Knowledge Commons of Institute of Automation,CAS
Learning Multimodal Taxonomy via Variational Deep Graph Embedding and Clustering | |
Huaiwen Zhang1,2; Quan Fang1,2; Shengsheng Qian1,2; Changsheng Xu1,2 | |
2018-10 | |
会议名称 | ACM international conference on Multimedia |
会议日期 | October 22 - 26, 2018 |
会议地点 | Seoul, Republic of Korea |
摘要 | Taxonomy learning is an important problem and facilitates various applications such as semantic understanding and information retrieval. Previous work for building semantic taxonomies has primarily relied on labor-intensive human contributions or focused on text-based extraction. In this paper, we investigate the problem of automatically learning multimodal taxonomies from the multimedia data on the Web. A systematic framework called Variational Deep Graph Embedding and Clustering (VDGEC) is proposed consisting of two stages as concept graph construction and taxonomy induction via variational deep graph embedding and clustering. VDGEC discovers hierarchical concept relationships by exploiting the semantic textual-visual correspondences and contextual co-occurrences in an unsupervised manner. The unstructured semantics and noisy issues of multimedia documents are carefully addressed by VDGEC for high quality taxonomy induction. We conduct extensive experiments on the real-world datasets. Experimental results demonstrate the effectiveness of the proposed framework, where VDGEC outperforms previous unsupervised approaches by a large gap. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/25824 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Huaiwen Zhang,Quan Fang,Shengsheng Qian,et al. Learning Multimodal Taxonomy via Variational Deep Graph Embedding and Clustering[C],2018. |
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 | ||
Learning Multimodal (3204KB) | 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