Efficiently Gluing Pre-Trained Language and Vision Models for Image Captioning.
Peipei Song|Yuanen Zhou|Xun Yang|Daqing Liu|Zhenzhen Hu|Depeng Wang|Meng Wang
| Anthology ID: | DBLP:journals/tist/SongZYLHWW24 |
|---|---|
| Year: | 2024 |
| Venue: | ACM Transactions on Intelligent Systems and Technology (TIST) |
| Pages: | 115:1-115:16 |
| URL: | https://doi.org/10.1145/3682067 |
| DOI: | https://doi.org/10.1145/3682067 |
| DBLP: | journals/tist/SongZYLHWW24 |
| BibTeX: |
@article{song-2024-efficiently,
author = {Peipei Song and
Yuanen Zhou and
Xun Yang and
Daqing Liu and
Zhenzhen Hu and
Depeng Wang and
Meng Wang},
title = {{Efficiently Gluing Pre-Trained Language and Vision Models for Image Captioning}},
journal = {ACM Transactions on Intelligent Systems and Technology (TIST)},
volume = {15},
number = {6},
pages = {115:1--115:16},
year = {2024},
url = {https://doi.org/10.1145/3682067},
doi = {https://doi.org/10.1145/3682067}
}