Action Recognition

Temporal Relational Modeling with Self-Supervision for Action Segmentation AAAI 2021 Temporal Relation based Attentive Prototype Network for Few-shot Action Recognition ACML 2021 Temporal Segmentation of Fine-gained Semantic Action: A Motion-Centered Figure Skating Dataset AAAI 2021 The IKEA ASM Dataset: Understanding People Assembling Furniture Through Actions, Objects and Pose WACV 2021 The MECCANO Dataset: Understanding Human-Object Interactions From Egocentric Videos in an Industrial-Like Domain WACV 2021 Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations CVPR 2021 TokenLearner: Adaptive Space-Time Tokenization for Videos NeurIPS 2021 Towards a Methodology Supporting Semiautomatic Annotation of HeadMovements in Video-recorded Conversations EMNLP 2021 Towards Long-Form Video Understanding CVPR 2021 Towards Unified Surgical Skill Assessment CVPR 2021 “Train one, Classify one, Teach one” - Cross-surgery transfer learning for surgical step recognition MIDL 2021 TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild ICCV 2021 UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles CVPR 2021 Understanding the Robustness of Skeleton-Based Action Recognition Under Adversarial Attack CVPR 2021 Unifying Nonlocal Blocks for Neural Networks ICCV 2021 Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition ICCV 2021 Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation ICCV 2021 Video Action Recognition with Neural Architecture Search ACML 2021 VideoLT: Large-Scale Long-Tailed Video Recognition 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 VideoSSL: Semi-Supervised Learning for Video Classification WACV 2021 Visual Alignment Constraint for Continuous Sign Language Recognition ICCV 2021 Visual Semantic Role Labeling for Video Understanding CVPR 2021 Weakly Supervised Action Selection Learning in Video CVPR 2021