← Processing
Computer Vision › Processing ›

Video Understanding

1592 directly classified papers

Papers per year

Papers

Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising AAAI 2025
Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models CVPR 2025
Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence WACV 2025
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation CVPR 2025
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers ICCV 2025
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents ICCV 2025
Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding ICCV 2025
Language Repository for Long Video Understanding ACL 2025
Streaming VideoLLMs for Real-Time Procedural Video Understanding ICCV 2025
HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation CVPR 2025
VisTRA: Visual Tool-use Reasoning Analyzer for Small Object Visual Question Answering ACL 2025
TACO: Taming Diffusion for in-the-wild Video Amodal Completion ICCV 2025
Online Generic Event Boundary Detection ICCV 2025
Efficient Motion-Aware Video MLLM CVPR 2025
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation ACL 2025
MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance ICCV 2025
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction CVPR 2025
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models ACL 2025
Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering CVPR 2025
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory ICCV 2025
BVINet: Unlocking Blind Video Inpainting with Zero Annotations ICCV 2025
HERO: Human Reaction Generation from Videos ICCV 2025
Diffusion-based 3D Hand Motion Recovery with Intuitive Physics ICCV 2025
Predicting Implicit Arguments in Procedural Video Instructions ACL 2025
MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning ICCV 2025