Action Recognition

FlyPose: Towards Robust Human Pose Estimation From Aerial Views WACV 2026 Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding CVPR 2026 From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities WACV 2026 Gamba: Mamba-based graph convolutional network with dynamic graph topology learning for action recognition CVPR 2026 GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents ACL 2026 GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection WACV 2026 HandWorld: Hand-Centric Unified Video Action Generation CVPR 2026 HARK: Hierarchical Agentic Retrieval with Keyframing for Video Understanding (Student Abstract) AAAI 2026 InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding ACL 2026 IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes AAAI 2026 LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation CVPR 2026 LASER: Lip Landmark Assisted Speaker Detection for Robustness WACV 2026 Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation CVPR 2026 Learning Action Hierarchies via Hybrid Geometric Diffusion WACV 2026 Learning Dynamics as Feedback: An Adaptive Entropy Flow Dynamics Framework for Long-tailed Human Action Recognition AAAI 2026 Learning Time in Static Classifiers AAAI 2026 Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding WACV 2026 Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data AAAI 2026 MA-Bench: Towards Fine-grained Micro-Action Understanding CVPR 2026 Memory Matters: Boosting Training-Free Zero-Shot Temporal Action Localization with a Learnable Lookup Table CVPR 2026 MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction WACV 2026 MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions WACV 2026 mmPred: Radar-based Human Motion Prediction in the Dark AAAI 2026 MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment CVPR 2026 MooCap: A Multi-View Benchmark for Cow-Object-Human Interaction and Behavior Dynamics CVPR 2026