Vman: visual-modified attention network for multimodal paradigms Vman: visual-modified attention network for multimodal paradigms

• Published in: The Visual computer Vol. 41; no. 4; pp. 2737 - 2754
• Main Authors: Song, Xiaoyu, Han, Dezhi, Chen, Chongqing, Shen, Xiang, Wu, Huafeng
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2025; Springer Nature B.V
• Subjects: Artificial Intelligence; Attention; Computer Graphics; Computer Science; Design; Image Processing and Computer Vision; Language; Localization; Modelling; Natural language; Proposals; Sensors; Dependency modeling; Transformer; Visual question answering (VQA); Vision-language task (VLT); Visual grounding (VG)

Due to excellent dependency modeling and powerful parallel computing capabilities, Transformer has become the primary research method in vision-language tasks (VLT). However, for multimodal VLT like VQA and VG, which demand high-dependency modeling and heterogeneous modality comprehension, solving t...