Vision-Text Cross-Modal Fusion for Accurate Video Captioning

Vision-Text Cross-Modal Fusion for Accurate Video Captioning

In this paper, we introduce a novel end-to-end multimodal video captioning framework based on cross-modal fusion of visual and textual data. The proposed approach integrates a modality-attention module, which captures the visual-textual inter-model relationships using cross-correlation. Further, we...

Full description

Bibliographic Details
Main Authors: Kaouther Ouenniche, Ruxandra Tapu, Titus Zaharia
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Multimodal video captioning
multimodal learning
cross correlation
transformers
contrastive learning
Online Access:https://ieeexplore.ieee.org/document/10283847/

Internet

https://ieeexplore.ieee.org/document/10283847/

Similar Items