https://github.com/alibaba-mmai-research/pytorch-video-understanding
공식 코드TAda! Temporally-Adaptive Convolutions for Video Understanding
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/aljosaosep/4DGVT
공식 코드https://github.com/amd-aig-aima/amd-hummingbird-t2v
공식 코드https://github.com/amir-aghdam/ActAlign
공식 코드ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
https://github.com/amshaker/mobile-videogpt
공식 코드Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model
https://github.com/andy-cheng/tempura
공식 코드TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
https://github.com/antoine77340/LOUPE
공식 코드Learnable pooling with Context Gating for video classification
https://github.com/antoine77340/Youtube-8M-WILLOW
공식 코드Learnable pooling with Context Gating for video classification
https://github.com/aofrancani/tsformer-vo
공식 코드Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach
https://github.com/apple/ml-cvnets
공식 코드https://github.com/apple/ml-slowfast-llava
공식 코드SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
https://github.com/appletea233/temporal-r1
공식 코드Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
https://github.com/art-jang/sign-to-subtitle
공식 코드Deep Understanding of Sign Language for Sign to Subtitle Alignment
https://github.com/arunos728/SELFY
공식 코드Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
https://github.com/asrafulashiq/wsad
공식 코드Weakly Supervised Temporal Action Localization Using Deep Metric Learning
https://github.com/atelili/2bivqa
공식 코드2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
https://github.com/atlas-eccv22/awesome-temporal-action-segmentation
공식 코드Temporal Action Segmentation: An Analysis of Modern Techniques
https://github.com/avinabsaha/hidro-vqa
공식 코드HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment
https://github.com/baaivision/vid2vid-zero
공식 코드Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
https://github.com/baidu-research/vidpress-sports
공식 코드https://github.com/baidu/Youtube-8M
공식 코드Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding
https://github.com/bcmi/causal-vidqa
공식 코드https://github.com/becomebright/groundvqa
공식 코드https://github.com/benchcouncil/aigcbench
공식 코드AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI
https://github.com/bespontaneous/mca-pytorch
공식 코드Don't Judge by the Look: Towards Motion Coherent Video Representation
https://github.com/biomedia-mbzuai/echocotr
공식 코드EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography
https://github.com/boheumd/MA-LMM
공식 코드MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
https://github.com/boliu61/youtube-8m
공식 코드Constrained-size Tensorflow Models for YouTube-8M Video Understanding Challenge
https://github.com/bpiyush/TestOfTime
공식 코드Test of Time: Instilling Video-Language Models with a Sense of Time
https://github.com/brandonman123/videocad
공식 코드https://github.com/brown-palm/Vamos
공식 코드https://github.com/bryant1410/fitclip
공식 코드FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
https://github.com/bryant1410/tclip
공식 코드FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
https://github.com/bryanyzhu/Hidden-Two-Stream
공식 코드Exploring Temporal Information for Improved Video Understanding
https://github.com/buxiangzhiren/vd-it
공식 코드Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
https://github.com/bytedance/Shot2Story
공식 코드Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.