David Wan, Jaemin Cho 0001, Elias Stengel-Eskin, Mohit Bansal. Contrastive Region Guidance: Improving Grounding in Vision-Language Models Without Training. In Ales Leonardis, Elisa Ricci 0001, Stefan Roth 0001, Olga Russakovsky, Torsten Sattler, Gül Varol, editors, Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXXIX. Volume 15137 of Lecture Notes in Computer Science, pages 198-215, Springer, 2024. [doi]
@inproceedings{WanCSB24,
title = {Contrastive Region Guidance: Improving Grounding in Vision-Language Models Without Training},
author = {David Wan and Jaemin Cho 0001 and Elias Stengel-Eskin and Mohit Bansal},
year = {2024},
doi = {10.1007/978-3-031-72986-7_12},
url = {https://doi.org/10.1007/978-3-031-72986-7_12},
researchr = {https://researchr.org/publication/WanCSB24},
cites = {0},
citedby = {0},
pages = {198-215},
booktitle = {Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part LXXIX},
editor = {Ales Leonardis and Elisa Ricci 0001 and Stefan Roth 0001 and Olga Russakovsky and Torsten Sattler and Gül Varol},
volume = {15137},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-031-72986-7},
}