https://github.com/junjie1003/DL-Fairness-Study
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 4
- 보존된 평가 기록
- 10
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/justld/3D-ResNets_paddle
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
https://github.com/jwwoody/mlb-deeplearning
https://github.com/jwwoody/mlb-youtube
https://github.com/jy0205/Pyramid-Flow
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
https://github.com/k-muhibul/Pattern_hand-gesture
Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks
https://github.com/kailashhambarde/DetReIDX
DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition
https://github.com/kaiqiangh/extracting-video-features-ResNeXt
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
https://github.com/kairess/efficientnet_example
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/karatuno/Action-Recognition
A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/kchengiva/Shift-GCN
https://github.com/kdha0727/lung-opacity-and-covid-chest-x-ray-detection
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/ken724049/action-recognition
PoseTrack: A Benchmark for Human Pose Estimation and Tracking
https://github.com/kenshohara/video-classification-3d-cnn-pytorch
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
https://github.com/kenziyuliu/DGNN-PyTorch
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/kiharalab/gnn_pocket
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/kimhaggie/YBIGTA_haggie
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/kingcong/stnet
StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
https://github.com/kiyoon/pyvideoai
An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
https://github.com/kjm1559/ADAE_LSTM_Autoencoder
https://github.com/kkahatapitiya/X3D-Multigrid
https://github.com/klemens-floege/oneprot
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/konstantinos-p/image_classification_SOTA
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/koo5/notes2
https://github.com/kshah33/viewcon
https://github.com/kylemin/S3D
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
https://github.com/kynk94/TF2-Image-Generation
https://github.com/kynkaat/role-of-imagenet-classes-in-fid
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/l13025816/PGCN
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
https://github.com/lRomul/ball-action-spotting
https://github.com/lab-midas/lapnet
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.