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.
InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model
Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos
An Analysis of Data Transformation Effects on Segment Anything 2
Fine-Grained Video Captioning through Scene Graph Consolidation
LongCaptioning: Unlocking the Power of Long Caption Generation in Large Multimodal Models
AVD2: Accident Video Diffusion for Accident Video Description
MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
Contrast-Unity for Partially-Supervised Temporal Sentence Grounding
iMOVE: Instance-Motion-Aware Video Understanding
VRoPE: Rotary Position Embedding for Video Large Language Models
video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
A Survey on Mamba Architecture for Vision Applications
Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis
CoS: Chain-of-Shot Prompting for Long Video Understanding
A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray
Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives
VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
AIN: The Arabic INclusive Large Multimodal Model
Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
Understanding Long Videos via LLM-Powered Entity Relation Graphs
TinyLLaVA-Video: A Simple Framework of Small-scale Large Multimodal Models for Video Understanding
HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.