VEC-MNER: Hybrid Transformer with Visual-Enhanced Cross-Modal Multi-level Interaction for Multimodal NER.

@inproceedings{wei-2024-vecmner, author = {Pengfei Wei and Hongjun Ouyang and Qintai Hu and Bi Zeng and Guang Feng and Qingpeng Wen}, 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 = {{VEC-MNER: Hybrid Transformer with Visual-Enhanced Cross-Modal Multi-level Interaction for Multimodal NER}}, booktitle = {{Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, Phuket, Thailand, June 10-14, 2024}}, pages = {469--477}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3652583.3658097}, doi = {https://doi.org/10.1145/3652583.3658097} }