Work

Hierarchical multimodal transformers for Multipage DocVQA

Year: 2023

Type: article

Source: Pattern Recognition

DOI: 10.1016/j.patcog.2023.109834

Authors: Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny

Institutions: Universitat Autònoma de Barcelona, Computer Vision Center

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4385237494

FWCI: 5.687

Cites: 28

Cited by: 67

Related to: 10