Work

Learning Rich Image Region Representation for Visual Question Answering

Year: 2019

Type: preprint

Abstract: We propose to boost VQA by leveraging more powerful feature extractors by improving the representation ability of both visual and text features and the ensemble of models. For visual feature, some detection techniques are used to improve the detector. For text feature, we adopt BERT as the language model and find that it can significantly improve VQA performance. Our solution won the second place in the VQA Challenge 2019.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1910.13077

Authors: Liu, Bei, Huang, Zhicheng, Zeng, Zhaoyang, Chen, Zheyu, Fu, Jianlong

Institution: Microsoft Research Asia (China)

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2982584731

Cites: 14

Cited by: 7

Related to: 10