Reformulating Graph Kernels for Self-Supervised Space-Time Correspondence Learning
Self-supervised space-time correspondence learning utilizing unlabeled videos holds great potential in computer vision. Most existing methods rely on contrastive learning with mining negative samples or adapting reconstruction from the image domain, which requires dense affinity across multiple fram...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 03., Seite 6543-6557
|
1. Verfasser: |
Qin, Zheyun
(VerfasserIn) |
Weitere Verfasser: |
Lu, Xiankai,
Liu, Dongfang,
Nie, Xiushan,
Yin, Yilong,
Shen, Jianbing,
Loui, Alexander C |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
Schlagworte: | Journal Article |