Papers with Code 아카이브
Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Sha-Lab/CMHSE
공식 코드https://github.com/ShoufaChen/AdaptFormer
공식 코드AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
https://github.com/Shunli-Wang/TSA-Net
공식 코드TSA-Net: Tube Self-Attention Network for Action Quality Assessment
https://github.com/SimilarityGuidedSampling/Similarity-Guided-Sampling
공식 코드https://github.com/Singularity42/cap2vid
공식 코드https://github.com/Siyu-C/ACAR-Net
공식 코드Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
https://github.com/Soumyabrata2003/Simba
공식 코드Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos
https://github.com/Soumyabrata2003/ViLP
공식 코드ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition
https://github.com/SunDoge/L-GCN
공식 코드Location-aware Graph Convolutional Networks for Video Question Answering
https://github.com/Sunnydreamrain/IndRNN_Theano_Lasagne
공식 코드Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
https://github.com/Sunnydreamrain/IndRNN_pytorch
공식 코드https://github.com/SwinTransformer/Video-Swin-Transformer
공식 코드https://github.com/TJU-YDragonW/TAMT
공식 코드TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
https://github.com/TaeSoo-Kim/TCNActionRecognition
공식 코드Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
https://github.com/TaikiMiyagawa/MSPRT-TANDEM
공식 코드The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
https://github.com/TencentYoutuResearch/SelfSupervisedLearning-DSM
공식 코드Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
https://github.com/TengdaHan/CoCLR
공식 코드Self-supervised Co-training for Video Representation Learning
https://github.com/TengdaHan/DPC
공식 코드https://github.com/TengdaHan/MemDPC
공식 코드Memory-augmented Dense Predictive Coding for Video Representation Learning
https://github.com/The-Martyr/OccludeNet-Dataset
공식 코드OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
https://github.com/Thinksky5124/SVTAS
공식 코드End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning
https://github.com/Tiiiger/SGC
공식 코드https://github.com/TrustedLLM/UnKE
공식 코드Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
https://github.com/Uason-Chen/CTR-GCN
공식 코드Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
https://github.com/UgurDemir/Tiny-VIRAT
공식 코드https://github.com/V-Sense/ACTION-Net
공식 코드https://github.com/VIPriors/vipriors-challenges-toolkit
공식 코드VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
https://github.com/VITA-Group/PA-HMDB51
공식 코드Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
https://github.com/VITA-Group/Privacy-AdversarialLearning
공식 코드Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
https://github.com/Va6lue/BST-Badminton-Stroke-type-Transformer
공식 코드BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports
https://github.com/VisionLearningGroup/R-C3D
공식 코드R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
https://github.com/WISION-Lab/eventful-transformer
공식 코드Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers
https://github.com/Walter0807/MotionBERT
공식 코드MotionBERT: A Unified Perspective on Learning Human Motion Representations
https://github.com/WenjieDu/PyPOTS
공식 코드TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
https://github.com/XZhang00/LU-LAFNs
공식 코드Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.