https://github.com/JoshuaEbenezer/ChipQA
공식 코드ChipQA: No-Reference Video Quality Prediction via Space-Time Chips
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/JoshuaEbenezer/ChipQA-0
공식 코드No-Reference Video Quality Assessment Using Space-Time Chips
https://github.com/JustinYuu/MACIL_SD
공식 코드https://github.com/JustinYuu/MM_Pyramid
공식 코드https://github.com/KimManjin/RSA
공식 코드Relational Self-Attention: What's Missing in Attention for Video Understanding
https://github.com/LargeWorldModel/LWM
공식 코드World Model on Million-Length Video And Language With Blockwise RingAttention
https://github.com/MCG-NJU/MultiSports
공식 코드MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
https://github.com/MCG-NJU/RTD-Action
공식 코드Relaxed Transformer Decoders for Direct Action Proposal Generation
https://github.com/MCG-NJU/VideoMAE
공식 코드VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://github.com/MCG-NJU/VideoMAE-Action-Detection
공식 코드VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://github.com/MIT-HAN-LAB/temporal-shift-module
공식 코드TSM: Temporal Shift Module for Efficient Video Understanding
https://github.com/MadryLab/cifar10_challenge
공식 코드Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/MadryLab/mnist_challenge
공식 코드Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/MenghaoGuo/Awesome-Vision-Attentions
공식 코드https://github.com/MertCokelek/SalViT360
공식 코드Spherical Vision Transformer for 360-degree Video Saliency Prediction
https://github.com/MichiganCOG/ViP
공식 코드https://github.com/MichiganNLP/video-fill-in-the-blank
공식 코드FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
https://github.com/Nathan-Li123/SMOTer
공식 코드https://github.com/Netflix/vmaf
공식 코드SpatioTemporal Feature Integration and Model Fusion for Full Reference Video Quality Assessment
https://github.com/OpenGVLab/UniFormerV2
공식 코드UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
https://github.com/ParitoshParmar/Fitness-AQA
공식 코드Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
https://github.com/ParitoshParmar/Win-Fail-Action-Recognition
공식 코드https://github.com/Pilhyeon/BAM-DETR
공식 코드BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
https://github.com/PolyU-ChenLab/ETBench
공식 코드E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
https://github.com/Qualcomm-AI-research/FrameExit
공식 코드FrameExit: Conditional Early Exiting for Efficient Video Recognition
https://github.com/QualityAssessment/DOVER
공식 코드https://github.com/QualityAssessment/DisCoVQA
공식 코드DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment
https://github.com/QualityAssessment/FAST-VQA-and-FasterVQA
공식 코드Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
https://github.com/Richard-61/FineAction
공식 코드FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
https://github.com/Roc-Ng/XDVioDet
공식 코드Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision
https://github.com/SaMMyCHoo/Light-VQA-plus
공식 코드Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance
https://github.com/Sense-X/X-Temporal
공식 코드https://github.com/Siyu-C/ACAR-Net
공식 코드Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
https://github.com/SwinTransformer/Video-Swin-Transformer
공식 코드https://github.com/THUDM/LVBench
공식 코드https://github.com/Taniya-Das/video_annotation
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.