Adapted GooLeNet for Visual Question Answering

被引：3

作者：

Huang, Jie ^{[1
]}

Hu, Yue ^{[1
]}

Yang, Weilong ^{[1
]}

机构：

[1] Natl Univ Def Technol, Coll Syst Engn, Changsha, Hunan, Peoples R China

来源：

2018 3RD INTERNATIONAL CONFERENCE ON MECHANICAL, CONTROL AND COMPUTER ENGINEERING (ICMCCE) | 2018年

基金：

中国国家自然科学基金;

关键词：

visual question answering; Adapted GooLeNet; MUTAN;

D O I：

10.1109/ICMCCE.2018.00132

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Visual Question Answering (VQA) aims at answering a question about an image. In this work, we introduce an effective architecture --Adapted GooLeNet (AG)-- into a typical VQA method MUTAN instead of LSTM for question features capturing. This improvement can capture more levels of language granularities in parallel, because of the various sizes of filters in AG. The empirical study on the benchmark dataset of VQA demonstrates that capturing sentence features on different levels of granularities benefit sentence modelling by utilizing AG.

引用

页码：603 / 606

页数：4

共 50 条

[41] LANGUAGE AND VISUAL RELATIONS ENCODING FOR VISUAL QUESTION ANSWERING
Liu, Fei
Liu, Jing
Fang, Zhiwei
Lu, Hanqing
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3307 - 3311
[42] Compositional Substitutivity of Visual Reasoning for Visual Question Answering
Li, Chuanhao
Li, Zhen
Jing, Chenchen
Wu, Yuwei
Zhai, Mingliang
Jia, Yunde
COMPUTER VISION - ECCV 2024, PT XLVIII, 2025, 15106 : 143 - 160
[43] Visual Question Answering using Explicit Visual Attention
Lioutas, Vasileios
Passalis, Nikolaos
Tefas, Anastasios
2018 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2018,
[44] Exploiting hierarchical visual features for visual question answering
Hong, Jongkwang
Fu, Jianlong
Uh, Youngjung
Mei, Tao
Byun, Hyeran
NEUROCOMPUTING, 2019, 351 : 187 - 195
[45] QUES-TO-VISUAL GUIDED VISUAL QUESTION ANSWERING
Wu, Xiangyu
Lu, Jianfeng
Li, Zhuanfeng
Xiong, Fengchao
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 4193 - 4197
[46] PRIOR VISUAL RELATIONSHIP REASONING FOR VISUAL QUESTION ANSWERING
Yang, Zhuoqian
Qin, Zengchang
Yu, Jing
Wan, Tao
2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 1411 - 1415
[47] Multiple answers to a question: a new approach for visual question answering
Hosseinabad, Sayedshayan Hashemi
Safayani, Mehran
Mirzaei, Abdolreza
VISUAL COMPUTER, 2021, 37 (01): : 119 - 131
[48] Question-Guided Hybrid Convolution for Visual Question Answering
Gao, Peng
Li, Hongsheng
Li, Shuang
Lu, Pan
Li, Yikang
Hoi, Steven C. H.
Wang, Xiaogang
COMPUTER VISION - ECCV 2018, PT I, 2018, 11205 : 485 - 501
[49] Generating Question Relevant Captions to Aid Visual Question Answering
Wu, Jialin
Hu, Zeyuan
Mooney, Raymond J.
57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 3585 - 3594
[50] Debiased Visual Question Answering via the perspective of question types
Huai, Tianyu
Yang, Shuwen
Zhang, Junhang
Zhao, Jiabao
He, Liang
PATTERN RECOGNITION LETTERS, 2024, 178 : 181 - 187

← 1 2 3 4 5 →