9th Multimodal Learning and Applications Workshop

Bridging the Granularity Gap: Object-Centric Masking for Contextual Visual Learning

Jike Zhong,

Yuxiang Lai,

Konstantinos Psounis

[pdf] [supp]

[bibtex]

@InProceedings{Zhong_2026_CVPR, author = {Zhong, Jike and Lai, Yuxiang and Psounis, Konstantinos}, title = {Bridging the Granularity Gap: Object-Centric Masking for Contextual Visual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {7596-7606} }