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.
Overview of Tencent Multi-modal Ads Video Understanding Challenge
A Survey on Temporal Sentence Grounding in Videos
Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
Multi-modal Representation Learning for Video Advertisement Content Structuring
Spatio-Temporal Perturbations for Video Attribution
LIGAR: Lightweight General-purpose Action Recognition
A survey on IQA
Identity-aware Graph Memory Network for Action Detection
StarVQA: Space-Time Attention for Video Quality Assessment
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency
Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
MUSIQ: Multi-scale Image Quality Transformer
AutoVideo: An Automated Video Action Recognition System
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning
Token Shift Transformer for Video Classification
Elaborative Rehearsal for Zero-shot Action Recognition
Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization
HR-Crime: Human-Related Anomaly Detection in Surveillance Videos
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
CogME: A Cognition-Inspired Multi-Dimensional Evaluation Metric for Story Understanding
Disentangle Your Dense Object Detector
Spatio-Temporal Context for Action Detection
Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection
Can An Image Classifier Suffice For Action Recognition?
Video Swin Transformer
FOVQA: Blind Foveated Video Quality Assessment
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
Towards Long-Form Video Understanding
Learning the Predictability of the Future
Discerning Generic Event Boundaries in Long-Form Wild Videos
End-to-end Temporal Action Detection with Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.