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.
FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation
$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues
Assessment of Subjective and Objective Quality of Live Streaming Sports Videos
VT-SSum: A Benchmark Dataset for Video Transcript Segmentation and Summarization
Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Technical Report: Temporal Aggregate Representations
Transformed ROIs for Capturing Visual Transformations in Videos
Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP
Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions
MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
Relation-aware Hierarchical Attention Framework for Video Question Answering
Real-Time Anomaly Detection and Feature Analysis Based on Time Series for Surveillance Video
Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Stochastic Image-to-Video Synthesis using cINNs
FrameExit: Conditional Early Exiting for Efficient Video Recognition
Improving precision of objective image/video quality metrics
Skimming and Scanning for Untrimmed Video Action Recognition
Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Temporal Query Networks for Fine-grained Video Understanding
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
Temporally smooth online action detection using cycle-consistent future anticipation
Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning
ADNet: Temporal Anomaly Detection in Surveillance Videos
Adaptive Intermediate Representations for Video Understanding
Crossover Learning for Fast Online Video Instance Segmentation
Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation
FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
TubeR: Tubelet Transformer for Video Action Detection
Visual Semantic Role Labeling for Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.