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.
F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking
How Can Objects Help Video-Language Understanding?
VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding
SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models
From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction
InstructionBench: An Instructional Video Understanding Benchmark
Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
Re-thinking Temporal Search for Long-Form Video Understanding
Moment Quantization for Video Temporal Grounding
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
Slow-Fast Architecture for Video Multi-Modal Large Language Models
TimeSearch: Hierarchical Video Search with Spotlight and Reflection for Human-like Long Video Understanding
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?
Aligned Better, Listen Better for Audio-Visual Large Language Models
H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding
DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition
OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model
Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding
From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations
PAVE: Patching and Adapting Video Large Language Models
ACVUBench: Audio-Centric Video Understanding Benchmark
Breaking the Encoder Barrier for Seamless Video-Language Understanding
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
AMD-Hummingbird: Towards an Efficient Text-to-Video Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.