Papers with Code 아카이브
Video Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 0
- 보존된 평가 기록
- 0
A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis
CyberV: Cybernetics for Test-time Scaling in Video Understanding
Audio-Sync Video Generation with Multi-Stream Temporal Control
Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision
Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models
DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation
APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval
TextVidBench: A Benchmark for Long Video Scene Text Understanding
AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
InterRVOS: Interaction-aware Referring Video Object Segmentation
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
EgoVLM: Policy Optimization for Egocentric Video Understanding
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
Scene Detection Policies and Keyframe Extraction Strategies for Large-Scale Video Analysis
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
DisTime: Distribution-based Time Representation for Video Large Language Models
VUDG: A Dataset for Video Understanding Domain Generalization
Learning reusable concepts across different egocentric video understanding tasks
VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software
Time Blindness: Why Video-Language Models Can't See What Humans Can?
SiLVR: A Simple Language-based Video Reasoning Framework
PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection
ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding
Universal Visuo-Tactile Video Understanding for Embodied Interaction
VidText: Towards Comprehensive Evaluation for Video Text Understanding
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.