@inbook{b79a228e26cb496a927b540ace3b045c,
title = "Learning Modality-Invariant Features by Cross-Modality Adversarial Network for Visual Question Answering",
abstract = "Visual Question Answering (VQA) is a typical multimodal task with significant development prospect on web application. In order to answer the question based on the corresponding image, a VQA model needs to utilize the information from different modality efficiently. Although the multimodal fusion methods such as attention mechanism make significant contribution for VQA, these methods try to co-learn the multimodal features directly, ignoring the large gap between different modality and thus poor aligning the semantic. In this paper, we propose a Cross-Modality Adversarial Network (CMAN) to address this limitation. Our method combines cross-modality adversarial learning with modality-invariant attention learning aiming to learn the modality-invariant features for better semantic alignment and higher answer prediction accuracy. The accuracy of model achieves 70.81% on the test-dev split on the VQA-v2 dataset. Our results also show that the model narrows the gap between different modalities effectively and improves the alignment performance of the multimodal information.",
keywords = "Domain adaptation, Modality-invariant co-learning, Visual question answering",
author = "Ze Fu and Changmeng Zheng and Yi Cai and Qing Li and Tao Wang",
note = "Funding Information: Acknowledgments. This work was supported by National Natural Science Foundation of China (No. 62076100), National Key Research and Development Program of China (Standard knowledge graph for epidemic prevention and production recovering intelligent service platform and its applications), the Fundamental Research Funds for the Central Universities, SCUT (No. D2201300, D2210010), the Science and Technology Programs of Guangzhou (201902010046), the Science and Technology Planning Project of Guangdong Province (No. 2020B0101100002). Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 5th International Joint Conference on Asia-Pacific Web and Web-Age Information Management, APWeb-WAIM 2021 ; Conference date: 23-08-2021 Through 25-08-2021",
year = "2021",
doi = "10.1007/978-3-030-85896-4_25",
language = "English",
isbn = "9783030858957",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "316--331",
editor = "U, {Leong Hou} and Marc Spaniol and Yasushi Sakurai and Junying Chen",
booktitle = "Web and Big Data - 5th International Joint Conference, APWeb-WAIM 2021, Proceedings",
address = "Germany",
}