TOC

First person body pose estimation

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions, ArXiv'19 {notes} {paper} {project page} {missing dataset?}

Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video, CVPR'17 {notes} {paper} {project page} {code.gz} {dataset.zip}

3D ego-pose estimation via imitation learning. ECCV'18 {paper}

Motion Capture from Body-Mounted Cameras, SIGGRAPH'11 {paper} {project page}

Hand detection

Analysis of the hands in egocentric vision: A survey, ArXiv'19 paper

Contextual Attention for Hand Detection in the Wild, ICCV'19 {notes} {paper} {project page} {code, Keras}

Analysis of Hand Segmentation in the Wild, CVPR'19 {paper} {code, Matlab}

Pixel-level Hand Detection for Ego-centric Videos, CVPR'13 {paper}

Object affordances

Grounded Human-Object Interaction Hotspots from Video, ICCV'19 {notes} {paper} {project page} {code PyTorch}

Generating 3D People in Scenes without People, ArXiv'19 {paper} {notes}

Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments, CVPR'19 {paper} {notes}

EGO-TOPO: Environment Affordances from Egocentric Video, ArXiv'20 {project page} {paper} {notes}

Object manipulation

Learning a Generative Model for Multi-Step Human–Object Interactions from Videos, Eurographics'19, {paper} {video}

Video-based Hand Manipulation Capture Through Composite Motion Control, SIGGRAPH'13 {paper} {video}

Object discovery

Object Discovery in Videos as Foreground Motion Clustering, CVPR19 {paper} {poster} {notes}

Next-Active-Object prediction from Egocentric Videos, JVCI'17 {paper} {project page}

Figure-Ground Segmentation Improves Handled Object Recognition in Egocentric Video, CVPR'10 {paper}

Manipulation generation

paper

An Example-Based Motion Synthesis Technique for Locomotion and Object Manipulation, SIGGRAPH'12 {paper} {video}

Task-based Locomotion, TOG'16 {project page} {paper}

Data-Driven Animation of Hand-Object Interactions, Conference on Automatic Face and Gesture Recognition'11 paper video

Motion clustering

Convolutional Sequence Generation for Skeleton-Based Action Synthesis, ICCV'19 {paper} {code}

Learning Trajectory Dependencies for Human Motion Prediction, ICCV'19 {paper} {code}{notes}

Graph Embedded Pose Clustering for Anomaly Detection, ArXiv'19 {paper} {code}

Efficient Unsupervised Temporal Segmentation of Motion Data, TPAMI'15 (?) {paper}

Metric Learning from Poses for Temporal Clustering of Human Motion, BMVC'12 {paper}

Human Motion Analysis with Deep Metric Learning, ECCV'18 {paper} {non official code} {ArXiv} {notes}

Human Motion Prediction via Spatio-Temporal Inpainting, ICCV'19 {paper} {ArXiv}

Structured Prediction Helps 3D Human Motion Modelling, ICCV'19 {project page} {paper} {code} {notes}

Human Motion Anticipation with Symbolic Label, ArXiv'19 {paper}

Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks, ACM Multimedia'16 {paper}

Imitation Learning for Human Pose Prediction, ICCV'19 [{paper}]

DLow: Diversifying Latent Flows for Diverse Human Motion Prediction {paper}

Action recognition

Skeleton-based

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition, CVPR'19, {paper} {code} {notes}

Bayesian Hierarchical Dynamic Model for Human Action Recognition, CVPR'19 {paper} {matlab code} [{bib, supp}](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_Bayesian_Hierarchical_Dynamic_Model_for_Human_Action_Recognition_CVPR_2019_paper.html

Graph Embedded Pose Clustering for Anomaly Detection, ArXiv'19, {paper} {code}

Efficient Temporal Sequence Comparison and Classification using Gram Matrix Embeddings On a Riemannian Manifold, CVPR'16 {paper} {matlab code} {project page}

Ego-centric

Fine-Grained Action Retrieval through Multiple Parts-of-Speech Embeddings, ICCV'19 {project page} {paper} {notes}

Learning Visual Actions Using Multiple Verb-Only Labels, BMVC'19 {paper} {notes}

Evaluates on Epic

EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition ICCV'19 {paper} {code (PyTorch)} {project page}

Audiovisual SlowFast Networks for Video Recognition, ArXiv'20 {paper} {code soon}

LSTA: Long Short-Term Attention for Egocentric Action Recognition, CVPR'19 {paper}

Action recognition

Video Action Transformer Network, CVPR'19 {paper} {project page}