2. 黄佳隆 (VLM Prompting Survey) | 《A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models》 (arxiv 2307) | |
| 2024.1.8 | 1. 李高杰 (VLM Prompting) | 《Learning to Prompt with Text Only Supervision for Vision-Language Models》 (arxiv 2401) | |
| 2024.1.8 | 2. 黄丽娜 (Universal Image Segmentation) | 《Unsupervised Universal Image Segmentation》 (arxiv 2312) | |
| 2024.1.3 | 1. 丁梓原 (VLM-based DG Segmentation) | 《VLTSeg: Simple Transfer of CLIP-Based Vision-Language Representations for Domain Generalized Semantic Segmentation》 (arxiv 2312) | |
| 2024.1.3 | 2. 张伊男 (Large Multi-Modal Model) | 《NExT-Chat: An LMM for Chat, Detection and Segmentation》 (arxiv 2311) | |
| 2023.12.25 | 1. 郭杰 (Foundation model & LLM) | 《From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models》 (arxiv 2310) | |
| 2023.12.25 | 2. 胡逸琛 (Multi-Task Transfer Learning) | 《VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense》 (AAAI 2024) | |
| 2023.12.18 | 1. 王培福 (Large Multi-Modal Model) | 《Pixel Aligned Language Models》 (arxiv 2312) | |
| 2023.12.18 | 2. 张浩杰 (Large Multi-Modal Model) | 《OneLLM: One Framework to Align All Modalities with Language》 (arxiv 2312) | |
| 2023.12.11 | 1. 范筱峰 (Category-Level Pose Estimation) | 《SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation》 (arxiv 2311) | |
| 2023.12.11 | 2. 黄佳隆 (Visual In-Context Model) | 《Sequential Modeling Enables Scalable Learning for Large Vision Models》 (arxiv 2312) | |
| 2023.12.4 | 1. 黄丽娜 (LLM-based Few-shot Segmentation) | 《LLaFS: When Large-Language Models Meet Few-Shot Segmentation》 (arxiv 2311) | |
| 2023.12.4 | 2. 许文卓 (Open-Vocabulary Segmentation) | 《CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction》 (arxiv 2310) | |
| 2023.11.27 | 1. 刘宇帆 (Prompt-Based Continual Learning) | 《Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality》 (NeurIPS 2023) | |
| 2023.11.27 | 2. 张伊男 (Open-Vocabulary Object Detection) | 《DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection》 (arxiv 2310) | |
| 2023.11.20 | 1. 李高杰 (LLM-based Classification) | 《Towards Open-Ended Visual Recognition with Large Language Model》 (arxiv 2311) | |
| 2023.11.20 | 2. 胡逸琛 (CLIP-prompts) | 《Waffling around for Performance: Visual Classification with Random Words and Broad Concepts》 (ICCV 2023) | |
| 2023.11.15 | 1. 丁梓原 (LMM-based Grounding & Segmentation) | 《GLaMM : Pixel Grounding Large Multimodal Model》 (arxiv 2311) | |
| 2023.11.15 | 2. 黄佳隆 (Vision Language Pretraining) | 《SILC: Improving Vision Language Pretraining with Self-Distillation》 (arxiv 2310) | |
| 2023.11.9 | 1. 郭杰 (LLM-based Object Detection) | 《CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection》 (ICCV 2023) | |
| 2023.11.9 | 2. 黄丽娜 (VLM-based Incremental Learning) | 《Class Incremental Learning with Pre-trained Vision-Language Models》 (arxiv 2310) | |
| 2023.11.2 | 1. 张浩杰 (Vision-Language Models) | 《GraphAdapter: Tuning Vision-Lunguage Models With Dual Knowledge Graph》 (NeurIPS 2023) | |
| 2023.11.2 | 2. 王培福 (Open World LLM-based Agent) | 《Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds》 (arxiv 2310) | |
| 2023.10.26 | 1. 范筱峰 (3D point cloud prompt tuning) | 《Instance-aware dynamic prompt tuning for pre-trained point cloud models》 (ICCV 2023) | |
| 2023.10.26 | 2. 张伊男 (Open World Object Detection) | 《Detecting Everything in the Open World: Towards Universal Object Detection》 (CVPR 2023) | |
| 2023.10.19 | 1. 刘宇帆 (VIT backbone) | 《Self-regulating Prompts: Foundational Model Adaptation without Forgetting》 (ICCV 2023) | |
| 2023.10.19 | 2. 胡逸琛 (Universal medical segmentation) | 《Universeg: Universal medical image segmentation》 (ICCV 2023) | |
| 2023.10.12 | 1. 黄丽娜 (VIT backbone) | 《DiT: Efficient Vision Transformers with Dynamic Token Routing》 (arxiv 2308) | |
| 2023.10.12 | 2. 黄佳隆 (WSI Classification) | 《Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification》 (ICCV 2023) | |
| 2023.10.5 | 1. 郭杰 (Multimodal-LLM) | 《Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models》 (NeurIPS 2023) | |
| 2023.10.5 | 2. 张伊男 (Object Detection) | 《Dense Distinct Query for End-to-End Object Detection》 (CVPR 2023) | |
| 2023.9.28 | 1. 陈琼朴 (Multimodal Learning) | 《MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning》 (CVPR 2023) | |
| 2023.9.28 | 2. 钟晴 (Domain Adaptation Semantic Segmantation) | 《To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation》 (ICCV 2023) | |
| 2023.9.21 | 1. 刘宇帆 (VLM-based Continual Learning) | 《Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models》 (ICCV 2023) | |
| 2023.9.21 | 2. 李高杰 (Object Detection) | 《Enhanced Training of Query-Based Object Detection via Selective Query Recollection》 (CVPR 2023) | |
| 2023.9.11 | 1. 丁梓原 (Test-Time Adaptation) | 《On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion》 (ICCV 2023 oral) | |
| 2023.9.11 | 2. 范筱峰 (3D Open-Vocabulary detection) | 《Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation》 (CVPR 2023) | |
| 2023.8.28 | 1. 郭杰 (Object Detection) | 《Less is More: Focus Attention for Efficient DETR》 (ICCV 2023) | |
| 2023.8.21 | 1. 丁梓原 (Panoramic Semantic Segmentation) | 《Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation》 (ICCV 2023) | |
| 2023.8.14 | 1. 黄佳隆 (Weakly-supervised WSI) | 《Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification》 (CVPR 2023) | |
| 2023.7.31 | 1. 胡逸琛 (Multimodal Learning) | 《Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data》 (CVPR 2023) | |
| 2023.7.24 | 1. 范筱峰 (6D Object Pose Estimation) | 《TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation》 (CVPR 2023) | |
| 2023.7.24 | 2. 黄丽娜 (Vision Transformer) | 《Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution》 (arxiv 2023) | |
| 2023.7.17 | 1. 李高杰 (SAM-like) | 《Semantic-SAM: Segment and Recognize Anything at Any Granularity》 (arxiv 2023) | |
| 2023.7.17 | 2. 张伊男 (Object Detection) | 《Detection Hub:Unifying Object Detection Datasets via Query Adaptation on Language Embedding》 (CVPR 2023) | |
| 2023.7.10 | 1. 刘宇帆 (Incremental Learning) | 《Endpoints Weight Fusion for Class Incremental Semantic Segmentation》 (CVPR 2023) | |
| 2023.7.10 | 2. 胡逸琛 (Multi-Modal Learning) | 《Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling》 (CVPR 2023) | |
| 2023.7.3 | 1. 丁梓原 (SAM综述) | 《A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering》 (arxiv 2023) | |
| 2023.7.3 | 2. 黄佳隆 (Self-Supervised Learning) | 《Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning》 (CVPR 2023) | |
| 2023.6.26 | 1. 郭杰 (Object Detection) | 《Detection Transformer with Stable Matching》 (arxiv 2023) | |
| 2023.6.26 | 2. 陈琼朴 (Multimodal Learning) | 《PMR: Prototypical Modal Rebalance for Multimodal Learning》 (CVPR 2023) | |
| 2023.6.19 | 1. 范筱峰 (6D Object Pose Estimation) | 《POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referenc》 (arxiv 2023) | |
| 2023.6.19 | 2. 黄丽娜 (Object Detection) | 《USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model》 (arxiv 2023) | |
| 2023.6.12 | 1. 刘宇帆 (Incremental Learning) | 《CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning》 (CVPR 2023) | |
| 2023.6.12 | 2. 张伊男 (Object Detection) | 《One-to-Few Label Assignment for End-to-End Dense Detection》 (CVPR 2023) | |
| 2023.6.5 | 1. 丁梓原 (Domain Adaptation) | 《Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation》 (arXiv 2023) | |
| 2023.5.28 | 1. 梁毅雄 (视觉大模型) | [Visual Foundation Models & Parameter-Efficient Learning] | |
| 2023.5.28 | 2. 张朝君 (Instance Segmentation) | 《Vision Transformers Are Good Mask Auto-Labelers》 (CVPR 2023) | |
| 2023.5.22 | 1. 李胜琦 (Semantic Segmentation) | 《Side Adapter Network for Open-Vocabulary Semantic Segmentation》 (CVPR 2023) | |
| 2023.5.22 | 2. 李高杰 (Object Detection) | 《DETRs Beat YOLOs on Real-time Object Detection》 (arXiv 2023) | |
| 2023.5.15 | 1. 吕乐乐 (Segmentation) | 《AutoFocusFormer: Image Segmentation off the Grid》(CVPR 2023) | |
| 2023.5.15 | 2. 范晓峰 (3D Reconstruction) | 《Anything-3D: Towards Single-view Anything Reconstruction in the Wild》(arXiv 2023) | |
| 2023.5.8 | 1. 陈雁 (Weakly-supervised Learning) | 《WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation》 (arXiv 2023) | |
| 2023.5.8 | 2. 刘宇帆 (Continual Learning) | 《CoMFormer: Continual Learning in Semantic and Panoptic Segmentation》 (CVPR 2023) | |
| 2023.5.4 | 1. 曾海龙 (Semantic Segmentation) | 《MP-Former: Mask-Piloted Transformer for Image Segmentation》 (CVPR 2023) | |
| 2023.5.4 | 2. 李高杰 (Open-Set Object Detection) | 《Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection》 (arXiv 2023) | |
| 2023.4.24 | 1. 李胜琦 (Semantic Segmentation) | 《Leveraging Hidden Positives for Unsupervised Semantic Segmentation》 (CVPR 2023) | |
| 2023.4.24 | 2. 丁梓原 (Semantic Segmentation) | 《Exploring Sparse Visual Prompt for Cross-domain Semantic Segmentation》 (arXiv 2023) | |
| 2023.4.17 | 1. 张朝君 (Instance Segmentation) | 《BoxSnake: Polygonal Instance Segmentation with Box Supervision》(arXiv 2023) | |
| 2023.4.17 | 2. 郭杰 (Object Detection) | 《Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR》 (CVPR 2023) | |
| 2023.4.10 | 1. 刘浩天 (Segmentation) | 《Segment Anything》 (arXiv 2023) | |
| 2023.4.10 | 2. 范晓峰 (6D Object Pose Estimation) | 《Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild》 (arXiv 2022) | |
| 2023.4.3 | 1. 吕乐乐 (Instance Segmentation) | 《FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation》 (CVPR 2023) | |
| 2023.4.3 | 2. 刘宇帆 (Incremental learning) | 《Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation》 (CVPR 2023) | |
| 2023.3.27 | 1. 陈雁 (Weakly-supervised Learning) | 《Token Contrast for Weakly-Supervised Semantic Segmentation》 (CVPR 2023) | |
| 2023.3.27 | 2. 李高杰 (Transformer) | 《BiFormer: Vision Transformer with Bi-Level Routing Attention》 (CVPR 2023) | |
| 2023.3.20 | 1. 张朝君 (Instance Segmentation) | 《SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation》 (CVPR 2023) | |
| 2023.3.20 | 2. 丁梓原 (Domain Adaptation) | 《Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation》 (arXiv 2023) | |
| 2023.3.13 | 1. 曾海龙 (Semantic Segmentation) | 《DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction》 (CVPR 2023) | |
| 2023.3.13 | 2. 郭杰 (Transformer) | 《Focal Modulation Networks》 (NeurIPS 2022) | |
| 2023.3.6 | 1. 刘宇帆 (Medical Image Segmentation) | 《3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation》 (ILCR 2023) | |
| 2023.3.6 | 2. 范晓峰 (6D Pose Estimation) | 《OnePose: One-Shot Object Pose Estimation Without CAD Models》 (CVPR 2022) | |
| 2023.2.27 | 1. 李胜琦 (Semantic Segmentation) | 《Semantic Segmentation via Pixel-to-Center Similarity Calculation》 (arXiv 2023) | |
| 2023.2.27 | 2. 陈雁 (Weakly-supervised Learning) | 《CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation》 (arXiv 2023) | |
| 2023.2.18 | 1. 吕乐乐 (Visual Recognition) | 《Visual Recognition with Deep Nearest Centroids 》 (ICLR 2023) | |
| 2023.2.18 | 2. 李高杰 (Transformer) | 《Vision Transformer Adapter for Dense Predictions》 (ICLR 2023) | |
| 2023.2.11 | 1. 张朝君 (Transformer) | 《Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation》 (arXiv 2022) | |
| 2023.2.11 | 2. 丁梓原 (Domain Adaptation) | 《MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation》 (arXiv 2023) | |
| 2023.2.4 | 1. 曾海龙 (Semi-supervised Learning) | 《Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation》 (arXiv 2022) | |
| 2023.2.4 | 2. 郭杰 (Object Detection) | 《DESTR: Object Detection with Split Transformer》 (CVPR2022) | |
| 2023.1.28 | 1. 范筱峰 (6D Pose Estimation) | 《CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers》 (WACV 2023) | |
| 2023.1.14 | 1. 吕乐乐 (Semantic Segmentation) | 《Head-Free Lightweight Semantic Segmentation with Linear Transformer》 (AAAI 2023) | |
| 2023.1.14 | 2. 李胜琦 (Semantic Segmentation) | 《Self-Supervised Visual Representation Learning with Semantic Grouping》 (NeurIPS 2022) | |
| 2023.1.7 | 1. 张朝君 (Instance Segmentation) | 《AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation》 (arXiv 2022) | |
| 2023.1.7 | 2. 陈雁 (Semantic Segmentation) | 《Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation》 (NeurIPS 2022) | |
| 2022.12.31 | 1. 李高杰 (Object Detection) | 《Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors》 (arXiv 2022) | |
| 2022.12.31 | 2. 刘宇帆 (Semi-supervised Learning) | 《Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images》 (Medical Image Analysis 2023) | |
| 2022.12.17 | 1. 张永胜 (网络结构) | 《On the Integration of Self-Attention and Convolution》 (CVPR 2022) | |
| 2022.12.17 | 2. 丁梓原 (Domain Adaptation) | 《MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation》 (arXiv 2022) | |
| 2022.12.10 | 1. 耿瑞祥 (Domain Generalization) | 《Grounding Visual Representations with Texts for Domain Generalization》 (ECCV 2022) | |
| 2022.12.10 | 2. 郭杰 (Object Detection) | 《DETRs with Hybrid Matching》 (arXiv 2022) | |
| 2022.12.3 | 1. 曾海龙 (Semantic Segmentation) | 《Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization》 (NeurIPS 2022) | |
| 2022.12.3 | 2. 范筱峰 (6D Pose Estimation) | 《PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation》 (CoRL 2022) | |
| 2022.11.26 | 1. 吕乐乐 (Transformer) | 《GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation》 (ICLR 2023) | |
| 2022.11.26 | 2. 刘宇帆 (Continual Learning) | 《Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation》 (NeurIPS 2022) | |
| 2022.11.19 | 1. 陈雁 (Semantic Segmentation) | 《Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling》 (IJCV 2022) | |
| 2022.11.19 | 2. 丁梓原 (Domain Adaptation) | 《Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation》 (NeurIPS 2022) | |
| 2022.11.12 | 1. 李胜琦 (Semantic Segmentation) | 《NamedMask: Distilling Segmenters from Complementary Foundation Models》 (arXiv 2022) | |
| 2022.11.12 | 2. 李高杰 (Object Detection) | 《Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment》 (arXiv 2022) | |
| 2022.11.5 | 1. 郭杰 (Object Detection) | 《Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks》 (NeurIPS 2022) | |
| 2022.11.4 | 1. 范筱峰 (3D Object Detection) | 3D目标检测 串讲 | |
| 2022.10.22 | 1. 张朝君 (Semantic Segmentation) | 《Learning Equivariant Segmentation with Instance-Unique Querying》 (NeurIPS 2022) | |
| 2022.10.22 | 2. 刘宇帆 (Continual Learning) | 《Continual Learning with Lifelong Vision Transformer》 (CVPR 2022) | |
| 2022.10.15 | 1. 曾海龙 (Semantic Segmentation) | 《Learning from Future: A Novel Self-Training Framework for Semantic Segmentation》 (NeurIPS 2022) | |
| 2022.10.15 | 2. 李高杰 (Object Detection) | 《Open-Vocabulary DETR with Conditional Matching》 (ECCV 2022) | |
| 2022.10.5 | 1. 李胜琦 (Semantic Segmentation) | 《Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation》 (arXiv 2022) | |
| 2022.10.5 | 2. 丁梓原 (Domain Adaptation) | 《HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation》 (ECCV 2022) | |
| 2022.9.28 | 1. 吕乐乐 (Semantic Segmentation) | 《SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation》 (NeurIPS 2022) | |
| 2022.9.28 | 2. 郭杰 (Object Detection) | 《ObjectBox: From Centers to Boxes for Anchor-Free Object Detection》 (ECCV 2022) | |
| 2022.9.21 | 1. 陈雁 (Semantic Segmentation) | 《L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation》(CVPR 2022) | |
| 2022.9.21 | 2. 范筱峰 (3D Object Detection) | 《MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection》 (CVPR 2022) | |
| 2022.9.14 | 1. 张朝君 (Instance Segmentation) | 《Mask Transfiner for High-Quality Instance Segmentation》 (CVPR 2022) | |
| 2022.9.14 | 2. 刘宇帆 (Semantic Segmentation) | 《RBC:Rectifying the Biased Context in Continual Semantic Segmentation》 (ECCV 2022) | |
| 2022.9.5 | 1. 曾海龙 (Domain Adaptation) | 《DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation》 (ECCV 2022) | |
| 2022.9.5 | 2. 李高杰 (Object Detection) | 《Exploring Plain Vision Transformer Backbones for Object Detection》 (ECCV 2022) | |
| 2022.8.29 | 1. 李胜琦 (Semantic Segmentation) | 《TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation》 (ECCV 2022 oral) | |
| 2022.8.29 | 2. 丁梓原 (Domain Adaptation) | 《Category Contrast for Unsupervised Domain Adaptation in Visual Tasks》 (CVPR 2022) | |
| 2022.8.15 | 1. 吕乐乐 (Semantic Segmentation) | 《Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation》 (ECCV 2022) | |
| 2022.8.15 | 2. 郭杰 (Object Detection) | 《Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection》 (ECCV 2022) | |
| 2022.8.8 | 1. 张朝君 (Weakly Supervised Learning) | 《Box-supervised Instance Segmentation with Level Set Evolution》 (ECCV 2022) | |
| 2022.8.8 | 2. 范筱峰 (3D Object Detection) | 《An end-to-end transformer model for 3d object detection》 (ICCV 2021) | |
| 2022.8.1 | 1. 曾海龙 (Transformer) | 《MetaFormer Is Actually What You Need for Vision》 (CVPR 2022 Oral) | |
| 2022.8.1 | 2. 李高杰 (Transformer) | 《DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection》 (arXiv 2022) | |
| 2022.7.25 | 1. 陈雁 (Semantic Segmentation) | 图像级标注弱监督语义分割串讲 | |
| 2022.7.18 | 1. 李胜琦 (Semantic Segmentation) | 《ReCo: Retrieve and Co-segment for Zero-shot Transfer》 (arXiv 2022) | |
| 2022.7.18 | 2. 刘宇帆 (Semantic Segmentation) | 《Representation Compensation Networks for Continual Semantic Segmentation》 (CVPR 2022) | |
| 2022.7.11 | 1. 陈雁 (Semantic Segmentation) | 《Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation》 (CVPR 2022) | |
| 2022.7.11 | 2. 丁梓原 (Domain Adaptivation) | 《ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation》 (CVPR 2022) | |
| 2022.7.4 | 1. 吕乐乐 (Semantic Segmentation) | 《Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers》 (CVPR 2022) | |
| 2022.7.4 | 2. 郭杰 (Transformer) | 《DAB-DETR: Dynamic anchor boxes are better queries for DETR》 (ICLR 2022) | |
| 2022.6.27 | 1. 李高杰 (Transformer) | 《DN-DETR: Accelerate DETR Training by Introducing Query DeNoising》 (CVPR 2022 Oral) | |
| 2022.6.27 | 2. 张朝君 (Weakly Supervised Learning) | 《Revisiting Weakly Supervised Pre-Training of Visual Perception Models》 (CVPR 2022) | |
| 2022.6.20 | 1. 曾海龙 (Domain Adaptivation) | 《DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation》 (CVPR 2022) | |
| 2022.6.13 | 1. 李胜琦 (Semantic Segmentation) | 《Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization》 (CVPR 2022 Oral) | |
| 2022.6.13 | 2. 陈雁 (Semantic Segmentation) | 《CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation》 (CVPR 2022) | |
| 2022.6.6 | 1. 刘宇帆 (Domain Adaptivation) | 《Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation》 (CVPR 2022) | |
| 2022.6.6 | 2. 耿瑞祥 (Knowledge Distillation) | 《Knowledge distillation: A good teacher is patient and consistent》 (CVPR 2022 Oral) | |
| 2022.5.30 | 1. 范筱峰 (View Synthesis) | 《NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis》 (ECCV 2020) | |
| 2022.5.30 | 2. 吕乐乐 (Contrastive Learning) | 《Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo》 (CVPR 2022) | |
| 2022.5.23 | 1. 张永胜 (Self-supervised Learning) | 《DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis》 (CVPR 2022) | |
| 2022.5.23 | 2. 张朝君 (Semantic Segmentation) | 《Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation》 (CVPR 2021) | |
| 2022.5.16 | 1. 曾海龙 (Semantic Segmentation) | 《Domain-Agnostic Prior for Transfer Semantic Segmentation》 (CVPR 2022) | |
| 2022.5.16 | 2. 丁梓原 (Semantic Segmentation) | 《Semantic-Aware Domain Generalized Segmentation》 (CVPR 2022 Oral) | |
| 2022.5.9 | 1. 李胜琦 (Knowledge Distillation) | 《Generalized Knowledge Distillation via Relationship Matching》 (TPAMI) | |
| 2022.5.9 | 2. 赵嘉伟 (Continual Learning) | 《Re-examining Distillation For Continual Object Detection》 (arXiv 2022) | |
| 2022.5.2 | 1. 刘浩天 (Object Detection) | 《AdaMixer: A Fast-Converging Query-Based Object Detector》 (CVPR 2022 Oral) | |
| 2022.5.2 | 2. 郭杰 (Object Detection) | 《Progressive End-to-End Object Detection in Crowded Scenes》 (CVPR 2022) | |
| 2022.4.25 | 1. 陈雁 (Semantic Segmentation) | 《Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation》 (ICCV 2021) | |
| 2022.4.25 | 2. 耿瑞祥 (Knowledge Distillation) | 《Self-Distillation from the Last Mini-Batch for Consistency Regularization》 (CVPR 2022) | |
| 2022.4.18 | 1. 张永胜 (Semantic Segmentation) | 《Rethinking Semantic Segmentation: A Prototype View》 (CVPR 2022 Oral) | |
| 2022.4.18 | 2. 吕乐乐 (网络结构) | 《MixFormer: Mixing Features across Windows and Dimensions》 (CVPR 2022 Oral) | |
| 2022.4.11 | 1. 曾海龙 (Semantic Segmentation) | 《Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels》 (CVPR 2022) | |
| 2022.4.11 | 2. 张朝君 (Semantic Segmentation) | 《Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation》 (CVPR 2022) | |
| 2022.4.4 | 1. 耿瑞祥 (Knowledge Distillation) | 《Decoupled Knowledge Distillation》 (CVPR 2022) | |
| 2022.4.4 | 2. 李胜琦 (Contrastive Learning) | 《Crafting Better Contrastive Views for Siamese Representation Learning》 (CVPR 2022) | |
| 2022.3.28 | 1. 吕乐乐 (Semantic Segmentation) | 《GroupViT: Semantic Segmentation Emerges from Text Supervision》 (arXiv 2022) | |
| 2022.3.28 | 2. 陈雁 (Semantic Segmentation) | 《Multi-class Token Transformer for Weakly Supervised Semantic Segmentation》 (CVPR 2022) | |
| 2022.3.17 | 1. 张永胜 (Semantic Segmentation) | 《UNSUPERVISED SEMANTIC SEGMENTATION BY DISTILLING FEATURE CORRESPONDENCES》 (ICLR 2022) | |
| 2022.3.17 | 2. 张朝君 (Instance Segmentation) | 《Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images》 (CVPR 2021) | |
| 2022.3.10 | 1. 曾海龙 (Semantic Segmentation) | 《Learning Semantic Segmentation from Multiple Datasets with Label Shifts》 (arXiv 2022) | |
| 2022.3.10 | 2. 李胜琦 (semantic segmentation) | 《GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference》 (AAAI 2022) | |
| 2022.3.3 | 1. 陈雁 (Semantic Segmentation) | 《Single-Stage Semantic Segmentation from Image Labels》 (CVPR 2020) | |
| 2022.3.3 | 2. 耿瑞祥 (Knowledge Distillation) | 《Distilling Object Detectors with Feature Richness》 (NeurIPS 2021) | |
| 2022.2.24 | 1. 冯硕 (Object Detection) | 《GiraffeDet: A Heavy-Neck Paradigm for Object Detection》 (ICLR 2022) | |
| 2022.2.24 | 2. 吕乐乐 (Transformer) | 《Combiner: Full Attention Transformer with Sparse Computation Cost》 (NeurIPS 2021) | |
| 2022.2.17 | 1. 张永胜 (Semantic Segmentation) | 《BOOTSTRAPPING SEMANTIC SEGMENTATION WITH REGIONAL CONTRAST》 (ICLR 2022) | |
| 2022.2.17 | 2. 张朝君 (Instance Segmentation) | 《BoxInst: High-Performance Instance Segmentation with Box Annotations》 (CVPR 2021) | |
| 2022.2.10 | 1. 曾海龙 (Transformer) | 《Masked-attention Mask Transformer for Universal Image Segmentation》 (arXiv 2021) | |
| 2022.2.10 | 2. 陈雁 (Semantic Segmentation) | 《Group-Wise Learning for Weakly Supervised Semantic Segmentation》 (TIP) | |
| 2022.1.27 | 1. 张永胜 (Knowledge Distillation) | 《Distilling Knowledge via Knowledge Review》 (CVPR 2021) | |
| 2022.1.27 | 2. 李胜琦 (Semantic Segmentation) | 《Semi-supervised Semantic Segmentation with Directional Context-aware Consistency》 (CVPR 2021) | |
| 2022.1.20 | 1. 赵嘉伟 (Classification) | 《Generalized Category Discovery》 (arXiv 2022) | |
| 2022.1.20 | 2. 张朝君 (Semantic Segmentation) | 《Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation》 (CVPR 2021) | |
| 2022.1.13 | 1. 吕乐乐 (Attention) | 《CoAtNet: Marrying Convolution and Attention for All Data Sizes》 (NeurlPS 2021) | |
| 2022.1.13 | 2. 王都 (Object Detection) | 《OTA: Optimal Transport Assignment for Object Detection》 (CVPR 2021) | |
| 2022.1.6 | 1. 赵杨 (Object Detection) | 《Bootstrap Your Object Detector via Mixed Training》 (NeurlPS 2021) | |
| 2022.1.6 | 2. 耿瑞祥 (Knowledge Distillation) | 《Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation》 (AAAI 2022) | |
| 2021.12.30 | 1. 苑思明 (Semantic Segmentation) | 《Progressive Semantic Segmentation》 (CVPR 2021) | |
| 2021.12.30 | 2. 曾海龙 (Domain Adaptation) | 《Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation》 (CVPR 2021) | |
| 2021.12.23 | 1. 刘浩天 (Transformer) | 《SOLQ: Segmenting Objects by Learning Queries》 (NeurlPS 2021) | |
| 2021.12.23 | 2. 冯硕 (Transformer) | 《Anchor DETR: Query Design for Transformer-Based Detector》 (arXiv 2021) | |
| 2021.12.23 | 3. 冯硕 (Transformer) | 《Conditional DETR for Fast Training Convergence》 (ICCV 2021) | |
| 2021.12.16 | 1. 李阳 (Transformer) | 《Gaussian Context Transformer》 (CVPR 2021) | |
| 2021.12.16 | 2. 陈雁 (Semantic Segmentation) | 《Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast》 (arXiv 2021) | |
| 2021.12.9 | 1. 李胜琦 (Transformer) | 《Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight》 (arXiv 2021) | |
| 2021.12.9 | 2. 耿瑞祥 (Knowledge Distillation) | 《Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data》 (NeurIPS 2021) | |
| 2021.12.2 | 1. 赵嘉伟 (Continual Learning) | 《Rehearsal Revealed: The Limits and Merits of Revisiting Samples in Continual Learning》 (ICCV 2021) | |
| 2021.12.2 | 2. 张永胜 (Distillation) | 《Tree-like Decision Distillation》 (CVPR 2021) | |
| 2021.11.25 | 1. 王都 (Dynamic Convolution) | 《Revisiting Dynamic Convolution via Matrix Decomposition》 (ICLR 2021) | |
| 2021.11.25 | 2. 吕乐乐 (DETR) | 《PnP-DETR:Towards Effcient Visual Analysis with Transformers》 (ICCV 2021) | |
| 2021.11.18 | 1. 赵杨 (Self-Supervised Learning) | 《Masked Autoencoders Are Scalable Vision Learners》 (arXiv 2021) | |
| 2021.11.18 | 2. 张朝君 (目标检测) | 《Humble Teachers Teach Better Students for Semi-Supervised Object Detection》 (CVPR 2021) | |
| 2021.11.8 | 1. 冯硕 (Transformer) | 《Emerging Properties in Self-Supervised Vision Transformers》 (ICCV 2021) | |
| 2021.11.1 | 1. 陈雁 (Instance Segmentation) | 《SOTR: Segmenting Objects with Transformers》 (ICCV 2021) | |
| 2021.10.25 | 1. 李胜琦 (Semantic Segmentation) | 《ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation》 (ICCV 2021) | |
| 2021.10.25 | 2. 耿瑞祥 (Object Detection) | 《LGD: Label-guided Self-distillation for Object Detection》 (arXiv 2021) | |
| 2021.10.18 | 1. 赵嘉伟 (Incremental Object Detection) | 《Morphable Detector for Object Detection on Demand》 (ICCV 2021) | |
| 2021.10.18 | 2. 张永胜 (Contrastive Learning) | 《Self-Supervised Visual Representations Learning by Contrastive Mask Prediction》 (ICCV 2021) | |
| 2021.10.11 | 1. 吕乐乐 (Weakly Supervised Learning) | 《Weakly Supervised Person Search with Region Siamese Networks》 (ICCV 2021) | |
| 2021.10.11 | 2. 王都 (Attention) | 《FcaNet: Frequency Channel Attention Networks》 (ICCV 2021) | |
| 2021.9.27 | 1. 曾海龙 (目标检测) | 《TOOD: Task-aligned One-stage Object Detection》 (ICCV 2021 Oral) | |
| 2021.9.27 | 2. 曾海龙 (目标检测) | 《Rethinking the Aligned and Misaligned Features in One-stage Object Detection》 (arxiv 2021) | |
| 2021.9.20 | 1. 刘浩天 (目标检测) | 《A Simple Semi-Supervised Learning Framework for Object Detection》 (arxiv 2020) | |
| 2021.9.20 | 2. 刘浩天 (目标检测) | 《End-to-End Semi-Supervised Object Detection with Soft Teacher》 (ICCV 2021) | |
| 2021.9.13 | 1. 耿瑞祥 (Domain Generalization) | 《Towards Learning Spatially Discriminative Feature Representations》 (ICCV 2021) | |
| 2021.9.13 | 2. 耿瑞祥 (Domain Generalization) | 《Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation》 (ACM MM 2021) | |
| 2021.9.6 | 1. 李阳 (图像分割) | 《PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment》 (ICCV 2019) | |
| 2021.9.6 | 2. 李阳 (图像分割) | 《Mining Latent Classes for Few-shot Segmentation》 (ICCV 2021 Oral) | |
| 2021.8.30 | 1. 曾海龙 (图像缩放) | 《Learning to Resize Images for Computer Vision Tasks》 (ICCV 2021) | |
| 2021.8.30 | 2. 曾海龙 (语义分割) | 《Per-Pixel Classification is Not All You Need for Semantic Segmentation》 (arxiv 2021) | |
| 2021.8.23 | 1. 张永胜 (对比学习) | 《DetCo: Unsupervised Contrastive Learning for Object Detection》 (ICCV 2021) | |
| 2021.8.23 | 2. 张永胜 (对比学习) | 《Improving Contrastive Learning by Visualizing Feature Transformation》 (ICCV 2021 Oral) | |
| 2021.8.16 | 1. 耿瑞祥 (Domain Generalization) | 《A Fourier-based Framework for Domain Generalization》 (CVPR 2021 Oral) | |
| 2021.8.16 | 2. 耿瑞祥 (Domain Generalization) | 《SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization》 (arXiv 2021) | |
| 2021.8.9 | 1. 刘浩天 (目标检测) | 《Dynamic ReLU》 (ECCV 2020) | |
| 2021.8.9 | 2. 刘浩天 (目标检测) | 《Dynamic Head: Unifying Object Detection Heads with Attentions》 (CVPR 2021) | |
| 2021.8.2 | 1. 曾海龙 (知识蒸馏) | 《Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels》 (CVPR 2021) | |
| 2021.8.2 | 2. 曾海龙 (知识蒸馏) | 《All Tokens Matter: Token Labeling for Training Better Vision Transformers》 (arxiv 2021) | |
| 2021.7.19 | 1. 张永胜 (自监督学习) | 《Unsupervised Object-Level Representation Learning from Scene Images》 (arxiv 2021) | |
| 2021.7.19 | 2. 张永胜 (自监督学习) | 《Towards Solving Inefficiency of Self-supervised Representation Learning》 (arxiv 2021) | |
| 2021.7.12 | 1. 耿瑞祥 (Domain Generalization) | 《Domain Generalization with MixStyle》 (ICLR 2021) | |
| 2021.7.12 | 2. 耿瑞祥 (Domain Generalization) | 《Reducing Domain Gap by Reducing Style Bias》 (CVPR 2021) | |
| 2021.7.5 | 1. 刘浩天 (Transformer) | 《Training data-efficient image transformers & distillation through attention》 (DeiT) | |
| 2021.7.5 | 2. 刘浩天 (Transformer) | 《CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows》 (arXiv 2021) | |
| 2021.6.28 | 1. 张永胜 (自监督学习) | 《Spatially Consistent Representation Learning》 (CVPR 2021) | |
| 2021.6.28 | 2. 曾海龙 (Transformer) | 《DeepViT: Towards Deeper Vision Transformer》 (arXiv 2021) | |
| 2021.6.21 | 1. 王都 (BN) | 《Representative Batch Normalization with Feature Calibration》 (CVPR 2021) | |
| 2021.6.21 | 2. 耿瑞祥 (Domain Generalization) | 《Gradient Matching for Domain Generalization》 (arXiv 2021) | |
| 2021.6.15 | 1. 何柱君 (特征交互) | 《Learning Attentive Pairwise Interaction for Fine-Grained Classification》 (AAAI 2020) | |
| 2021.6.15 | 2. 赵杨 (Transformer) | 《Conditional Positional Encodings for Vision Transformers》 (arXiv 2021) | |
| 2021.6.7 | 1. 陈佳林 (GAN) | 《Analyzing and Improving the Image Quality of StyleGAN》 (CVPR 2020) | |
| 2021.6.7 | 2. 赵嘉伟 (Transformer) | 《An Attention Free Transformer》 (arXiv 2021) | |
| 2021.6.1 | 1. 冯硕 (Transformer) | 《Aggregating Nested Transformers》 (arXiv 2021) | |
| 2021.6.1 | 2. 刘浩天 (Transformer) | 《Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks》 (arXiv 2021) | |
| 2021.5.25 | 1. 耿瑞祥 (语义分割) | 《FSDR: Frequency Space Domain Randomization for Domain Generalization》 (CVPR 2021) | |
| 2021.5.25 | 2. 张永胜 (无监督学习) | 《Jigsaw Clustering for Unsupervised Visual Representation Learning》 (CVPR 2021) | |
| 2021.5.18 | 1. 潘长立 (网络结构) | 《Involution: Inverting the Inherence of Convolution for Visual Recognition》 (CVPR 2021) | |
| 2021.5.18 | 2. 赵嘉伟 (增量学习) | 《Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning》 (CVPR 2021) | |
| 2021.5.11 | 1. 苑思明 (语义分割) | 《Rethinking BiSeNet For Real-time Semantic Segmentation》 (CVPR 2021) | |
| 2021.5.11 | 2. 尹志华 (Attention) | 《Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth》 (arXiv 2021) | |
| 2021.4.27 | 1. 王都 (目标检测) | 《VarifocalNet: An IoU-aware Dense Object Detector》 (CVPR 2021) | |
| 2021.4.27 | 2. 刘浩天 (语义分割) | 《InverseForm: A Loss Function for Structured Boundary-Aware Segmentation》 (CVPR 2021) | |
| 2021.4.20 | 1. 冯硕 (Transformer) | 《Swin Transformer: Hierarchical Vision Transformer using Shifted Windows》 (arXiv 2021) | |
| 2021.4.20 | 2. 张永胜 (语义分割) | 《PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation》 (CVPR 2021) | |
| 2021.4.13 | 1. 邬任重 (GAN) | 《Towards Real-World Blind Face Restoration with Generative Facial Prior》 (arXiv 2021) | |
| 2021.4.13 | 2. 耿瑞祥 (语义分割) | 《RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening》 (CVPR 2021) | |
| 2021.4.6 | 1. 李阳 (语义分割) | Capturing Omni-Range Context for Omnidirectional Segmentation》 (CVPR 2021) | |
| 2021.4.6 | 2. 苑思明 (数据增广) | 《KeepAugment: A Simple Information-Preserving Data Augmentation Approach》 (CVPR 2021) | |
| 2021.3.29 | 1. 赵嘉伟 (目标检测) | 《Towards Open World Object Detection》 (CVPR 2021) | |
| 2021.3.29 | 2. 王都 (目标检测) | 《Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection》 (CVPR 2021) | |
| 2021.3.22 | 1. 刘浩天 (目标检测) | 《You Only Look One-level Feature》 (CVPR 2021) | |
| 2021.3.22 | 2. 张永胜 (语义分割) | 《Learning Statistical Texture for Semantic Segmentation》 (CVPR 2021) | |
| 2021.3.15 | 1. 耿瑞祥 (Transformer) | 《Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions》 (arXiv 2021) | |
| 2021.3.15 | 2. 邬任重 (关键点检测) | 《3FabRec: Fast Few-shot Face alignment by Reconstruction》 (CVPR 2020) | |
| 2021.3.8 | 1. 冯硕 (目标检测) | 《UP-DETR: Unsupervised Pre-training for Object Detection with Transformers》 (CVPR 2021) | |
| 2021.3.8 | 2. 赵嘉伟 (增量学习) | 《PLOP: Learning without Forgetting for Continual Semantic Segmentation》 (CVPR 2021) | |
| 2021.3.1 | 1. 陈佳林 (目标检测) | 《Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis》 (ICLR 2021) | |
| 2021.3.1 | 2. 李阳 (语义分割) | 《Hierarchical Multi-Scale Attention for Semantic Segmentation》 (arXiv 2020) | |
| 2021.2.22 | 1. 苑思明 (目标检测) | 《Fast Convergence of DETR with Spatially Modulated Co-Attention》 (arXiv 2020) | |
| 2021.2.22 | 2. 何柱君 (自监督学习) | 《Instance Localization for Self-supervised Detection Pretraining》 (arXiv 2021) | |
| 2021.2.8 | 1. 苑思明 (语义分割) | 《EfficientFCN: Holistically-guided Decoding for Semantic Segmentation》 (ECCV 2020) | |
| 2021.2.8 | 2. 尹志华 (网络结构) | 《RepVGG: Making VGG-style ConvNets Great Again》 (arXiv 2021) | |
| 2021.2.1 | 1. 王都 (目标检测) | 《Probabilistic Anchor Assignment with IoU Prediction for Object Detection》 (ECCV 2020) | |
| 2021.2.1 | 2. 赵杨 (对比学习) | 《Self-EMD: Self-Supervised Object Detection without ImageNet》 (arXiv 2020) | |
| 2021.1.21 | 1. 张永胜 (语义分割) | 《Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers》 (arXiv 2020) | |
| 2021.1.21 | 2. 邬任重 (AEV) | 《Auto-Encoding Variational Bayes》 (ICLR 2014) | |
| 2021.1.14 | 1. 赵嘉伟 (对比学习) | 《Hierarchical Semantic Aggregation for Contrastive Representation Learning》 (arXiv 2020) | |
| 2021.1.14 | 2. 耿瑞祥 (网络结构) | 《Funnel Activation for Visual Recognition》 (ECCV 2020) | |
| 2021.1.7 | 1. 梁毅雄 (自监督学习) | Self-supervised learning in Computer Vision | |
| 2020.12.24 | 1. 冯硕 (目标检测) | 《End-to-End Object Detection with Fully Convolutional Network》 (arXiv 2020) | |
| 2020.12.24 | 2. 刘浩天 (网络结构) | 《LambdaNetworks: Modeling long-range Interactions without Attention》 (arXiv 2020) | |
| 2020.12.17 | 1. 尹志华 (对比学习) | 《Dense Contrastive Learning for Self-Supervised Visual Pre-Training》 (arXiv 2020) | |
| 2020.12.17 | 2. 苑思明 (目标检测) | 《Sparse R-CNN: End-to-End Object Detection with Learnable Proposals》 (arXiv 2020) | |
| 2020.12.10 | 1. 陈佳林 (信息瓶颈) | 《Deep Variational Information Bottleneck》 (ICLR 2017) | |
| 2020.12.10 | 2. 王都 (目标检测) | 《Deformable DETR: Deformable Transformers for End-to-End Object Detection》 (arXiv 2020) | |
| 2020.12.03 | 1. 潘长立 (目标检测) | 《Dive Deeper Into Box for Object Detection》 (ECCV 2020) | |
| 2020.12.03 | 2. 张永胜 (语义分割) | 《CCNet:Criss-Cross Attention for Semantic Segmentation》 (ICCV 2019) | |
| 2020.11.26 | 1. 李阳 (语义分割) | 《Mining cross-image semantics for weakly supervised semantic segmentation》 (ECCV 2020) | |
| 2020.11.26 | 2. 耿瑞祥 (目标检测) | 《Missing Labels in Object Detection》 (CVPR 2019) | |
| 2020.11.16 | 1. 何柱君 (目标检测) | 《RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder》 (NIPS 2020) | |
| 2020.11.16 | 2. 邬任重 (VAE、GAN) | 《Bringing Old Photos Back to Life》 (CVPR 2020 oral) | |
| 2020.11.09 | 1. 冯硕 (目标检测) | 《Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection》 (NIPS 2020) | |
| 2020.11.09 | 2. 赵嘉伟 (增量学习) | 《Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation》 (ECCV 2020) | |
| 2020.11.02 | 1. 刘浩天 (长尾问题) | 《Feature Space Augmentation for Long-Tailed Data》 (ECCV 2020) | |
| 2020.11.02 | 2. 赵杨 (目标检测) | 《LabelEnc: A New Intermediate Supervision Method for Object Detection》 (ECCV 2020) | |
| 2020.10.26 | 1. 苑思明 (检测、分割) | 《Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation》 (ECCV 2020) | |
| 2020.10.26 | 2. 张永胜 (对比学习) | 《Contrastive learning of global and local features for medical image segmentation with limited annotations》 (NIPS 2020) | |
| 2020.10.19 | 1. 赵嘉伟 (增量学习) | 《Incremental Few-Shot Object Detection》 (CVPR 2020) | |
| 2020.10.19 | 2. 耿瑞祥 (对比学习) | 《Prototypical Contrastive Learning of Unsupervised Representations》 (arXiv 2020) | |
| 2020.10.12 | 1. 王都 (网络结构) | 《Visual Transformers: Token-based Image Representation and Processing for Computer Vision》 (arXiv 2020) | |
| 2020.10.12 | 2. 赵杨 (对比学习) | 《Hard Negative Mixing for Contrastive Learning》 (arXiv 2020) | |
| 2020.10.5 | 1. 李阳 (语义分割) | 《Object-Contextual Representations for Semantic Segmentation》 (ECCV 2020) | |
| 2020.10.5 | 2. 邬任重 (自动编码) | 《Adversarial Latent Autoencoders》 (CVPR 2020) | |
| 2020.9.28 | 1. 冯硕 (目标检测) | 《RepPoints v2: Verification Meets Regression for Object Detection》 (arXiv 2020) | |
| 2020.9.28 | 2. 刘浩天 (mixup) | 《Manifold mixup: Better representations by interpolating hidden states》 (ICML 2019) | |
| 2020.9.21 | 1. 苑思明 (实例分割) | 《EmbedMask: Embedding Coupling for One-stage Instance Segmentation》 (CVPR 2020) | |
| 2020.9.21 | 2. 赵杨 (对比学习) | 《What Should Not Be Contrastive in Contrastive Learning》 (arxiv 2020) | |
| 2020.9.14 | 1. 赵嘉伟 (增量学习) | 《Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights》 (ECCV 2018) | |
| 2020.9.14 | 2. 王都 (分割) | 《Semantic Flow for Fast and Accurate Scene Parsing》 (ECCV 2020) | |
| 2020.9.7 | 1. 李阳 (改进空洞卷积) | 《PSConv: sqeezing feature pyramid into one compact poly-scale convolutional layer》 (ECCV 2020) | |
| 2020.9.7 | 2. 赵杨 (对比学习) | 《Contrastive Multiview Coding》 (arxiv 2019) | |
| 2020.8.31 | 1. 冯硕 (目标检测) | 《BorderDet: Border Feature for Dense Object Detection》 (ECCV 2020) | |
| 2020.8.31 | 2. 刘浩天 (语义分割) | 《Dual Super-Resolution Learning for Semantic Segmentation》 (CVPR 2020) | |
| 2020.8.24 | 1. 王都 (transformer优化) | 《Reformer: The Efficient Transformer》 (ICLR 2020) | |
| 2020.8.24 | 2. 苑思明 (检测和分割) | 《D2Det: Towards High Quality Object Detection and Instance Segmentation》 (CVPR 2020) | |
| 2020.8.17 | 1. 李阳 (语义分割) | 《Improving Semantic Segmentation via Decoupled Body and Edge Supervision》 (ECCV 2020) | |
| 2020.8.17 | 2. 赵嘉伟 (增量学习) | 《Editable Neural Networks》 (ICLR 2020) | |
| 2020.8.10 | 1. 冯硕 (特征金字塔) | 《Feature Pyramid Transformer》 (ECCV 2020) | |
| 2020.8.10 | 2. 刘浩天 | 工作报告 | |
| 2020.08.03 | 1. 苑思明 (实例分割) | 《PolyTransform: Deep Polygon Transformer for Instance Segmentation》 (CVPR 2020) | |
| 2020.08.03 | 2. 王都 (transformer) | 《On Layer Normalization in the Transformer Architecture》 (ICML 2020) | |
| 2020.7.27 | 1. 李阳 (注意力机制) | 《ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks》 (CVPR 2020) | |
| 2020.7.27 | 2. 赵嘉伟 (增量学习) | 《Faster ILOD Incremental Learning for Object Detectors based on FasterRCNN》 (PRL 2020) | |
| 2020.7.20 | 1. 刘浩天 (分类) | 《Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax》 (CVPR 2020 Oral) | |
| 2020.7.20 | 2. 潘长立 | 工作报告 | |
| 2020.7.13 | 1. 何柱君 (目标检测) | 《Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels》 (CVPR 2020 Oral) | |
| 2020.7.13 | 2. 冯硕 (实例分割) | 《Conditional Convolutions for Instance Segmentation》 (ECCV 2020) | |
| 2020.7.6 | 1. 苑思明 (实例分割) | 《Mask Encoding for Single Shot Instance Segmentation》 (CVPR 2020) | |
| 2020.7.6 | 2. 王都 (分类) | 《BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition》 (CVPR 2020) | |
| 2020.6.29 | 1. 李阳 (实例分割) | 《Deep Snake for Real-Time Instance Segmentation》 (CVPR 2020 Oral) | |
| 2020.6.29 | 2. 赵嘉伟 (增量学习) | 《Task-free Continual Learning》 (CVPR 2019) 《Dropout as an Implicit Gating Mechanism For Continual Learning》(CVPR 2020 Workshops) | |
| 2020.6.19 | 1. 冯硕 (目标检测) | 《Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection》 (CVPR-2020) | |
| 2020.6.19 | 2. 陈佳林 (GAN) | 《MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis》 (CVPR-2020) | |
| 2020.6.12 | 1. 何柱君 (目标检测) | 《End-to-end Object Detection with Transformers》(CVPR-2020) | |
| 2020.6.12 | 2. 唐志鸿 (分割&检测) | MSCOCO分割与检测技术流 | |
| 2020.5.29 | 1. 程海涛 (图像配准) | 《Recursive Cascaded Networks for Unsupervised Medical Image Registration》(ICCV-2019) | |
| 2020.5.29 | 赵嘉伟 (增量学习) | 1.《IL2M: Class Incremental Learning With Dual Memory 》(ICCV-2019)2.《Compacting, Picking and Growing for Unforgetting Continual Learning 》(NeurIPS-2019) | |
| 2020.5.22 | 1)李阳 (加法器网络) | 《AdderNet:Do We Really Need Multiplications in Deep Learning》(CVPR-2020) | |
| 2020.5.22 | 2)苑思明 (实例分割) | 《CenterMask:Single Shot Instance segmentation with Point Representation》(CVPR-2020) | |
| 2020.5.15 | 1)潘长立 (目标检测) | 《YOLOv4: Optimal Speed and Accuracy of Object Detection》(arXiv-2020) | |
| 2020.5.15 | 2)冯硕 (卷积的改进,目标检测,分割) | 《Dynamic Region-Aware Convolution》(arXiv-2020) | |
| 2020.5.8 | 1)何柱君 (图卷积网络) | 《Spectral Networks and Locally Connected Networks on Graphs》(ICLR-2014) | |
| 2020.5.8 | 2)陈佳林 (互信息,分类) | 《Mutual Information Neural Estimation》(ICML-2018) | |
| 2020.4.30 | 1)王都 (目标检测,半监督) | 《Proposal Learning for Semi-Supervised Object Detection》(arXiv-2020) | |
| 2020.4.30 | 2)赵嘉伟 (图像分类,决策树和神经网络的结合) | 《NBDT: Neural-Backed Decision Trees》(arXiv-2020) | |
| 2020.4.24 | 1)尹志华 (ResNet改进,注意力机制) | 《ResNeSt: Split-Attention Networks》(2020) | |
| 2020.4.24 | 2)程海涛 (图像配准,自监督) | 《Non-rigid image registration using self-supervised fully convolutional networks without training data》(ISBI-2018) | |
| 2020.4.17 | 1)李阳 (可形变的卷积核) | 《Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation》(ICLR-2020) | |
| 2020.4.17 | 2)苑思明 (检测和分割相互促进) | 《RDSNet:A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation》(AAAI-2020) | |
| 2020.4.10 | 1)何柱君 (Object Detection) | 《Learning Rich Features at High-Speed for Single-Shot Object Detection》(ICCV-2019) | |
| 2020.4.10 | 2)冯硕 (Instance Segmentation) | 《SOLOv2: Dynamic, Faster and Stronger 》(arXiv-2020) | |
| 2020.4.3 | 1)潘长立 | 《1st Place Solutions for OpenImage2019 - Object Detection and Instance Segmentation》(arXiv-2020) | |
| 2020.4.3 | 2)孙婉欣 | 《Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression 》(AAAI-2020) | |
| 2020.3.27 | 1)赵嘉伟 | 《Neural Networks are Surprisingly Modular》(2020) | |
| 2020.3.27 | 2)唐志鸿 (Visual Representation Learning) | 《A Simple Framework for Contrastive Learning of Visual Representation》(arXiv-2020) | |
| 2020.3.20 | 1)陈佳林 (GAN) | 《Real or Not Real, that is the Question》(ICLR-2020) | |
| 2020.3.20 | 2)严勐 (Compression) | 《 Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman coding》(ICLR-2016) | |
| 2020.3.13 | 1)程海涛 (图像配准融合) | 《Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning based Registration》(MICCAI-2018) 《Adversarial image registration with application for mr and trus image fusion》(MLMI-2018) | |
| 2020.3.13 | 2)王都 (数据增强) | 《Autoaugment: Learning augmentation strategies from data》(CVPR-2019) | |
| 2020.3.6 | 1)冯硕 (lightweight model) | 《GhostNet: More Features from Cheap Operations》(CVPR-2020) | |
| 2020.3.6 | 2)李阳 (segmentation) | 《Semantic Correlation Promoted Shape-Variant Context for Sementation》(CVPR-2019) | |
| 2020.2.28 | 1)何柱君 | 《Employing Deep Part-Object Relationships for Salient Object Detection》(ICCV-2019) | |
| 2020.2.28 | 2)苑思明 | 《Deep Learning Approach for Evaluating Knee | |
| 2020.2.21 | 1)潘长立 (bouding box regression) | 《Side-Aware Boundary Localization for More Precise Object Detection》(arXiv-2019) | |
| 2020.2.21 | 2)尹志华 (attention) | 《On the Relationship between Self-Attention and Convolutional Layers》(ICLR-2020) | |
| 2020.2.14 | 1)陈佳林 (GAN) | 《On the''steerability" of generative adversarial networks》(arXiv-2019) | |
| 2020.2.14 | 2)赵嘉伟 | 《Rotate your networks: Better weight consolidation and less catastrophic forgetting》(ICPR-2018) | |
| 2020.2.7 | 1)程海涛 | 《CNN Driven Sparse Multi-Level B-spline Image Registration》(CVPR-2018) | |
| 2020.2.7 | 2)王都 | 《Mixmatch: A holistic approach to semi-supervised learning》(NeurIPS-2019) | |
| 2019.1.14 | 1)李阳 | 《Dynamic Multi-scale Filters for Semantic Segmentation》(ICCV-2019) | |
| 2019.1.14 | 2)冯硕 | 《SOLO: Segmenting Objects by Locations》(arXiv-2019) | |
| 2019.1.8 | 1)何柱君 (biliner pooling) | 《Semantic segmentation with second-order pooling》(ECCV-2012) 《Bilinear cnn models for fine-grained visual recognition》(ICCV-2015) 《Compact bilinear pooling》(CVPR-2016) | |
| 2019.1.8 | 2)赵杨 (Instance Segmentation) | 《BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation》(arXiv-2020) | |
| 2019.1.2 | 1)潘长立 | 《Dense RepPoints: Representing Visual Objects with Dense Point Sets》(arXiv-2019) 《Empirical Upper-bound in Object Detection and More》(arXiv-2019) 《How much Position Information Do Convolutional Neural Networks Encode?》(ICLR-2020) | |
| 2019.1.2 | 2)唐志鸿 (GAN) | 《SinGAN:Learning a Generative Model from a Single Natural Image》(ICCV-2019 Best Paper) | |
| 2019.12.24 | 1)尹志华 (image segmentation) | 《PointRend: Image Segmentation as Rendering》(arXiv-2019) | |
| 2019.12.24 | 2)陈佳林 (image-to-image translation) | 《Diverse image-to-image translation via disentangled representations》(ECCV-2018) | |
| 2019.12.18 | 1)赵嘉伟 (Incremental Learning) | 《Learning without forgetting》(PAMI-2017) 《icarl: Incremental classifier and representation learning》(CVPR-2017) 《End-to-end incremental learning》(ECCV-2018) | |
| 2019.12.18 | 2)孙婉欣 (Object Detection) | 《Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors》(CVPR-2019) | |
| 2019.12.11 | 1)李阳 (Semantic Segmentation) | 《ACFNet:Attentional Class Feature Network for Semantic Segmentation》 (ICCV-2019) 《Asymmetric Non-Local Neural Networks for Semantic Segmentation》 (ICCV-2019) 《Adaptive Context Network for Scene Parsing》 (ICCV-2019) | |
| 2019.12.11 | 2)王都 (object detection) | 《C-mil: Continuation multiple instance learning for weakly supervised object detection》(CVPR-2019) | |
| 2019.12.4 | 1)何柱君 (dropblock, triplet loss, second-order information ) | 《Dropblock: A regularization method for convolutional networks》(NIPS-2018) 《In defense of the triplet loss for person re-identification》(arXiv-2017) 《Second-Order Non-Local Attention Networks for Person Re-Identification》(ICCV-2019) | |
| 2019.12.4 | 2)严勐 (unsupervised learning) | 《Momentum Contrast for Unsupervised Visual Representation Learning》(arXiv-2019) | |
| 2019.11.27 | 1)冯硕 (FPN结构优化) | 《Path Aggregation Network for Instance Segmentation》( CVPR-2018 ) 《NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection》(CVPR-2019) 《EfficientDet: Scalable and Efficient Object Detection》(arXiv-2019) | |
| 2019.11.27 | 2)尹志华 (attention) | 《Attention Augmented Convolutional Networks》(ICCV-2019) 《Attention Augmented Convolutional Networks》(ICCV-2019) | |
| 2019.11.20 | 1)程海涛 (image registration) | 《A deep learning framework for unsupervised affine and deformable image registration》(Medical Image Analysis-2019) | |
| 2019.11.20 | 2)陈佳林 (增强 GAN 的稳定性) | 《Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow》(arXiv-2018) | |
| 2019.11.13 | 1)赵杨 (池化) | 《LIP: Local Importance-based Pooling》(CVPR-2019) | |
| 2019.11.13 | 2)赵嘉伟 (multi-instance multi-task) | 《Deep convolutional neural networks for multi-instance multi-task》(International Conference on Data Mining-2015) | |
| 2019.11.6 | 1)李阳 (Segmentation) | 《DANet: Dual Attention Network for Scene Segmentation》 (CVPR-2019) 《CCNet: Criss-Cross Attention for Semantic Segmentation》 (ICCV-2019) 《EMANet: Expectation-Maximization Attention Networks for Semantic Segmentation》 (ICCV-2019) | |
| 2019.11.6 | 2)王都 (WSI) | 《Neural Image Compression for Gigapixel Histopathology Image Analysis》(PAMI-2019) | |
| 2019.11.1 | 1)尹志华 (空间注意力) | 《An Empirical Study of Spatial Attention Mechanisms in Deep Networks》(ICCV-2019) | |
| 2019.11.1 | 2)何柱君 (Semi-Supervised,GAN和detection的结合 ) | 《Semi-Supervised Pedestrian Instance Synthesis and Detection with Mutual Reinforcement》(ICCV-2019) | |
| 2019.10.28 | 潘长立 (目标检测) | 头脑风暴 | |
| 2019.10.25 | 1)冯硕 (Instance Segmentation) | 《PolarMask: Single Shot Instance Segmentation with Polar Representation》(arXiv-2019) | |
| 2019.10.25 | 2)陈佳林 (染色归一化) | 《Stain Standardization Capsule: A pre-processing module for histopathological image analysis》 | |
| 2019.10.21 | 程海涛 (Image Registration) | 《Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network》(arXiv-2019) 《Recursive Cascaded Networks for Unsupervised Medical Image Registration》(arXiv-2019) | |
| 2019.10.18 | 1)赵嘉伟 (NMS) | 《Adaptive NMS: Refining Pedestrian Detection in a Crowd》(CVPR-2019) 《MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors》(CVPR-2019) | |
| 2019.10.18 | 2)何柱君 | RoI特征提取方法回顾 | |
| 2019.10.14 | 赵杨 (上采样,Deformable Conv) | 1)《CARAFE: Content-Aware ReAssembly of FEatures》(arXiv-2019) 2)《Deformable convolutional networks》(ICCV-2017) 3)《Deformable convnets v2: More deformable, better results》(CVPR-2019) | |
| 2019.10.11 | 1. 苑思明 (Texture Classification) | 《Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns》(PAMI-2002) | |
| 2019.10.11 | 2. 王都 (Object Detection) | 《Libra r-cnn: Towards balanced learning for object detection》(CVPR-2019) 《Prime Sample Attention in Object Detection》(arXiv-2019) | |
| 2019.10.8 | 李阳 (Features Aggregation) | 1. Deep Layer Aggregation (CVPR2018) 2. DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation (CVPR2019) 3. Data-Driven Neuron Allocation for Scale Aggregation Networks (CVPR2019) | |
| 2019.9.30 | 尹志华 (目标检测) | 《RepPoints: Point Set Representation for Object Detection》(arXiv-2019 | |
| 2019.9.2 | 冯硕 (目标检测) | FreeAnchor: Learning to Match Anchors for Visual Object Detection(NeurIPS-2019 ) | |
| 2019.9.2 | 1)陈佳林 (image-to-image translation) | Multimodal unsupervised image-to-image translation(ECCV-2018) | |
| 2019.9.2 | 2)程海涛 (图像配准和融合) | 近期工作总结 | |
| 2019.9.16 | 赵嘉伟 | Relational inductive biases, deep learning, and graph networks. (arXiv-2018) | |
| 2019.9.9 | 何柱君 (Relation networks) | 1)A simple neural network module for relational reasoning. (NIPS-2017) 2)Discovering objects and their relations from entangled scene representations. (arXiv-2017) 3)Relation networks for object detection.(CVPR-2018) | |
| 2019.9.2 | 王都 | Hamid Rezatofighi, Nathan Tsoi. Generalized intersection over union: A metric and a loss for bounding box regression.CoRR, abs/1902.09630, 2019. | |
| 2019.8.26 | 唐志鸿 (point-based detection) | 近期工作总结 | |
| 2019.8.19 | 陈佳林 (GAN) | Karras, Tero, Samuli Laine, and Timo Aila. "A style-based generator architecture for generative adversarial networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. | |
| 2019.8.12 | 冯硕 (一阶段目标检测的特征对齐) | 1) Region proposal by guided anchoring (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition) 2) Revisiting Feature Alignment for One-stage Object Detection (arXiv preprint) | |
| 2019.8.5 | 程海涛 | 1)《Zero Shot Learning for Multi-Modal Real Time Image Registration》 2)《ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features》 3)《End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network》 4)《Nonrigid Image Registration Using Multi-scale 3D Convolutional Neural Networks》 5)《ELASTIC REGISTRATION OF MEDICAL IMAGES WITH GANS》 | |
| 2019.7.29 | 1)尹志华 (目标检测) | Cascade network 小结 | |
| 2019.7.22 | 1)何柱君 (目标检测) | 《Spatial memory for context reasoning in object detection》(ICCV-2017) 《Structure inference net: Object detection using scene-level context and instance-level relationships》(CVPR-2018) | |
| 2019.7.22 | 2)赵嘉伟 (a new type of convolution) | 《HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs》(CVPR-2019) | |
| 2019.7.15 | 1)潘长立 (目标检测) | 《anchor 小结》 | |
| 2019.7.15 | 2)赵杨 (EM,分类) | 《Patch-based convolutional neural network for whole slide tissue image classification》 (重讲)(CVPR-2016) | |
| 2019.7.8 | 1)孙婉欣 (目标检测) | 《FoveaBox: Beyond Anchor-based Object Detector》(arXiv 2019) | |
| 2019.7.8 | 2)陈佳林 (GAN) | 《Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks》(CVPR-2019)《Unsupervised attention-guided image-to-image translation》(NIPS-2018) | |
| 2019.7.1 | 1)王都 (语义分割) | 《Fast-SCNN: Fast Semantic Segmentation Network》(arXiv 2019) | |
| 2019.7.1 | 2)程海涛 (多聚焦图像融合) | 《Multi-scale convolutional neural network for multi-focus image fusion》(IVC-2019) | |
| 2019.6.24 | 1)冯硕 (CNN) | 《EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks》(arXiv 2019) | |
| 2019.6.24 | 2)赵杨 (CNN) | 《Patch-based convolutional neural network for whole slide tissue image classification》(CVPR-2016) | |
| 2019.6.19 | 1)尹志华 (可视化) | 《Grad-cam: Visual explanations from deep networks via gradient-based localization》(CVPR 2017) | |
| 2019.6.19 | 2)何柱君 (CNN) | 《Kervolutional Neural Networks》(CVPR-2019) | |
| 2019.6.10 | 1)潘长立 (目标检测) | 《Bounding Box Regression with Uncertainty for Accurate Object Detection》(CVPR-2019) | |
| 2019.6.3 | 1)严勐 (目标检测) | 《DetNet:A Backbone network for Object Detection》(arXiv 2018) 《Scale-Aware Trident Networks for Object Detection》(ICCV 2019) | |
| 2019.5.27 | 1)程海涛 (多聚焦融合) | 《Ensemble of CNN for multi-focus image fusion》 《MCFNet: Multi-layer Concatenation Fusion Network for Medical Images Fusion》 | |
| 2019.5.27 | 2)陈佳林 (多聚焦融合) | 《FuseGAN: Learning to fuse Multi-focus Image via Conditional Generative Adversarial Network》 | |
| 2019.5.20 | 1)何柱君 (自动聚焦) | 《An image auto-focusing algorithm for industrial image measurement》 《Combining gradient ascent search and support vector machines for effective autofocus of a field emission--scanning electron microscope》 《A Robotic Auto-Focus System based on Deep Reinforcement Learning》 | |
| 2019.5.13 | 1)潘长立 (对抗样本) | 对抗样本 | |
| 2019.5.13 | 2)孙婉欣 (anchor-free) | 《Region Proposal by Guided Anchoring》 《Feature Selective Anchor-Free Module for Single-Shot Object Detection》 | |
| 2019.5.6 | 1)尹志华 (anchor free objection detection-one stage) | 近期工作小节 | |
| 2019.5.6 | 2)严勐 (light weight network) | 近期工作小节 | |
| 2019.4.29 | 1)程海涛 (图像配准、融合) | 《An Unsupervised Learning Model for Deformable Medical Image Registration》 《DenseFuse: A Fusion Approach to Infrared and Visible Images》 | |
| 2019.4.29 | 2)何柱君 (loss function) | 《Large-margin softmax loss for convolutional neural networks》 《Rethinking Feature Distribution for Loss Functions in Image Classification》 | |
| 2019.4.22 | 1)潘长立 (CNN) | 《Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution》 | |
| 2019.4.22 | 2)陈佳林 (GAN) | 《GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium》 《Spectral Normalization for Generative Adversarial Networks》 《Self-Attention Generative Adversarial Networks》 《Large Scale GAN Training for High Fidelity Natural Image Synthesis》 | |
| 2019.4.15 | 1)孙婉欣 (目标检测) | 《An analysis of scale invariance in object detection snip》 《SNIPER: Efficient multi-scale training》 | |
| 2019.4.15 | 2)尹志华 (图像分割) | 《TensorMask: A Foundation for Dense Object Segmentation》 《YOLACT: Real-time Instance Segmentation》 | |
| 2019.4.8 | 1)严勐 (目标检测) | 近期工作总结(attention、noisy-label) | |
| 2019.3.31 | 1)张帆 (图像质量评价) | 《RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment》 《No-reference Image Quality Assessment with Reinforcement Recursive List-wise Ranking》 | |
| 2019.3.31 | 2)何柱君 (BN) | 《How Does Batch Normalization Help Optimization?》 | |
| 2019.3.25 | 1)唐志鸿 (目标检测+分割) | 《Merged Mask-RNN with boosting feature pyramid network》 | |
| 2019.3.25 | 2)陈佳林 (头脑风暴) | 染色归一化和图像分割 | |
| 2019.3.22 | 1)张帆 (图像质量评价) | 头脑风暴: 《基于深度卷积神经网络的数字图像质量评价》 | |
| 2019.3.22 | 2)严勐 (目标检测) | 头脑风暴:《基于特征金字塔网络(FPN)的细胞检测》 | |
| 2019.3.17 | 1)孙婉欣 (细胞检测) | 头脑风暴:《 基于 yolov3 的宫颈细胞自动检测算法》 | |
| 2019.3.17 | 2)潘长立 (细胞检测) | 头脑风暴:《 基于 yolov3 的宫颈细胞自动检测算法》 | |
| 2019.3.11 | 1)陈佳林 染色归一化 | StainGAN+Adaptive color deconvolution | |
| 2019.3.11 | 2)何柱君 (自动聚焦) | 头脑风暴:《 基于深度卷积神经网络的光学显微镜自动聚焦算法》 | |
| 2019.3.4 | 1)尹志华 (Extreme point) | 《ExtremeNet: Bottom-up Object Detection by Grouping Extreme and Center Points》 《Deep Extreme Cut:From Extreme Points to Object Segmentation》 | |
| 2019.3.4 | 2)何柱君 (Face Alignment) | 《Face Alignment by Explicit Shape Regression》 《Supervised Descent Method and Its Applications to Face Alignment》 | |
| 2019.3.4 | 3)唐志鸿 | 近期工作总结 | |
| 2019.2.25 | 1)程海涛 (图像融合) | 《Image Segmentation-Based Multi-Focus Image Fusion Through Multi-Scale Convolutional Neural Network》 《Infrared and Visible Image Fusion using a Deep Learning Framework》 | |
| 2019.2.25 | 2)潘长立 (目标检测) | 《Bag of Freebies for Training Object Detection Neural Networks mixup》 | |
| 2019.2.25 | 3)张帆 (图像质量评价) | Learning to rank 小结 | |
| 2019.1.21 | 1)陈佳林 (染色归一化) | 《Color normalization in digital histopathology images》 《Comparison of Normalization Algorithms for Cross-Batch Color Segmentation of Histopathological Images》 《EM-based segmentation-driven color standardization of digitized histopathology》 | |
| 2019.1.21 | 2)严勐 (图像分类) | inception famliy 小结 | |
| 2019.1.14 | 1)潘长立 (目标检测中的对抗训练) | a-fast-rcnn | |
| 2019.1.14 | 1)尹志华 (语义分割) | 《DecoupleedNet (NIPS 2015)》 《E-Net(2016)& LinkNet(VCIP 2017)》 《RefineNet(CVPR 2017)》 《PSPNet(CVPR 2017)》 《FC-DenseNet(CVPR 2017)》 《DeepLab v3+(ECCV 2018)》 | |
| 2019.1.7 | 1)何柱君 (自动聚焦) | 《Efficient auto-focus algorithm utilizing discrete difference equation prediction model for digital still cameras》 | |
| 2019.1.7 | 2)程海涛 (图像融合) | 《Multi-focus image fusion with a deep convolutional neural network》,《Pixel convolutional neural network for multi-focus image fusion | |
| 2018.12.24 | 1)张帆 (图像质量评价) | 无参考图像质量评价算法小结 | |
| 2018.12.24 | 1)孙婉欣 (目标检测) | PFPNet(目标检测中的特征金字塔) | |
| 2018.12.17 | 1)毛渊 (图像融合) | 近期工作总结 | |
| 2018.12.10 | 1)尹志华 (语义分割) | DeepLab系列 | |
| 2018.12.10 | 2)陈佳林 (染色归一化) | 《Color transfer between images》 《Quantification of histochemical staining by color deconvolution》 | |
| 2018.12.10 | 3)潘长立 (对抗训练) | DefenseGAN | |
| 2018.12.3 | 1)何柱君 (Normalization) | BN、SyncBN、Group Normalization | |
| 2018.12.3 | 2)程海涛 ( 图像融合) | DeepFuse | |
| ⬆ back to top | | | |