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/gordicaleksa/pytorch-GAT
https://github.com/gouthamvgk/coreml_conversion_hub
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/gpspelle/Convert_channel
https://github.com/gregorbachmann/scaling_mlps
https://github.com/gsig/charades-algorithms
https://github.com/guide2157/ChulaXrayClassifier
What Makes Training Multi-Modal Classification Networks Hard?
https://github.com/guiggh/hand_pose_action
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
https://github.com/guilk/diva
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
https://github.com/gulvarol/ltc
https://github.com/gulvarol/surreact
Synthetic Humans for Action Recognition from Unseen Viewpoints
https://github.com/guoxih/busy-quiet-net
https://github.com/haamoon/mmtm
https://github.com/halimasoulb/human-pose-estimation-3d-lidar
https://github.com/halixness/generative_timesformer_pytorch
Is Space-Time Attention All You Need for Video Understanding?
https://github.com/hamed-ahangari/Separation-Index-of-convolutional-layers-in-EfficientNet-B0
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/handasontam/GAT-with-edgewise-attention
https://github.com/handhand123/prsa-net
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
https://github.com/hangzhaomit/HACS-dataset
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
https://github.com/haofanwang/video-swin-transformer-pytorch
https://github.com/haomo-ai/superfusion
https://github.com/happen2me/cross-gnn
https://github.com/happygds/two_level
https://github.com/hariharannatesh/Action-Recognition-using-Pytorch-Geometric
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
https://github.com/hassony2/kinetics_i3d_pytorch
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/hayatkhan8660-maker/DVFL-Net
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
https://github.com/hazdzz/ChebyNet
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
https://github.com/hazdzz/GCN
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/hazdzz/SGC
https://github.com/hehefan/P4Transformer
https://github.com/hehefan/PSTNet2
https://github.com/helloxy96/CS5242_Project2020
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/hg1722/fashionista
https://github.com/hhe-distance/AIF-CNN
https://github.com/hi-archers/stableke
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.