Papers with Code 아카이브
Weakly Supervised Action Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 9
- 보존된 평가 기록
- 107
In this task, the training data consists of videos with a list of activities in them without any temporal boundary annotations. However, while testing, given a video, the algorithm should recognize the activities in the video and also provide the start and end time.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/goddoe/hide-and-seek
https://github.com/harlanhong/MM2021-CO2-Net
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
https://github.com/jayChung0302/videomix
VideoMix: Rethinking Data Augmentation for Video Classification
https://github.com/ldjlammers/Hide-and-Seek-CS4240
https://github.com/lizhilin-ustc/AAAI2023-AICL
https://github.com/lizhilin-ustc/AFPS
https://github.com/lizhilin-ustc/SAL
https://github.com/nazmul-karim170/NFT-Augmented-Backdoor-Purification
VideoMix: Rethinking Data Augmentation for Video Classification
https://github.com/xiaojuntang22/iccv2023-ddgnet
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
https://github.com/zhengshou/AutoLoc
UntrimmedNets for Weakly Supervised Action Recognition and Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.