Pyramidal Cross-Modal Transformer with Sustained Visual Guidance for Multi-Label Image Classification.

@inproceedings{li-2024-pyramidal, author = {Zhuohua Li and Ruyun Wang and Fuqing Zhu and Jizhong Han and Songlin Hu}, editor = {Cathal Gurrin and Rachada Kongkachandra and Klaus Sch\"{o}ffmann and Duc-Tien Dang-Nguyen and Luca Rossetto and Shin'ichi Satoh and Liting Zhou}, title = {{Pyramidal Cross-Modal Transformer with Sustained Visual Guidance for Multi-Label Image Classification}}, booktitle = {{Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, Phuket, Thailand, June 10-14, 2024}}, pages = {740--748}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3652583.3658005}, doi = {https://doi.org/10.1145/3652583.3658005} }