期刊
INFORMATION SCIENCES
卷 543, 期 -, 页码 504-516出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2020.05.064
关键词
Micro-video; Scene Recognition; Attention; Consistent Semantic Learning
资金
- National Natural Science Foundation of China [61671274, 61876098, 61573219]
- National Key R&D Program of China [2018YFC0830100, 2018YFC0830102]
- special funds for distinguished professors of Shandong Jianzhu University
Micro-video scene recognition is challenged by content inconsistency and varying importance of frames, limiting its accuracy. To address this, attention-based consistent semantic learning (ACSL) is proposed to maintain semantic consistency and outperforms other methods in experimental evaluations.
Micro-videos are one of the most popular multimedia forms in mobile internet domain, and scene recognition is important for micro-video semantic analyses and understanding. Compared with traditional videos, scene recognition in micro-videos is subject to content inconsistency for the same scene owing to the subjectivity of photographers. Moreover, the importance of frames for semantic representation differs in the same micro-video. These phenomenons limit micro-video scene recognition. To address these issues, in this paper, attention-based consistent semantic learning (ACSL) is proposed for micro-video scene recognition; this consists of a two-branch framework combined with an attention mechanism for the maintenance of the semantic consistency within classes. The experiments conducted in this study on multiple datasets revealed that the proposed ACSL achieves a better performance than other video scene recognition methods. (C) 2020 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据