Chatgpt asks, blip-2 answers: Automatic questioning towards enriched visual descriptions

D Zhu, J Chen, K Haydarov, X Shen, W Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Asking insightful questions is crucial for acquiring knowledge and expanding our
understanding of the world. However, the importance of questioning has been largely …

Chatting makes perfect: Chat-based image retrieval

M Levy, R Ben-Ari, N Darshan… - Advances in Neural …, 2024 - proceedings.neurips.cc
Chats emerge as an effective user-friendly approach for information retrieval, and are
successfully employed in many domains, such as customer service, healthcare, and finance …

Knowledge-based visual question generation

J **e, W Fang, Y Cai, Q Huang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Visual question generation task aims to generate meaningful questions about an image
targeting an answer. Existing methods focus on the visual concepts in the image for question …

Guiding visual question generation

N Vedd, Z Wang, M Rei, Y Miao, L Specia - arxiv preprint arxiv …, 2021 - arxiv.org
In traditional Visual Question Generation (VQG), most images have multiple concepts (eg
objects and categories) for which a question could be generated, but models are trained to …

Deconfounded visual question generation with causal inference

J Chen, Z Guo, J **e, Y Cai, Q Li - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Visual Question Generation (VQG) task aims to generate meaningful and logically
reasonable questions about the given image targeting an answer. Existing methods mainly …

Multiple objects-aware visual question generation

J **e, Y Cai, Q Huang, T Wang - Proceedings of the 29th ACM …, 2021 - dl.acm.org
Visual question generation task aims to generate meaningful questions about an image
according to a target answer. Existing studies mainly focus on merely one object related to …

ConVQG: Contrastive Visual Question Generation with Multimodal Guidance

L Mi, S Montariol, JC Navarro, X Dai… - Proceedings of the …, 2024 - ojs.aaai.org
Asking questions about visual environments is a crucial way for intelligent agents to
understand rich multi-faceted scenes, raising the importance of Visual Question Generation …

What bert sees: Cross-modal transfer for visual question generation

T Scialom, P Bordes, PA Dray, J Staiano… - arxiv preprint arxiv …, 2020 - arxiv.org
Pre-trained language models have recently contributed to significant advances in NLP tasks.
Recently, multi-modal versions of BERT have been developed, using heavy pre-training …

Goal-driven visual question generation from radiology images

M Sarrouti, A Ben Abacha, D Demner-Fushman - Information, 2021 - mdpi.com
Visual Question Generation (VQG) from images is a rising research topic in both fields of
natural language processing and computer vision. Although there are some recent efforts …

DiagramQG: A Dataset for Generating Concept-Focused Questions from Diagrams

X Zhang, L Zhang, Y Wu, M Huang, W Wu, B Li… - arxiv preprint arxiv …, 2024 - arxiv.org
Visual Question Generation (VQG) has gained significant attention due to its potential in
educational applications. However, VQG researches mainly focus on natural images …