Papers with Code 아카이브
Unsupervised Video Object Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 6
- 보존된 평가 기록
- 76
The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/2023-MindSpore-4/Code5/tree/main/D2Co
https://github.com/Kinpzz/RCRNet-Pytorch
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
https://github.com/OliverRensu/RTNet
https://github.com/ahasan-haque/TMO-RAFT
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
https://github.com/antonilo/unsupervised_detection
Unsupervised Moving Object Detection via Contextual Information Separation
https://github.com/bo-miao/MAMP
https://github.com/griffbr/VOSVS
https://github.com/idilesenzulfikar/UNOVOST
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
https://github.com/isyangshu/amc-net
https://github.com/kini5gowda/ALBA-RL-for-VOS
https://github.com/mfaisal59/EpipolarScore
EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
https://github.com/mfaisal59/RBSF
EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
https://github.com/pacifinapacific/PixelFlow
Joint-task Self-supervised Learning for Temporal Correspondence
https://github.com/vidit98/FrameSelect
https://github.com/vik-goel/MOREL
Unsupervised Video Object Segmentation for Deep Reinforcement Learning
https://github.com/wenguanwang/AGS
https://github.com/xiaolonw/TimeCycle
https://github.com/xilin1991/ClusterNet
Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.