video understanding

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding CVPR 2026 HARK: Hierarchical Agentic Retrieval with Keyframing for Video Understanding (Student Abstract) AAAI 2026 Harnessing Object Grounding for Time-Sensitive Video Understanding WACV 2026 HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering CVPR 2026 HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding ACL 2026 Hierarchical Action Learning for Weakly-Supervised Action Segmentation CVPR 2026 Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information WACV 2026 HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge ACL 2026 HTTrack: Learning to Perceive Targets via Historical Trajectories in Satellite Video Tracking AAAI 2026 HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks CVPR 2026 Hybrid State Representation for Video Procedure Planning WACV 2026 KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding WACV 2026 KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs AAAI 2026 Learning Action Hierarchies via Hybrid Geometric Diffusion WACV 2026 Learning Spatio-temporal Feature Representations for Video-based Gaze Estimation WACV 2026 Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models CVPR 2026 Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding WACV 2026 LensWalk: Agentic Video Understanding by Planning How You See in Videos CVPR 2026 Let VLMs Grade Their Own Thoughts: A Self-Quantification Approach to Reasoning-Aware Reward Modeling CVPR 2026 LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding AAAI 2026 LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding CVPR 2026 MA-Bench: Towards Fine-grained Micro-Action Understanding CVPR 2026 MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX AAAI 2026 MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding WACV 2026 MeToM: Metadata-Guided Token Merging for Efficient Video LLMs CVPR 2026