Results 31 to 40 of about 34,250 (255)
An Improved Attention for Visual Question Answering [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 We consider the problem of Visual Question Answering (VQA). Given an image and a free-form, open-ended, question, expressed in natural language, the goal of VQA system is to provide accurate answer to this question with respect to the image. The task is challenging because it requires simultaneous and intricate understanding of both visual and textual ...
Tanzila Rahman +3 more
openaire +2 more sources
A Metamorphic Testing Approach for Assessing Question Answering Systems
Mathematics, 2021 Question Answering (QA) enables the machine to understand and answer questions posed in natural language, which has emerged as a powerful tool in various domains. However, QA is a challenging task and there is an increasing concern about its quality.
Kaiyi Tu, Mingyue Jiang, Zuohua Ding
doaj +1 more source
Question Relevance in Visual Question Answering
CoRR, 2018 Free-form and open-ended Visual Question Answering systems solve the problem of providing an accurate natural language answer to a question pertaining to an image. Current VQA systems do not evaluate if the posed question is relevant to the input image and hence provide nonsensical answers when posed with irrelevant questions to an image. In this paper,
Prakruthi Prabhakar +2 more
openaire +2 more sources
Improving reasoning with contrastive visual information for visual question answering
Electronics Letters, 2021 Visual Question Answering (VQA) aims to output a correct answer based on cross‐modality inputs including question and visual content. In general pipeline, information reasoning plays the key role for a reasonable answer.
Yu Long +3 more
doaj +1 more source
DOMAS: DATA ORIENTED MEDICAL VISUAL QUESTION ANSWERING USING SWIN TRANSFORMER
Studia Universitatis Babes-Bolyai: Series Informatica, 2023 The Medical Visual Question Answering problem is a joined Computer Vision and Natural Language Processing task that aims to obtain answers in natural language to a question, posed in natural language as well, regarding an image.
Teodora-Alexandra TOADER
doaj +1 more source
Survey of Text-based Visual Question Answering [PDF]
Jisuanji gongchengTraditional Visual Question Answering(VQA)only focuses on the visual object information in the image, ignoring the text information in the image. In addition to visual information, Text-based Visual Question Answering (TextVQA)also focuses on the text ...
Guide ZHU, Hai HUANG
doaj +1 more source
Visual question answering with gated relation‐aware auxiliary
IET Image Processing, 2022 The great advances in computer vision and natural language processing make significant progress in visual question answering. In the visual question answering task, the visual representation is essential for understanding the image content.
Xiangjun Shao +2 more
doaj +1 more source
Multi-Shared Attention with Global and Local Pathways for Video Question Answering [PDF]
Jisuanji kexue, 2021 Video question answering is a challenging task of significant importance toward visual understanding.However,current visual question answering (VQA) methods mainly focus on a single static image,which is distinct from the sequential visual data we faced ...
WANG Lei-quan, HOU Wen-yan, YUAN Shao-zu, ZHAO Xin, LIN Yao, WU Chun-lei
doaj +1 more source
iVQA: Inverse Visual Question Answering [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model
Liu, Feng, +4 more
openaire +3 more sources
Co-Attention Network With Question Type for Visual Question Answering
IEEE Access, 2019 Visual Question Answering (VQA) is a challenging multi-modal learning task since it requires an understanding of both visual and textual modalities simultaneously.
Chao Yang +4 more
doaj +1 more source