Soyeon Caren Han, Siqu Long, Siwen Luo, Kunze Wang, Josiah Poon. VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks. In Donia Scott, Núria Bel, Chengqing Zong, editors, Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020. pages 3107-3117, International Committee on Computational Linguistics, 2020. [doi]
@inproceedings{HanLLWP20, title = {VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks}, author = {Soyeon Caren Han and Siqu Long and Siwen Luo and Kunze Wang and Josiah Poon}, year = {2020}, url = {https://www.aclweb.org/anthology/2020.coling-main.277/}, researchr = {https://researchr.org/publication/HanLLWP20}, cites = {0}, citedby = {0}, pages = {3107-3117}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020}, editor = {Donia Scott and Núria Bel and Chengqing Zong}, publisher = {International Committee on Computational Linguistics}, isbn = {978-1-952148-27-9}, }