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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/4paradigm-cv/se-stad
공식 코드A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector
https://github.com/983632847/sam-for-videos
공식 코드https://github.com/AleksandrIvchenko/QoE-assesment
공식 코드Study on the Assessment of the Quality of Experience of Streaming Video
https://github.com/AleksandrIvchenko/QoE-models
공식 코드Study on the Assessment of the Quality of Experience of Streaming Video
https://github.com/Alena-Xinran/MaTAV
공식 코드Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations
https://github.com/AmmarKamoona/Multiple-Instance-Based-Video-Anomaly-Detection-Using-Deep-Temporal-Encoding-Decoding
공식 코드Multiple Instance-Based Video Anomaly Detection using Deep Temporal Encoding-Decoding
https://github.com/ArrowLuo/CLIP4Clip
공식 코드CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
https://github.com/Baoliang93/GSTVQA
공식 코드https://github.com/BriansIDP/video-SALMONN-o1
공식 코드video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
https://github.com/Buzz-Beater/EgoTaskQA
공식 코드https://github.com/ChenHsing/Awesome-Video-Diffusion-Models
공식 코드https://github.com/Cogito2012/CarCrashDataset
공식 코드Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
https://github.com/Cogito2012/UString
공식 코드Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
https://github.com/CompVis/image2video-synthesis-using-cINNs
공식 코드https://github.com/DAVEISHAN/TCLR
공식 코드TCLR: Temporal Contrastive Learning for Video Representation
https://github.com/Darcyddx/Video-LLM
공식 코드https://github.com/DavidZhang73/AssemblyVideoManualAlignment
공식 코드Aligning Step-by-Step Instructional Diagrams to Video Demonstrations
https://github.com/DeLightCMU/ElaborativeRehearsal
공식 코드https://github.com/DeepSportRadar/ball-3d-localization-challenge
공식 코드DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
https://github.com/Dod-o/VT-SSum
공식 코드VT-SSum: A Benchmark Dataset for Video Transcript Segmentation and Summarization
https://github.com/Epiphqny/VisTR
공식 코드https://github.com/EvalCrafter/EvalCrafter
공식 코드EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
https://github.com/FlagOpen/FlagEmbedding/tree/master/MLVU
공식 코드https://github.com/FlappyPeggy/DMAD
공식 코드https://github.com/FranzHahn/NPL-50-3-2595-2608-Correction
공식 코드Critical analysis on the reproducibility of visual quality assessment using deep features
https://github.com/GZHU-DVL/CLIPVQA
공식 코드https://github.com/HJYao00/DenseConnector
공식 코드https://github.com/HJYao00/Side4Video
공식 코드Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning
https://github.com/Hasnat79/UAL_Bench
공식 코드UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
https://github.com/HopLee6/VJMHT-PyTorch
공식 코드Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
https://github.com/HumamAlwassel/DETAD
공식 코드https://github.com/HumanMLLM/LLaVA-Scissor
공식 코드LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
https://github.com/IVGSZ/Flash-VStream
공식 코드Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
https://github.com/IsaacChanghau/VSLNet
공식 코드Span-based Localizing Network for Natural Language Video Localization
https://github.com/IuliaDuta/RSTG
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.