action recognition

957 papers

Explore in graph

Also known as

HAR AAR

Co-occurring keywords

video understanding (1647) self-supervised learning (3751) contrastive learning (3979) convolutional neural network (4216) temporal modeling (468) multimodal learning (4622) representation learning (6174) video classification (215) video representation (150) weakly supervised learning (1323)

Papers

Temporal Relation based Attentive Prototype Network for Few-shot Action Recognition ACML 2021

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering ACL 2021

Selective Feature Compression for Efficient Activity Recognition Inference ICCV 2021

Refining Activation Downsampling With SoftPool ICCV 2021

Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity ICCV 2021

Action-Conditioned 3D Human Motion Synthesis With Transformer VAE ICCV 2021

Motion-Augmented Self-Training for Video Recognition at Smaller Scale ICCV 2021

Just One Moment: Structural Vulnerability of Deep Action Recognition Against One Frame Attack ICCV 2021

H2O: Two Hands Manipulating Objects for First Person Interaction Recognition ICCV 2021

Multi-Modal Multi-Action Video Recognition ICCV 2021

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization CVPR 2021

WhyAct: Identifying Action Reasons in Lifestyle Vlogs EMNLP 2021

Searching for Two-Stream Models in Multivariate Space for Video Recognition ICCV 2021

Learning Self-Similarity in Space and Time As Generalized Motion for Video Action Recognition ICCV 2021

Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data ICCV 2021

Action-guided 3D Human Motion Prediction NIPS 2021

MAU: A Motion-Aware Unit for Video Prediction and Beyond NIPS 2021

Reformulating Zero-shot Action Recognition for Multi-label Actions NIPS 2021

OadTR: Online Action Detection With Transformers ICCV 2021

Vi2CLR: Video and Image for Visual Contrastive Learning of Representation ICCV 2021

ASCNet: Self-Supervised Video Representation Learning With Appearance-Speed Consistency ICCV 2021

Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition ICCV 2021

Video Self-Stitching Graph Network for Temporal Action Localization ICCV 2021

Home Action Genome: Cooperative Compositional Action Understanding CVPR 2021

SSA2D: Single Shot Actor-Action Detection in Videos (Student Abstract) AAAI 2021