Contrastive Pre-training with Multi-level Alignment for Grounded Multimodal Named Entity Recognition.

@inproceedings{bao-2024-contrastive, author = {Xigang Bao and Mengyuan Tian and Luyao Wang and Zhiyuan Zha and Biao Qin}, 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 = {{Contrastive Pre-training with Multi-level Alignment for Grounded Multimodal Named Entity Recognition}}, booktitle = {{Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, Phuket, Thailand, June 10-14, 2024}}, pages = {795--803}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3652583.3658011}, doi = {https://doi.org/10.1145/3652583.3658011} }