https://github.com/huggingface/pytorch-image-models
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Papers with Code 아카이브
Action Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 28
- 보존된 평가 기록
- 444
Image source: The Kinetics Human Action Video Dataset
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/huggingface/transformers
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://github.com/huyz1117/Non_Local_Net_TensorFlow
https://github.com/iacolippo/octconv-pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/iamhoushiyou/tsn
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
https://github.com/iduta/pyconvsegnet
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
https://github.com/impiga/plain-detr
https://github.com/innat/UniFormerV2
https://github.com/innat/VideoMAE
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://github.com/innat/VideoSwin
https://github.com/isaaccorley/hydro-foundation-model
https://github.com/ivanwilliammd/I3DR-Net-Transfer-Learning
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/japicazosuni/TFG_HAR
https://github.com/jbutepage/semi_supervised_variational_recurrent_neural_network
A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling
https://github.com/jeffreyhuang1/two-stream-action-recognition
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
https://github.com/jeffreyyihuang/two-stream-action-recognition
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
https://github.com/jerryljq/ActionRecognition
Two-Stream Convolutional Networks for Action Recognition in Videos
https://github.com/jerrywn121/TianChi_AIEarth
Is Space-Time Attention All You Need for Video Understanding?
https://github.com/jiajunhua/facebookresearch-Detectron
https://github.com/jihun-kr/SlowFast
https://github.com/jojo13572001/DenseDepth
High Quality Monocular Depth Estimation via Transfer Learning
https://github.com/jordiae/DeepLearning-MAI
https://github.com/jpviguerasguillen/feedback-non-local-attention-fnla
https://github.com/jpviguerasguillen/feedback-non-local-attention_fNLA
https://github.com/juenkhaw/action_recognition_project
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/juenkhaw/action_recognition_project1
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/junweiliang/multitrain
https://github.com/karatuno/Action-Recognition
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/keras-team/keras-io/blob/master/examples/vision/token_learner.py
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
https://github.com/keras-team/keras-io/blob/master/examples/vision/vivit.py
https://github.com/khu-vll/cast
CAST: Cross-Attention in Space and Time for Video Action Recognition
https://github.com/kietngt00/hmdb51-recognition
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/kingcong/ecolite
ECO: Efficient Convolutional Network for Online Video Understanding
https://github.com/kingcong/r2plus1d
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/kk1694/octaveconv-pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/kkahatapitiya/X3D-Multigrid
X3D: Expanding Architectures for Efficient Video Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.