Qiang Su, Zhixin Li. Multilayer Vision and Language Augmented Transformer for Image Captioning. In Fenrong Liu, Arun Anand Sadanandan, Duc Nghia Pham, Petrus Mursanto, Dickson Lukose, editors, PRICAI 2023: Trends in Artificial Intelligence - 20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023, Jakarta, Indonesia, November 15-19, 2023, Proceedings, Part II. Volume 14326 of Lecture Notes in Computer Science, pages 210-222, Springer, 2023. [doi]
@inproceedings{SuL23-6,
title = {Multilayer Vision and Language Augmented Transformer for Image Captioning},
author = {Qiang Su and Zhixin Li},
year = {2023},
doi = {10.1007/978-981-99-7022-3_19},
url = {https://doi.org/10.1007/978-981-99-7022-3_19},
researchr = {https://researchr.org/publication/SuL23-6},
cites = {0},
citedby = {0},
pages = {210-222},
booktitle = {PRICAI 2023: Trends in Artificial Intelligence - 20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023, Jakarta, Indonesia, November 15-19, 2023, Proceedings, Part II},
editor = {Fenrong Liu and Arun Anand Sadanandan and Duc Nghia Pham and Petrus Mursanto and Dickson Lukose},
volume = {14326},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-981-99-7022-3},
}