https://github.com/koshian2/OctConv-TFKeras
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
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/kylemin/S3D
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
https://github.com/l0stpenguin/DenseDepthResNet
High Quality Monocular Depth Estimation via Transfer Learning
https://github.com/l5shi/OCTAVE-CONVOLUTION
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/lamia482/octconv-pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/leftthomas/r2plus1d-c3d
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/lemon-liley/isabella
High Quality Monocular Depth Estimation via Transfer Learning
https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/beit
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/swin_transformer_v2
https://github.com/liu824/representation-flow-for-action-recognition-paddlepaddle
https://github.com/lucidrains/CoCa-pytorch
CoCa: Contrastive Captioners are Image-Text Foundation Models
https://github.com/lucidrains/STAM-pytorch
https://github.com/lucidrains/TimeSformer-pytorch
Is Space-Time Attention All You Need for Video Understanding?
https://github.com/lucidrains/flash-cosine-sim-attention
https://github.com/lucidrains/uniformer-pytorch
https://github.com/luciferbobo/dae-aqa
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
https://github.com/lukashedegaard/continual-skeletons
https://github.com/lxtGH/OctaveConv_pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/lyqcom/aaic_swintransformerv2
https://github.com/m-bain/video-transformers
Is Space-Time Attention All You Need for Video Understanding?
https://github.com/mHealthBuet/SegCodeNet
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/markliou/OctConv
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/matsuren/OctaveConv.pytorch
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
https://github.com/matyasbohacek/spoter
https://github.com/mcgridles/LENS
Two-Stream Convolutional Networks for Action Recognition in Videos
https://github.com/md-mohaiminul/objectstatechange
Is Space-Time Attention All You Need for Video Understanding?
https://github.com/metalbubble/TRN-pytorch
https://github.com/microsoft/computervision-recipes
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/microsoft/unicl
https://github.com/mil-tokyo/FTGAN
Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture
https://github.com/mindspore-ai/models/blob/master/research/cv/glore_res
https://github.com/mindspore-ai/models/blob/master/research/cv/glore_res200
https://github.com/mindspore-ai/models/tree/master/research/cv/ecolite
ECO: Efficient Convolutional Network for Online Video Understanding
https://github.com/mindspore-ai/models/tree/master/research/cv/r2plus1d
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/mindspore-ai/models/tree/master/research/cv/tsm
TSM: Temporal Shift Module for Efficient Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.