← Analysis
Computer Vision › Analysis ›

Action Recognition

1421 directly classified papers

Papers per year

Papers

Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning ICCV 2025
Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection AAAI 2025
Heterogeneous Skeleton-Based Action Representation Learning CVPR 2025
Condensing Action Segmentation Datasets via Generative Network Inversion CVPR 2025
DEEP: an automatic bidirectional translator leveraging an ASR for translation of Italian sign language ACL 2025
Temporal Alignment-Free Video Matching for Few-shot Action Recognition CVPR 2025
Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information ICCV 2025
DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding ICCV 2025
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence AAAI 2025
HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation AAAI 2025
SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis ICCV 2025
Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on ASL Videos IJCNLP 2025
Anomize: Better Open Vocabulary Video Anomaly Detection CVPR 2025
Automated Patient Positioning with Learned 3D Hand Gestures WACV 2025
Proxy-Bridged Game Transformer for Interactive Extreme Motion Prediction ICCV 2025
Temporal Rate Reduction Clustering for Human Motion Segmentation ICCV 2025
Hierarchical-aware Orthogonal Disentanglement Framework for Fine-grained Skeleton-based Action Recognition ICCV 2025
Scaling Action Detection: AdaTAD++ with Transformer-Enhanced Temporal-Spatial Adaptation ICCV 2025
Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition ICCV 2025
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation ICCV 2025
SceneMI: Motion In-betweening for Modeling Human-Scene Interaction ICCV 2025
ConvMixFormer- A Resource-Efficient Convolution Mixer for Transformer-Based Dynamic Hand Gesture Recognition WACV 2025
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition ICCV 2025
RobAVA: A Large-scale Dataset and Baseline Towards Video based Robotic Arm Action Understanding ICCV 2025
SignRep: Enhancing Self-Supervised Sign Representations ICCV 2025