MCDINO: Self-supervised learning of masks based on combination of multi-path channel attention and local feature weighting.

Yunxue Shao|Zhiyang Wang|Lingfeng Wang


Anthology ID:DBLP:journals/ijmir/ShaoWW25
Year:2025
Venue:International Journal of Multimedia Information Retrieval (IJMIR)
Pages:25
URL:https://doi.org/10.1007/S13735-025-00371-X
DOI:https://doi.org/10.1007/S13735-025-00371-X
DBLP:journals/ijmir/ShaoWW25
BibTeX:
@article{shao-2025-mcdino, author = {Yunxue Shao and Zhiyang Wang and Lingfeng Wang}, title = {{MCDINO: Self-supervised learning of masks based on combination of multi-path channel attention and local feature weighting}}, journal = {International Journal of Multimedia Information Retrieval (IJMIR)}, volume = {14}, number = {3}, pages = {25}, year = {2025}, url = {https://doi.org/10.1007/S13735-025-00371-X}, doi = {https://doi.org/10.1007/S13735-025-00371-X} }