Bo Zou, Chao Yang, Chengbin Quan, Youjian Zhao. SpaceCLIP: A Vision-Language Pretraining Framework With Spatial Reconstruction On Text. In Abdulmotaleb El-Saddik, Tao Mei, Rita Cucchiara, Marco Bertini 0001, Diana Patricia Tobon Vallejo, Pradeep K. Atrey, M. Shamim Hossain, editors, Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023. pages 519-528, ACM, 2023. [doi]
@inproceedings{ZouYQZ23,
title = {SpaceCLIP: A Vision-Language Pretraining Framework With Spatial Reconstruction On Text},
author = {Bo Zou and Chao Yang and Chengbin Quan and Youjian Zhao},
year = {2023},
doi = {10.1145/3581783.3612379},
url = {https://doi.org/10.1145/3581783.3612379},
researchr = {https://researchr.org/publication/ZouYQZ23},
cites = {0},
citedby = {0},
pages = {519-528},
booktitle = {Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
editor = {Abdulmotaleb El-Saddik and Tao Mei and Rita Cucchiara and Marco Bertini 0001 and Diana Patricia Tobon Vallejo and Pradeep K. Atrey and M. Shamim Hossain},
publisher = {ACM},
}