Visual Question Answering on CLEVR Dataset via Multimodal Fusion and Relational Reasoning

被引：0

作者：

Allahyari, Abbas ^{[1
]}

Borna, Keivan ^{[1
]}

机构：

[1] Kharazmi Univ, Dept Comp Sci, Tehran, Iran

来源：

2021 52ND ANNUAL IRANIAN MATHEMATICS CONFERENCE (AIMC) | 2021年

关键词：

Visual Question Answering; Visual Reasoning; Multi-modal Learning; Deep Learning;

D O I：

10.1109/AIMC54250.2021.9656978

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Visual question answering (VQA) is a new interdisciplinary research area, in which a model attempts to answer a free-form question in natural language based on a given image. In this paper we improve an existing model, which leverages relational networks and attention mechanism, by decreasing its train and inference time while preserving a comparable accuracy.

引用

页码：74 / 76

页数：3

共 50 条

[1] Multimodal feature fusion by relational reasoning and attention for visual question answering
Zhang, Weifeng
Yu, Jing
Hu, Hua
Hu, Haiyang
Qin, Zengchang
[J]. INFORMATION FUSION, 2020, 55 : 116 - 126
[2] MUREL: Multimodal Relational Reasoning for Visual Question Answering
Cadene, Remi
Ben-younes, Hedi
Cord, Matthieu
Thome, Nicolas
[J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 1989 - 1998
[3] ViCLEVR: a visual reasoning dataset and hybrid multimodal fusion model for visual question answering in Vietnamese
Tran, Khiem Vinh
Phan, Hao Phu
Van Nguyen, Kiet
Nguyen, Ngan Luu Thuy
[J]. MULTIMEDIA SYSTEMS, 2024, 30 (04)
[4] Relational reasoning and adaptive fusion for visual question answering
Shen, Xiang
Han, Dezhi
Zong, Liang
Guo, Zihan
Hua, Jie
[J]. APPLIED INTELLIGENCE, 2024, 54 (06) : 5062 - 5080
[5] Multimodal Learning and Reasoning for Visual Question Answering
Ilievski, Ilija
Feng, Jiashi
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[6] OpenViVQA: Task, dataset, and multimodal fusion models for visual question answering in Vietnamese
Nguyen, Nghia Hieu
Vo, Duong T. D.
Nguyen, Kiet Van
Nguyen, Ngan Luu-Thuy
[J]. INFORMATION FUSION, 2023, 100
[7] DMRFNet: Deep Multimodal Reasoning and Fusion for Visual Question Answering and explanation generation
Zhang, Weifeng
Yu, Jing
Zhao, Wenhong
Ran, Chuan
[J]. INFORMATION FUSION, 2021, 72 : 70 - 79
[8] Multimodal Graph Reasoning and Fusion for Video Question Answering
Zhang, Shuai
Wang, Xingfu
Hawbani, Ammar
Zhao, Liang
Alsamhi, Saeed Hamood
[J]. 2022 IEEE INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, 2022, : 1410 - 1415
[9] Multimodal Knowledge Reasoning for Enhanced Visual Question Answering
Hussain, Afzaal
Maqsood, Ifrah
Shahzad, Muhammad
Fraz, Muhammad Moazam
[J]. 2022 16TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY & INTERNET-BASED SYSTEMS, SITIS, 2022, : 224 - 230
[10] LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering
Gao, Jingying
Wu, Qi
Blair, Alan
Pagnucco, Maurice
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,

← 1 2 3 4 5 →