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/kpeng9510/relamix
공식 코드Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
https://github.com/kpeng9510/trans4soar
공식 코드Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions
https://github.com/kracwarlock/action-recognition-visual-attention
공식 코드https://github.com/krystalan/bi_zsre
공식 코드https://github.com/kunli-cs/pcan
공식 코드Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition
https://github.com/kunyulin/xov-action
공식 코드Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition
https://github.com/kylehuang9/sefar
공식 코드https://github.com/kylemin/Gaze-Attention
공식 코드Integrating Human Gaze into Attention for Egocentric Activity Recognition
https://github.com/lambert-x/video-semisup
공식 코드Learning from Temporal Gradient for Semi-supervised Action Recognition
https://github.com/laura-wang/video-pace
공식 코드Self-supervised Video Representation Learning by Pace Prediction
https://github.com/laura-wang/video_repres_mas
공식 코드https://github.com/laura-wang/video_repres_sts
공식 코드Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
https://github.com/laurenok24/nsaqa
공식 코드Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment
https://github.com/ldarrick/PathSignatures
공식 코드https://github.com/ldkong1205/transvae
공식 코드Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
https://github.com/leaplabthu/dynamic_perceiver
공식 코드https://github.com/leesb7426/team
공식 코드Temporal Alignment-Free Video Matching for Few-shot Action Recognition
https://github.com/leexinhao/ZeroI2V
공식 코드ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
https://github.com/leiwangr/udtw
공식 코드https://github.com/leiwangr/video-ar
공식 코드https://github.com/leo-liuzy/propmend
공식 코드https://github.com/leonlha/Video-Action-Recognition-via-PSO-ConvNet-Transformer-Collaborative-Learning-with-Dynamics
공식 코드Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer
https://github.com/leonlha/pso-convnet-dynamics
공식 코드PSO-Convolutional Neural Networks with Heterogeneous Learning Rate
https://github.com/leonlha/video-action-recognition-collaborative-learning-with-dynamics-via-pso-convnet-transformer
공식 코드Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer
https://github.com/levigty/acl
공식 코드Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
https://github.com/levigty/aimclr
공식 코드https://github.com/lhc1224/OSAD_Net
공식 코드https://github.com/lihaoxin05/stillmix
공식 코드Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
https://github.com/liluxuan1997/DPP
공식 코드https://github.com/lilygeorgescu/ubnormal
공식 코드UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
https://github.com/limaosen0/AS-GCN
공식 코드Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
https://github.com/lingo-iitgn/xme
공식 코드https://github.com/linqinliang/decowa
공식 코드Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
https://github.com/lins-lab/collabedit
공식 코드CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
https://github.com/linuxsino/arr
공식 코드From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.