Dual-level collaborative transformer for image captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang… - Proceedings of the …, 2021 - ojs.aaai.org
Descriptive region features extracted by object detection networks have played an important
role in the recent advancements of image captioning. However, they are still criticized for the …

[PDF][PDF] Dual-Level Collaborative Transformer for Image Captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang, CW Lin, R Ji - 2021 - scholar.archive.org
Descriptive region features extracted by object detection networks have played an important
role in the recent advancements of image captioning. However, they are still criticized for the …

[PDF][PDF] Dual-Level Collaborative Transformer for Image Captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang, CW Lin, R Ji - 2021 - cdn.aaai.org
Descriptive region features extracted by object detection networks have played an important
role in the recent advancements of image captioning. However, they are still criticized for the …

Dual-Level Collaborative Transformer for Image Captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang… - arXiv preprint arXiv …, 2021 - arxiv.org
Descriptive region features extracted by object detection networks have played an important
role in the recent advancements of image captioning. However, they are still criticized for the …

Dual-Level Collaborative Transformer for Image Captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang… - arXiv e …, 2021 - ui.adsabs.harvard.edu
Descriptive region features extracted by object detection networks have played an important
role in the recent advancements of image captioning. However, they are still criticized for the …

Dual-level Collaborative Transformer for Image Captioning

Y Luo, J Ji, X Sun, L Cao, Y Wu, F Huang… - Proceedings of the …, 2021 - cir.nii.ac.jp
抄録< jats: p> Descriptive region features extracted by object detection networks have
played an important role in the recent advancements of image captioning. However, they are …