@inproceedings{ec974ff1ed514143a9decfaf765f9023,
title = "VTQA2023: ACM Multimedia 2023 Visual Text Question Answering Challenge",
abstract = "The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are limited to just picking the answer from a pre-defined set of options and lack attention to text. We present a new challenge with a dataset that contains 23,781 questions based on 10124 image-text pairs. Specifically, the task requires the model to align multimedia representations of the same entity to implement multi-hop reasoning between image and text and finally use natural language to answer the question. The aim of this challenge is to develop and benchmark models that are capable of multimedia entity alignment, multi-step reasoning and open-ended answer generation.",
keywords = "dataset, multimodal, visual question answering",
author = "Kang Chen and Tianli Zhao and Xiangqian Wu",
note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 31st ACM International Conference on Multimedia, MM 2023 ; Conference date: 29-10-2023 Through 03-11-2023",
year = "2023",
month = oct,
day = "27",
doi = "10.1145/3581783.3614244",
language = "英语",
series = "MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia",
publisher = "Association for Computing Machinery, Inc",
pages = "9646--9650",
booktitle = "MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia",
}