Shadowgraph
TrendingAbout
Sign in

ayiyayi/Awesome-Egocentric-and-Exocentric-Vision

42

12 commits

updated Nov 14, 2025

See the code

README

🌟 Awesome Egocentric-and-Exocentric Vision

Survey Paper Last Updated PRs Welcome Stars

A curated list of papers and datasets on Egocentric (first-person) and Exocentric (third-person) Vision. This repo complements our survey and is continuously updated.

📖 Contents

📑 Papers

🔹 Egocentric for Exocentric

✨ Video Generation

TitleVenueYearCode
Intention-driven Ego-to-Exo Video Generationarxiv2024-
Ego-to-Exo: Interfacing Third Person Visuals from Egocentric Views in Real-time for Improved ROV Teleoperationarxiv2024-

✨ Action Understanding

TitleVenueYearCode
From my view to yours: Egoaugmented learning in large vision language models
for understanding exocentric daily living activities		arxiv2025Github

✨ View Birdification

TitleVenueYearCode
View birdification in the crowd: Ground-plane localization from perceived movementsarxiv2021-
Viewbirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric viewRAL2022-
Incrowdformer: On-ground pedestrian world model from egocentric viewsarxiv2023-

✨ View Selection

TitleVenueYearCode
Camera selection for occlusion-less surgery recording via training with an egocentric cameraAccess2021-

🔹 Exocentric for Egocentric

✨ Video Generation

TitleVenueYearCode
From third person to first person: Dataset and baselines for synthesis and retrievalCVPRW2019Github
Crossview exocentric to egocentric video synthesisarxiv2021-
Parallel generative adversarial network for third-person to first-person image generationCVPRW2022-
Towards third-person visual imitation learning using generative adversarial networksICDL2022-
4diff: 3d-aware diffusion model for third-to-first viewpoint translationECCV2024Github
Diffusing in someone else’s shoes: Robotic perspective taking with diffusionHumanoids2024Github
Put myself in your shoes: Lifting the egocentric perspective from exocentric videosECCV2024-
Exocentric-to-EgocentricVideoGenerationNeulIPS2024Github
EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric VideosICLR2025-

✨ Video Captioning

TitleVenueYearCode
Exo2egodvc: Dense video captioning of egocentric procedural activities using web instructional videosWACV2023Github
Retrieval-augmented egocentric video captioningCVPR2024Github

✨ Action Understanding

TitleVenueYearCode
Unsupervised and semi-supervised domain adaptation for action recognition from dronesWACV2020-
Ego-exo: Transferring visual representations from third-person to first-person videosCVPR2021Github
Audio-Adaptive Activity Recognition Across Video DomainsCVPR2022Github
Estimating egocentric 3d human pose in the wild with external weak supervisionCVPR2022Github
Cross-view action recognition understanding from exocentric to egocentric perspectivearxiv2023-
Cross-view generalisation in action recognition: Feature design for transitioning from exocentric to egocentric viewsRobot2023-
Learning from semantic alignment between unpaired multiviews for egocentric video recognitionICCV2023Github
Egofish3d: Egocentric 3d pose estimation from a fisheye camera via selfsupervised learningTMM2023Github
Ex2eg-mae: A framework for adaptation of exocentric video masked autoencoders for egocentric social role understandingECCV2024-
Synchronization is all you need: Exocentric-to-egocentric transfer for temporal action segmentation
with unlabeled synchronized video pairs		ECCV2024Github
Unlocking exocentric video-language data for egocentric video representation learningarxiv2024-
EgoPrivacy: What Your First-Person Camera Says About You?arxiv2025Github

✨ Affordance Grounding

TitleVenueYearCode
Learning affordance grounding from exocentric imagesCVPR2022Github
Locate: Localize and transfer object parts for weakly supervised affordance groundingCVPR2023Github
Weakly supervised multimodal affordance grounding for egocentric imagesAAAI2024Github
Self-explainable affordance learning with embodied captionarxiv2024-
Strategies to leverage foundational model knowledge in object affordance groundingCVPRW2024-
Intra: Interaction relationship-aware weakly supervised affordance groundingECCV2024-
Learning granularity-aware affordances from humanobject interaction for tool-based functional grasping in dexterous roboticsarxiv2024Github

✨ Remote Drone Teleoperation

TitleVenueYearCode
Droneaugmented human vision: Exocentric control for drones exploring hidden areasTVCG2018-
Third-person piloting: Increasing situational awareness using a spatially coupled second droneUIST2019-
Starhopper: A touch interface for remote object-centric drone navigationGraphics Interface2020-
Birdviewar: Surroundings-aware remote drone piloting using an augmented thirdperson perspectiveCHI2023Github

🔹 Joint Learning

✨ Video Captioning

TitleVenueYearCode
Fourth-Person Captioning: Describing Daily Events by Uni-supervised and Tri-regularized TrainingSMC2018-
Lifelogging caption generation via fourth-person vision in a human–robot symbiotic environmentROBOMECH2020-

✨ Cross-View Retrieval

TitleVenueYearCode
Egotransfer: Transferring motion across egocentric and exocentric domains using deep neural networksarxiv2016-
Actor and observer: Joint modeling of first and third-person videosCVPR2018Github
From Third Person to First Person: Dataset and Baselines for Synthesis and RetrievalCVPRW2019Github
First- and third-person video co-analysis by learning spatial-temporal joint attentionTPAMI2020-
Objectrelator: Enabling cross-view object relation understanding in ego-centric and exo-centric videosarxiv2024Github
Sound Bridge: Associating Egocentric and Exocentric Videos via Audio CuesCVPR2025Github

✨ 3D Camera Localization

TitleVenueYearCode
Relating view directions of complementary-view mobile cameras via the human shadowIJCV2023Github
From a bird’s eye view to see: Joint camera and subject registration without the camera calibrationCVPR2024Github
Yowo: You only walk once to jointly map an indoor scene and register ceiling-mounted camerasTCSVT2024-

✨ Action Understanding

TitleVenueYearCode
Action recognition in the presence of one egocentric and multiple static camerasACCV2014-
An exocentric look at egocentric actions and vice versaCVIU2016-
Recognizing micro-actions and reactions from paired egocentric videosCVPR2016-
Actor and observer: Joint modeling of first and third-person videosCVPR2018Github
Holographic feature learning of egocentric-exocentric videos for multi-domain action recognitionTMM2021-
Holistic-guided disentangled learning with cross-video semantics mining for concurrent first-person and third-person activity recognitionTNNLS2022-
Look both ways: Self-supervising driver gaze estimation and road scene saliencyECCV2022Github
Aide: A vision-driven multi-view, multi-modal, multitasking dataset for assistive driving perceptionICCV2023Github
Learning fine-grained view-invariant representations from unpaired ego-exo videos via temporal alignmentNeurIPS2023Github
Pov: Prompt-oriented view-agnostic learning for egocentric hand-object interaction in the multi-view worldACMMM2023Github
Enhancing egocentric 3d pose estimation with third person viewsPR2023Github
Next-generation surgical navigation: Marker-less multi-view 6dof pose estimation of surgical instrumentsarxiv2023Github
Tell, don’t show: Language guidance eases transfer across domains in images and videosICML2024Github
Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation LearningCVPR2025Github
Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video RepresentationsCVPR2025Github
Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus AdaptationACM MM2025-

✨ Egocentric Wearer Identification

TitleVenueYearCode
Ego2top: Matching viewers in egocentric and top-view videosarxiv2016-
Identifying first-person camera wearers in third-person videosCVPR2017-
Egocentric meets top-viewTPAMI2018
Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignmentECCV2018-
Joint person segmentation and identification in synchronized first- and third-person videosECCV2018Github
Visual-gps: Ego-downward and ambient video based person location associationCVPRW2019-
Seeing the unseen: Predicting the first-person camera wearer’s location and pose in third-person scenesICCVW2021-
Fusing personal and environmental cues for identification and segmentation of first-person camera wearers in third-person viewsCVPR2024Github

✨ Cross-View Human Tracking and Association

TitleVenueYearCode
Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignmentECCV2018-
Complementary-view co-interest person detectionACM MM2020Github
CVMHT: Complementary-view multiple human trackingAAAI2020Github
Multiple human association and tracking from egocentric and complementary top viewsTPAMI2021Github
Connecting the complementary-view videos: Joint camera identification and subject associationCVPR2022Github

✨ Robotic Manipulation

TitleVenueYearCode
Third-Person Visual Imitation Learning via Decoupled Hierarchical ControllerNeulIPS2019GitHub
Vision-based manipulators need to also see from their handsICLR2021Github
Self-supervised disentangled representation learning for third-person imitation learningIROS2021-
Look closer: Bridging egocentric and third-person views with transformers for robotic manipulationarxiv2022Github
Visual-policy learning through multi-camera view to single-camera view knowledge distillation for robot manipulation tasksLRR2023-
Multi-View Masked World Models for Visual Robotic Manipulationarxiv2023Github
Multi-view disentanglement for reinforcement learning with multiple camerasarxiv2024Github

✨ Remote Drone Teleoperation

TitleVenueYearCode
Spatial assisted human-drone collaborative navigation and interaction through immersive mixed realityICRA2024Github

📊 Datasets

Action Understanding

DatasetYearPaperProjectCode
CMU-MMAC2009Guide to the carnegie mellon university multimodal activity (cmu-mmac) databaseProject-
Charades-Ego2018Actor and observer: Joint modeling of first and third-person videosProjectGithub
H2O2021H2o: Two hands manipulating objects for first person interaction recognitionProjectGithub
Assembly1012022Assembly101: A large-scale multi-view video dataset for understanding procedural activitiesProjectGithub
Homage2021Home action genome: Cooperative compositional action understandingProjectGithub
LEMMA2020Lemma: A multiview dataset for le arning m ulti-agent m ulti-task a ctivitiesProjectGithub
FT-HID2022Ft-hid: a large-scale rgb-d dataset for first-and third-person human interaction analysis-Github
EgoPW2022Estimating egocentric 3d human pose in the wild with external weak supervisionProjectGithub
First2Third-Pose2022Enhancing egocentric 3d pose estimation with third person views-GitHub
ARCTIC2023ARCTIC: A dataset for dexterous bimanual hand-object manipulationProjectGithub
ECHP2023Egofish3d: Egocentric 3d pose estimation from a fisheye camera via selfsupervised learning-Github
AssemblyHands2023Assemblyhands: Towards egocentric activity understanding via 3d hand pose estimationProjectGithub
EgoHumans2023Ego-humans: An ego-centric 3d multi-human benchmarkProjectGithub
-2023Next-generation surgical navigation: Marker-less multi-view 6dof pose estimation of surgical instrumentsProject-
ThermoHands2024Thermohands: A benchmark for 3d hand pose estimation from egocentric thermal imageProjectGithub
OVR2024Ovr: A dataset for open vocabulary temporal repetition counting in videos-Github
Nymeria2024Nymeria: A massive collection of multimodal egocentric daily motion in the wildProjectGithub
OAKINK22024Oakink2: A dataset of bimanual hands-object manipulation in complex task completionProjectGithub
CORE4D2024Core4d: A 4d humanobject-human interaction dataset for collaborative object rearrangementProjectGithub
Ego-Exo4D2024Ego-exo4d: Understanding skilled human activity from first-and third-person perspectivesProjectGithub
EgoExoLearn2024Egoexolearn: A dataset for bridging asynchronous ego-and exo-centric view of procedural activities in real world-Github
EgoExo-Fitness2024Egoexo-fitness: Towards egocentric and exocentric full-body action understanding-Github
EgoExOR2025EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding-Github
EPFL-Smart-Kitchen-302025EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models-Github

Driving

DatasetYearPaperProjectCode
LBW2022Look both ways: Self-supervising driver gaze estimation and road scene saliency-Github
AIDE2023Aide: A vision-driven multi-view, multi-modal, multitasking dataset for assistive driving perception-Github
WTS2024Wts: A pedestrian-centric traffic video dataset for fine-grained spatial-temporal understandingProjectGithub

Affordance Grounding

DatasetYearPaperProjectCode
PAD2021One-shot affordance detection-Github
AGD20K2022Learning affordance grounding from exocentric images-Github
FAH2024Learning granularity-aware affordances from humanobject interaction for tool-based functional grasping in dexterous robotics-Github

Generation

DatasetYearPaperProjectCode
ThirdtoFirst2021Ego-exo: Transferring visual representations from third-person to first-person videos-Github

Scene Understanding

DatasetYearPaperProjectCode
360 + x2024360 + x: A panoptic multi-modal scene understanding datasetProjectGithub

Video Question Answering

DatasetYearPaperProjectCode
GazeVQA2023Gazevqa: A video question answering dataset for multiview eye-gaze task-oriented collaborations-Github

Egocentric Wearer Identification

DatasetYearPaperProjectCode
TF20232024Fusing personal and environmental cues for identification and segmentation of first-person camera wearers in third-person views-Github

Cross-View Human Tracking and Association

DatasetYearPaperProjectCode
CVMHT2020Complementary-view multiple human tracking-GitHub
DMHA2022Connecting the complementary-view videos: Joint camera identification and subject association-Github

Camera Registration

DatasetYearPaperProjectCode
-2024From a bird’s eye view to see: Joint camera and subject registration without the camera calibration-Github

Similar repos

Lyman-Smoker/Awesome_Ego_Action

A curated list of Egocentric Action Understanding resources

60

Sid2697/awesome-egocentric-vision

A curated list of egocentric (first-person) vision and related area resources

349

player0718/awesome-ego-video-datasets

🎥 [Awesome] Egocentric / First-Person Video Datasets 📚 Papers, Benchmarks & Resources for Ego…

227

OpenGVLab/EgoExoLearn

[CVPR 2024] Data and benchmark code for the EgoExoLearn dataset

89

yukangcao/Awesome-4D-Spatial-Intelligence

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv…

528

ChanganVR/awesome-embodied-vision

Reading list for research topics in embodied vision

709

hq-King/Awesome-Affordance-Learning

230

PolySummit/Awesome-3D-Reconstruction-and-Generation

🌟 A curate list of papers, datasets, and projects for 3D Reconstruction and Generation.

95

ayiyayi/Awesome-Egocentric-and-Exocentric-Vision

42

12 commits

updated Nov 14, 2025

See the code

README

🌟 Awesome Egocentric-and-Exocentric Vision

Survey Paper Last Updated PRs Welcome Stars

A curated list of papers and datasets on Egocentric (first-person) and Exocentric (third-person) Vision. This repo complements our survey and is continuously updated.

📖 Contents

📑 Papers

🔹 Egocentric for Exocentric

✨ Video Generation

TitleVenueYearCode
Intention-driven Ego-to-Exo Video Generationarxiv2024-
Ego-to-Exo: Interfacing Third Person Visuals from Egocentric Views in Real-time for Improved ROV Teleoperationarxiv2024-

✨ Action Understanding

TitleVenueYearCode
From my view to yours: Egoaugmented learning in large vision language models
for understanding exocentric daily living activities		arxiv2025Github

✨ View Birdification

TitleVenueYearCode
View birdification in the crowd: Ground-plane localization from perceived movementsarxiv2021-
Viewbirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric viewRAL2022-
Incrowdformer: On-ground pedestrian world model from egocentric viewsarxiv2023-

✨ View Selection

TitleVenueYearCode
Camera selection for occlusion-less surgery recording via training with an egocentric cameraAccess2021-

🔹 Exocentric for Egocentric

✨ Video Generation

TitleVenueYearCode
From third person to first person: Dataset and baselines for synthesis and retrievalCVPRW2019Github
Crossview exocentric to egocentric video synthesisarxiv2021-
Parallel generative adversarial network for third-person to first-person image generationCVPRW2022-
Towards third-person visual imitation learning using generative adversarial networksICDL2022-
4diff: 3d-aware diffusion model for third-to-first viewpoint translationECCV2024Github
Diffusing in someone else’s shoes: Robotic perspective taking with diffusionHumanoids2024Github
Put myself in your shoes: Lifting the egocentric perspective from exocentric videosECCV2024-
Exocentric-to-EgocentricVideoGenerationNeulIPS2024Github
EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric VideosICLR2025-

✨ Video Captioning

TitleVenueYearCode
Exo2egodvc: Dense video captioning of egocentric procedural activities using web instructional videosWACV2023Github
Retrieval-augmented egocentric video captioningCVPR2024Github

✨ Action Understanding

TitleVenueYearCode
Unsupervised and semi-supervised domain adaptation for action recognition from dronesWACV2020-
Ego-exo: Transferring visual representations from third-person to first-person videosCVPR2021Github
Audio-Adaptive Activity Recognition Across Video DomainsCVPR2022Github
Estimating egocentric 3d human pose in the wild with external weak supervisionCVPR2022Github
Cross-view action recognition understanding from exocentric to egocentric perspectivearxiv2023-
Cross-view generalisation in action recognition: Feature design for transitioning from exocentric to egocentric viewsRobot2023-
Learning from semantic alignment between unpaired multiviews for egocentric video recognitionICCV2023Github
Egofish3d: Egocentric 3d pose estimation from a fisheye camera via selfsupervised learningTMM2023Github
Ex2eg-mae: A framework for adaptation of exocentric video masked autoencoders for egocentric social role understandingECCV2024-
Synchronization is all you need: Exocentric-to-egocentric transfer for temporal action segmentation
with unlabeled synchronized video pairs		ECCV2024Github
Unlocking exocentric video-language data for egocentric video representation learningarxiv2024-
EgoPrivacy: What Your First-Person Camera Says About You?arxiv2025Github

✨ Affordance Grounding

TitleVenueYearCode
Learning affordance grounding from exocentric imagesCVPR2022Github
Locate: Localize and transfer object parts for weakly supervised affordance groundingCVPR2023Github
Weakly supervised multimodal affordance grounding for egocentric imagesAAAI2024Github
Self-explainable affordance learning with embodied captionarxiv2024-
Strategies to leverage foundational model knowledge in object affordance groundingCVPRW2024-
Intra: Interaction relationship-aware weakly supervised affordance groundingECCV2024-
Learning granularity-aware affordances from humanobject interaction for tool-based functional grasping in dexterous roboticsarxiv2024Github

✨ Remote Drone Teleoperation

TitleVenueYearCode
Droneaugmented human vision: Exocentric control for drones exploring hidden areasTVCG2018-
Third-person piloting: Increasing situational awareness using a spatially coupled second droneUIST2019-
Starhopper: A touch interface for remote object-centric drone navigationGraphics Interface2020-
Birdviewar: Surroundings-aware remote drone piloting using an augmented thirdperson perspectiveCHI2023Github

🔹 Joint Learning

✨ Video Captioning

TitleVenueYearCode
Fourth-Person Captioning: Describing Daily Events by Uni-supervised and Tri-regularized TrainingSMC2018-
Lifelogging caption generation via fourth-person vision in a human–robot symbiotic environmentROBOMECH2020-

✨ Cross-View Retrieval

TitleVenueYearCode
Egotransfer: Transferring motion across egocentric and exocentric domains using deep neural networksarxiv2016-
Actor and observer: Joint modeling of first and third-person videosCVPR2018Github
From Third Person to First Person: Dataset and Baselines for Synthesis and RetrievalCVPRW2019Github
First- and third-person video co-analysis by learning spatial-temporal joint attentionTPAMI2020-
Objectrelator: Enabling cross-view object relation understanding in ego-centric and exo-centric videosarxiv2024Github
Sound Bridge: Associating Egocentric and Exocentric Videos via Audio CuesCVPR2025Github

✨ 3D Camera Localization

TitleVenueYearCode
Relating view directions of complementary-view mobile cameras via the human shadowIJCV2023Github
From a bird’s eye view to see: Joint camera and subject registration without the camera calibrationCVPR2024Github
Yowo: You only walk once to jointly map an indoor scene and register ceiling-mounted camerasTCSVT2024-

✨ Action Understanding

TitleVenueYearCode
Action recognition in the presence of one egocentric and multiple static camerasACCV2014-
An exocentric look at egocentric actions and vice versaCVIU2016-
Recognizing micro-actions and reactions from paired egocentric videosCVPR2016-
Actor and observer: Joint modeling of first and third-person videosCVPR2018Github
Holographic feature learning of egocentric-exocentric videos for multi-domain action recognitionTMM2021-
Holistic-guided disentangled learning with cross-video semantics mining for concurrent first-person and third-person activity recognitionTNNLS2022-
Look both ways: Self-supervising driver gaze estimation and road scene saliencyECCV2022Github
Aide: A vision-driven multi-view, multi-modal, multitasking dataset for assistive driving perceptionICCV2023Github
Learning fine-grained view-invariant representations from unpaired ego-exo videos via temporal alignmentNeurIPS2023Github
Pov: Prompt-oriented view-agnostic learning for egocentric hand-object interaction in the multi-view worldACMMM2023Github
Enhancing egocentric 3d pose estimation with third person viewsPR2023Github
Next-generation surgical navigation: Marker-less multi-view 6dof pose estimation of surgical instrumentsarxiv2023Github
Tell, don’t show: Language guidance eases transfer across domains in images and videosICML2024Github
Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation LearningCVPR2025Github
Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video RepresentationsCVPR2025Github
Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus AdaptationACM MM2025-

✨ Egocentric Wearer Identification

TitleVenueYearCode
Ego2top: Matching viewers in egocentric and top-view videosarxiv2016-
Identifying first-person camera wearers in third-person videosCVPR2017-
Egocentric meets top-viewTPAMI2018
Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignmentECCV2018-
Joint person segmentation and identification in synchronized first- and third-person videosECCV2018Github
Visual-gps: Ego-downward and ambient video based person location associationCVPRW2019-
Seeing the unseen: Predicting the first-person camera wearer’s location and pose in third-person scenesICCVW2021-
Fusing personal and environmental cues for identification and segmentation of first-person camera wearers in third-person viewsCVPR2024Github

✨ Cross-View Human Tracking and Association

TitleVenueYearCode
Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignmentECCV2018-
Complementary-view co-interest person detectionACM MM2020Github
CVMHT: Complementary-view multiple human trackingAAAI2020Github
Multiple human association and tracking from egocentric and complementary top viewsTPAMI2021Github
Connecting the complementary-view videos: Joint camera identification and subject associationCVPR2022Github

✨ Robotic Manipulation

TitleVenueYearCode
Third-Person Visual Imitation Learning via Decoupled Hierarchical ControllerNeulIPS2019GitHub
Vision-based manipulators need to also see from their handsICLR2021Github
Self-supervised disentangled representation learning for third-person imitation learningIROS2021-
Look closer: Bridging egocentric and third-person views with transformers for robotic manipulationarxiv2022Github
Visual-policy learning through multi-camera view to single-camera view knowledge distillation for robot manipulation tasksLRR2023-
Multi-View Masked World Models for Visual Robotic Manipulationarxiv2023Github
Multi-view disentanglement for reinforcement learning with multiple camerasarxiv2024Github

✨ Remote Drone Teleoperation

TitleVenueYearCode
Spatial assisted human-drone collaborative navigation and interaction through immersive mixed realityICRA2024Github

📊 Datasets

Action Understanding

DatasetYearPaperProjectCode
CMU-MMAC2009Guide to the carnegie mellon university multimodal activity (cmu-mmac) databaseProject-
Charades-Ego2018Actor and observer: Joint modeling of first and third-person videosProjectGithub
H2O2021H2o: Two hands manipulating objects for first person interaction recognitionProjectGithub
Assembly1012022Assembly101: A large-scale multi-view video dataset for understanding procedural activitiesProjectGithub
Homage2021Home action genome: Cooperative compositional action understandingProjectGithub
LEMMA2020Lemma: A multiview dataset for le arning m ulti-agent m ulti-task a ctivitiesProjectGithub
FT-HID2022Ft-hid: a large-scale rgb-d dataset for first-and third-person human interaction analysis-Github
EgoPW2022Estimating egocentric 3d human pose in the wild with external weak supervisionProjectGithub
First2Third-Pose2022Enhancing egocentric 3d pose estimation with third person views-GitHub
ARCTIC2023ARCTIC: A dataset for dexterous bimanual hand-object manipulationProjectGithub
ECHP2023Egofish3d: Egocentric 3d pose estimation from a fisheye camera via selfsupervised learning-Github
AssemblyHands2023Assemblyhands: Towards egocentric activity understanding via 3d hand pose estimationProjectGithub
EgoHumans2023Ego-humans: An ego-centric 3d multi-human benchmarkProjectGithub
-2023Next-generation surgical navigation: Marker-less multi-view 6dof pose estimation of surgical instrumentsProject-
ThermoHands2024Thermohands: A benchmark for 3d hand pose estimation from egocentric thermal imageProjectGithub
OVR2024Ovr: A dataset for open vocabulary temporal repetition counting in videos-Github
Nymeria2024Nymeria: A massive collection of multimodal egocentric daily motion in the wildProjectGithub
OAKINK22024Oakink2: A dataset of bimanual hands-object manipulation in complex task completionProjectGithub
CORE4D2024Core4d: A 4d humanobject-human interaction dataset for collaborative object rearrangementProjectGithub
Ego-Exo4D2024Ego-exo4d: Understanding skilled human activity from first-and third-person perspectivesProjectGithub
EgoExoLearn2024Egoexolearn: A dataset for bridging asynchronous ego-and exo-centric view of procedural activities in real world-Github
EgoExo-Fitness2024Egoexo-fitness: Towards egocentric and exocentric full-body action understanding-Github
EgoExOR2025EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding-Github
EPFL-Smart-Kitchen-302025EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models-Github

Driving

DatasetYearPaperProjectCode
LBW2022Look both ways: Self-supervising driver gaze estimation and road scene saliency-Github
AIDE2023Aide: A vision-driven multi-view, multi-modal, multitasking dataset for assistive driving perception-Github
WTS2024Wts: A pedestrian-centric traffic video dataset for fine-grained spatial-temporal understandingProjectGithub

Affordance Grounding

DatasetYearPaperProjectCode
PAD2021One-shot affordance detection-Github
AGD20K2022Learning affordance grounding from exocentric images-Github
FAH2024Learning granularity-aware affordances from humanobject interaction for tool-based functional grasping in dexterous robotics-Github

Generation

DatasetYearPaperProjectCode
ThirdtoFirst2021Ego-exo: Transferring visual representations from third-person to first-person videos-Github

Scene Understanding

DatasetYearPaperProjectCode
360 + x2024360 + x: A panoptic multi-modal scene understanding datasetProjectGithub

Video Question Answering

DatasetYearPaperProjectCode
GazeVQA2023Gazevqa: A video question answering dataset for multiview eye-gaze task-oriented collaborations-Github

Egocentric Wearer Identification

DatasetYearPaperProjectCode
TF20232024Fusing personal and environmental cues for identification and segmentation of first-person camera wearers in third-person views-Github

Cross-View Human Tracking and Association

DatasetYearPaperProjectCode
CVMHT2020Complementary-view multiple human tracking-GitHub
DMHA2022Connecting the complementary-view videos: Joint camera identification and subject association-Github

Camera Registration

DatasetYearPaperProjectCode
-2024From a bird’s eye view to see: Joint camera and subject registration without the camera calibration-Github

Similar repos

Lyman-Smoker/Awesome_Ego_Action

A curated list of Egocentric Action Understanding resources

60

Sid2697/awesome-egocentric-vision

A curated list of egocentric (first-person) vision and related area resources

349

player0718/awesome-ego-video-datasets

🎥 [Awesome] Egocentric / First-Person Video Datasets 📚 Papers, Benchmarks & Resources for Ego…

227

OpenGVLab/EgoExoLearn

[CVPR 2024] Data and benchmark code for the EgoExoLearn dataset

89

yukangcao/Awesome-4D-Spatial-Intelligence

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv…

528

ChanganVR/awesome-embodied-vision

Reading list for research topics in embodied vision

709

hq-King/Awesome-Affordance-Learning

230

PolySummit/Awesome-3D-Reconstruction-and-Generation

🌟 A curate list of papers, datasets, and projects for 3D Reconstruction and Generation.

95