https://github.com/MTLab/MorphMLP
공식 코드MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
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/Maddy12/ActionRecognitionRobustnessEval
공식 코드Large-scale Robustness Analysis of Video Action Recognition Models
https://github.com/Maghoumi/DeepGRU
공식 코드https://github.com/Mathux/ACTOR
공식 코드Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
https://github.com/MehwishG/T3D-CNN
공식 코드Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework
https://github.com/MichiganCOG/Surgical_Hands_RELEASE
공식 코드Temporally Guided Articulated Hand Pose Tracking in Surgical Videos
https://github.com/Mikexu007/AS-CAL
공식 코드https://github.com/Mikexu007/AS_CAL
공식 코드https://github.com/Mikexu007/PCRP
공식 코드Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
https://github.com/MohsenFayyaz89/T3D
공식 코드Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
https://github.com/NIEQiang001/unsupervised-human-pose
공식 코드Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement
https://github.com/Nachwa/object_states
공식 코드https://github.com/Necolizer/CHASE
공식 코드CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
https://github.com/Necolizer/ISTA-Net
공식 코드https://github.com/NyleSiddiqui/MultiView_Actions
공식 코드DVANet: Disentangling View and Action Features for Multi-View Action Recognition
https://github.com/OpenGVLab/VideoMAEv2
공식 코드VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
https://github.com/OrdinaryQin/TCA-GCN
공식 코드Skeleton-based Action Recognition via Temporal-Channel Aggregation
https://github.com/PIC4SeRCentre/MPOSE2021_Dataset
공식 코드Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/video/models/bmn
공식 코드BMN: Boundary-Matching Network for Temporal Action Proposal Generation
https://github.com/PanasonicConnect/ego4d_lta_ens_srw_seqdep_verb_noun_cooc
공식 코드Technical Report for Ego4D Long Term Action Anticipation Challenge 2023
https://github.com/ParitoshParmar/Fitness-AQA
공식 코드Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
https://github.com/ParitoshParmar/HalluciNet
공식 코드HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN
https://github.com/ParitoshParmar/MTL-AQA
공식 코드What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
https://github.com/ParitoshParmar/Win-Fail-Action-Recognition
공식 코드https://github.com/PeihaoChen/RSPNet
공식 코드RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
https://github.com/PeizhuoLi/neural-blend-shapes
공식 코드https://github.com/PetarV-/GAT
공식 코드https://github.com/PinzhengWang322/Reveal_Attention_Drift
공식 코드Revealing and Mitigating Over-Attention in Knowledge Editing
https://github.com/R00Kie-Liu/Sampler
공식 코드Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition
https://github.com/R00Kie-Liu/TA2N
공식 코드TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
https://github.com/RS2002/KNN-MMD
공식 코드KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
https://github.com/SJTUHaiyangYu/BackdoorMBTI
공식 코드BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
https://github.com/SUTDCV/Animal-Kingdom
공식 코드Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding
https://github.com/SUTDCV/UAV-Human
공식 코드UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
https://github.com/Sausage-SONG/Few-shot-action-recognition
공식 코드https://github.com/SeanChen0220/PoseFall
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.