@inproceedings{b432037bb238490e861a6be6b7ce36d0,
title = "Confidence-Based Event-Centric Online Video Question Answering on a Newly Constructed ATBS Dataset",
abstract = "Deep neural networks facilitate video question answering (VideoQA), but the real-world applications on video streams such as CCTV and live cast place higher demands on the solver. To address the challenges of VideoQA on long videos of unknown length, we define a new set of problems called Online Open-ended Video Question Answering (O2VQA). It requires an online state-updating mechanism for the solver to decide if the collected information is sufficient to conclude an answer. We then propose a Confidence-based Event-centric Online Video Question Answering (CEO-VQA) model to solve this problem. Furthermore, a dataset called Answer Target in Background Stream (ATBS) is constructed to evaluate this newly developed online VideoQA application. Compared to the baseline VideoQA method that watches the whole video, the experimental results show that the proposed method achieves a significant performance gain.",
keywords = "Online Video Question Answering, Open-ended VideoQA, Video Understanding, VideoQA",
author = "Weikai Kong and Shuhong Ye and Chenglin Yao and Jianfeng Ren",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10095044",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",
address = "United States",
}