Vqa and visual reasoning: An overview of recent datasets, methods and challenges

RY Zakari, JW Owusu, H Wang, K Qin, ZK Lawal… - arXiv preprint arXiv …, 2022 - arxiv.org
Artificial Intelligence (AI) and its applications have sparked extraordinary interest in recent
years. This achievement can be ascribed in part to advances in AI subfields including …

GraghVQA: Language-guided graph neural networks for graph-based visual question answering

W Liang, Y Jiang, Z Liu - arXiv preprint arXiv:2104.10283, 2021 - arxiv.org
Images are more than a collection of objects or attributes--they represent a web of
relationships among interconnected objects. Scene Graph has emerged as a new modality …

Enhancing e-commerce recommendation systems through approach of buyer's self-construal: necessity, theoretical ground, synthesis of a six-step model, and …

Y Feng - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
The current recommendation system predominantly relies on evidential factors such as
behavioral outcomes and purchasing history. However, limited research has been …

Multi-step question-driven visual question answering for remote sensing

M Zhang, F Chen, B Li - IEEE Transactions on Geoscience and …, 2023 - ieeexplore.ieee.org
Visual question answering (VQA) aims to build an interactive system that infers the answer
according to the input image and text-based question. Recently, VQA for remote sensing has …

SelfGraphVQA: a self-supervised graph neural network for scene-based question answering

BC de Oliveira Souza, M Aasan… - Proceedings of the …, 2023 - openaccess.thecvf.com
The intersection of vision and language is of major interest due to the increased focus on
seamless integration between recognition and reasoning. Scene graphs (SGs) have …

Neuro-symbolic learning: Principles and applications in ophthalmology

M Hassan, H Guan, A Melliou, Y Wang, Q Sun… - arXiv preprint arXiv …, 2022 - arxiv.org
Neural networks have been rapidly expanding in recent years, with novel strategies and
applications. However, challenges such as interpretability, explainability, robustness, safety …

Medical visual question answering based on question-type reasoning and semantic space constraint

M Wang, X He, L Liu, L Qing, H Chen, Y Liu… - Artificial Intelligence in …, 2022 - Elsevier
Medical visual question answering (Med-VQA) aims to accurately answer clinical questions
about medical images. Despite its enormous potential for application in the medical domain …

Herald: an annotation efficient method to detect user disengagement in social conversations

W Liang, KH Liang, Z Yu - arXiv preprint arXiv:2106.00162, 2021 - arxiv.org
Open-domain dialog systems have a user-centric goal: to provide humans with an engaging
conversation experience. User engagement is one of the most important metrics for …

SA-VQA: Structured alignment of visual and semantic representations for visual question answering

P Xiong, Q You, P Yu, Z Liu, Y Wu - arXiv preprint arXiv:2201.10654, 2022 - arxiv.org
Visual Question Answering (VQA) attracts much attention from both industry and academia.
As a multi-modality task, it is challenging since it requires not only visual and textual …

Research on visual question answering based on GAT relational reasoning

Y Miao, W Cheng, S He, H Jiang - Neural Processing Letters, 2022 - Springer
Due to the diversity of questions in VQA, it brings new challenges to the construction of VQA
model. Existing VQA models focus on constructing a new attention mechanism, which …