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.
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision
Learning Object State Changes in Videos: An Open-World Perspective
Text-Conditioned Resampler For Long Form Video Understanding
ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room
Full-reference Video Quality Assessment for User Generated Content Transcoding
Artificial intelligence optical hardware empowers high-resolution hyperspectral video understanding at 1.2 Tb/s
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models
RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation
Grounded Question-Answering in Long Egocentric Videos
Audio-Visual LLM for Video Understanding
MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding
Retrieval-based Video Language Model for Efficient Long Video Question Answering
Action Scene Graphs for Long-Form Understanding of Egocentric Videos
HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Zero-Shot Video Question Answering with Procedural Programs
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding
CAST: Cross-Attention in Space and Time for Video Action Recognition
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation
DEVIAS: Learning Disentangled Video Representations of Action and Scene
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
Panoptic Video Scene Graph Generation
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning
BatchNorm-based Weakly Supervised Video Anomaly Detection
Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
PG-Video-LLaVA: Pixel Grounding Large Video-Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.