MSViT: Training Multiscale Vision Transformers for Image Retrieval

Xue Li, Jiong Yu, Shaochen Jiang, Hongchun Lu, Ziyang Li. MSViT: Training Multiscale Vision Transformers for Image Retrieval. IEEE Transactions on Multimedia, 26:2809-2823, 2024. [doi]

Authors

Xue Li

This author has not been identified. Look up 'Xue Li' in Google

Jiong Yu

This author has not been identified. Look up 'Jiong Yu' in Google

Shaochen Jiang

This author has not been identified. Look up 'Shaochen Jiang' in Google

Hongchun Lu

This author has not been identified. Look up 'Hongchun Lu' in Google

Ziyang Li

This author has not been identified. Look up 'Ziyang Li' in Google