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/ruiyan1995/Interactive_Fusion_for_CAR
공식 코드Interactive Fusion of Multi-level Features for Compositional Activity Recognition
https://github.com/ruizhuo-xu/skeleton2vec
공식 코드https://github.com/rupertluo/valley
공식 코드Valley: Video Assistant with Large Language model Enhanced abilitY
https://github.com/ruthless-man/awesome-learn-from-model
공식 코드https://github.com/rvl-lab-utoronto/video_similarity_search
공식 코드SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
https://github.com/rwightman/pytorch-image-models
공식 코드EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
https://github.com/rymarinelli/leaking_lora
공식 코드Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
https://github.com/s-shamil/HandFormer
공식 코드https://github.com/sadafgulshad1/Hierarchical-ProtoPNet
공식 코드https://github.com/sadeghrahmanib/dear
공식 코드https://github.com/safwennaimi/representation-learning-for-skeleton-action-recognition-with-convolutional-transformers-and-byol
공식 코드https://github.com/sagarverma/EgoActionRecognition
공식 코드Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
https://github.com/saidwivedi/POCO
공식 코드https://github.com/sallymmx/actionclip
공식 코드https://github.com/samyadeepbasu/locogen
공식 코드On Mechanistic Knowledge Localization in Text-to-Image Generative Models
https://github.com/samyak0210/ViNet
공식 코드ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction
https://github.com/sandy-zeng/pcl
공식 코드Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
https://github.com/sangminwoo/actionmae
공식 코드Towards Good Practices for Missing Modality Robust Action Recognition
https://github.com/sankadivandya/ks-kss-dataset
공식 코드https://github.com/sanketsans/ganov2
공식 코드Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
https://github.com/sarinda251/cdfsl-v
공식 코드https://github.com/sayibet/fight-detection-surv-dataset
공식 코드https://github.com/sbargal/Caffe-ExcitationBP-RNNs
공식 코드https://github.com/scalable-model-editing/gradual-catastrophic-forgetting
공식 코드Model Editing at Scale leads to Gradual and Catastrophic Forgetting
https://github.com/scalable-model-editing/knowledge-editing-regularization
공식 코드https://github.com/scalable-model-editing/rebuilding-rome
공식 코드Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
https://github.com/scalable-model-editing/unified-model-editing
공식 코드https://github.com/scu-zjz/forensichub
공식 코드ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
https://github.com/scu-zjz/imdlbenco
공식 코드IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
https://github.com/secure-and-intelligent-systems-lab/semanticvideotransformer
공식 코드End-to-End Semantic Video Transformer for Zero-Shot Action Recognition
https://github.com/seleucia/goca
공식 코드GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
https://github.com/sengopal/cv-activity-classification
공식 코드Multi class activity classification in videos using Motion History Image generation
https://github.com/seonokkim/3dyoga90
공식 코드3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding
https://github.com/sfadingz/tse_gcn
공식 코드Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
https://github.com/shahroudy/NTURGB-D
공식 코드NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.