Work

DSTA: Reinforcing Vision-Language Understanding for Scene-Text VQA With Dual-Stream Training Approach

Year: 2024

Type: article

Source: IEEE Signal Processing Letters

DOI: 10.1109/lsp.2024.3486104

Authors: Yingtao Tan, Yingying Chen, Jinqiao Wang

Institutions: Chinese Academy of Sciences, Institute of Automation

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: Chinese Academy of Sciences

OpenAlex ID: W4403721424

FWCI:

Cites: 35

Cited by:

Related to: 10