Papers with Code 아카이브
Action Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 8
- 평가표
- 11
- 보존된 평가 기록
- 81
Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/wuryantoAji/POINTNET
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/wushidonguc/two-stream-action-recognition-keras
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
https://github.com/wwydmanski/rl_tennis
https://github.com/wzmsltw/BSN-boundary-sensitive-network
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
https://github.com/xiaoiker/GCN-NAS
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
https://github.com/xiuyu0000/new_papers_codes/tree/main/I3D
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/xiuyu0000/vision/blob/main/mindvision/ms3d/models/pointnet2cls.py
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/xiuyu0000/vision/blob/main/mindvision/msvideo/models/i3d.py
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/xlliu7/BMN-Boundary-Matching-Network
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
https://github.com/xtma/simple-pytorch-rl
https://github.com/xurui1217/pointnet.pytorch-master
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/xuyuandong/simple-ddpg
https://github.com/xyshadow/baseline_ddpg
https://github.com/y2kmz/pointnetv2
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yCobanoglu/infinite-width-gnns
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/yangjun1994/CAGCN
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/yangyucheng000/pointnet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yangyucheng000/unipose-mindspore
UniPose: Unified Human Pose Estimation in Single Images and Videos
https://github.com/yanhuchen/quantum-graph-convolutional-network
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/yanx27/Pointnet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yanxp/PointNet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yaohungt/GSTEG_CVPR_2019
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/ydtydr/hyla
https://github.com/ydzhang-stormstout/HAT
https://github.com/yevgm/deepadv3d
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yfsong0709/ResGCNv1
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
https://github.com/ykrmm/sota_gnn
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/youngjun0627/movie-rating
https://github.com/ytng001/sensemaking
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/yukezhu/tensorflow-reinforce
https://github.com/yurakuratov/hidden_capacity
https://github.com/yururyuru00/GAT_pyG
https://github.com/yusme/DDPG
https://github.com/yz-cnsdqz/TemporalActionParsing-FineGrained
Temporal Convolutional Networks for Action Segmentation and Detection
https://github.com/zcxu-eric/Ego4d_TalkNet_ASD
Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.