Positive-augmented contrastive learning for image and video captioning evaluation

S Sarto, M Barraco, M Cornia… - Proceedings of the …, 2023 - openaccess.thecvf.com
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …
被引用次数：39 相关文章

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi, R Cucchiara - cvpr.thecvf.com
Presentazione standard di PowerPoint Page 1 {name.surname}@unimore.it University of
Modena and Reggio Emilia, Italy Sara Sarto, Manuele Barraco, Marcella Cornia, Lorenzo …

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi… - arXiv e …, 2023 - ui.adsabs.harvard.edu
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi… - 2023 IEEE/CVF …, 2023 - ieeexplore.ieee.org
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi… - 2023 IEEE/CVF …, 2023 - computer.org
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi… - arXiv preprint arXiv …, 2023 - arxiv.org
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …

Positive-Augmented Constrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi… - Proceedings of the …, 2023 - iris.unimore.it
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language models. In …
[PDF] researchgate.net

[PDF][PDF] Positive-Augmented Constrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi, R Cucchiara - researchgate.net
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …
[PDF] unimore.it

[PDF][PDF] Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

S Sarto, M Barraco, M Cornia, L Baraldi, R Cucchiara - iris.unimore.it
The CLIP model has been recently proven to be very effective for a variety of cross-modal
tasks, including the evaluation of captions generated from vision-and-language …