Knowledge Commons of Institute of Automation,CAS
WL-MSR: Watch and Listen for Multimodal Subtitle Recognition | |
Liu, Jiawei1,2![]() ![]() ![]() ![]() | |
2023-06 | |
会议名称 | IEEE International Conference on Acoustics, Speech and Signal Processing |
会议日期 | 2023-6-4 |
会议地点 | Greece |
摘要 | Video subtitles could be defined as the combination of visualized subtitles in frames and textual content recognized from speech, which play a significant role in video understanding for both humans and machines. In this paper, we propose a novel Watch and Listen for Multimodal Subtitle Recognition (WL-MSR) framework to obtain comprehensive video subtitles, by fusing the information provided by Optical Character Recognition (OCR) and Automatic Speech Recognition (ASR) models. Specifically, we build a Transformer model with mask and crop strategies and multi-level identity embeddings to aggregate both the textual results and features of the two modalities. To pre-filter out the noise items in OCR results before fusion, we adopt an OCR filter based on ASR results and confidence scores of OCR. By combining these techniques, our solution wins the 2nd place in Multimodal Subtitle Recognition Challenge on ICPR2022. |
七大方向——子方向分类 | 多模态智能 |
国重实验室规划方向分类 | 多模态协同认知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52325 |
专题 | 紫东太初大模型研究中心 |
作者单位 | 1.The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Liu, Jiawei,Wang, Hao,Wang, Weining,et al. WL-MSR: Watch and Listen for Multimodal Subtitle Recognition[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
WL-MSR_Watch_and_Lis(1673KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论