Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks | |
Zeyu Cui1,2![]() ![]() ![]() ![]() | |
2019-05 | |
会议名称 | The World Wide Web Conference (WWW) |
页码 | 307–317 |
会议日期 | 2019-5-12 |
会议地点 | San Francisco, CA, USA |
会议录编者/会议主办者 | Association for Computing Machinery |
出版地 | New York, NY, USA |
摘要 | With the rapid development of fashion market, the customers' demands of customers for fashion recommendation are rising. In this paper, we aim to investigate a practical problem of fashion recommendation by answering the question “which item should we select to match with the given fashion items and form a compatible outfit”. The key to this problem is to estimate the outfit compatibility. Previous works which focus on the compatibility of two items or represent an outfit as a sequence fail to make full use of the complex relations among items in an outfit. To remedy this, we propose to represent an outfit as a graph. In particular, we construct a Fashion Graph, where each node represents a category and each edge represents interaction between two categories. Accordingly, each outfit can be represented as a subgraph by putting items into their corresponding category nodes. To infer the outfit compatibility from such a graph, we propose Node-wise Graph Neural Networks (NGNN) which can better model node interactions and learn better node representations. In NGNN, the node interaction on each edge is different, which is determined by parameters correlated to the two connected nodes. An attention mechanism is utilized to calculate the outfit compatibility score with learned node representations. NGNN can not only be used to model outfit compatibility from visual or textual modality but also from multiple modalities. We conduct experiments on two tasks: (1) Fill-in-the-blank: suggesting an item that matches with existing components of outfit; (2) Compatibility prediction: predicting the compatibility scores of given outfits. Experimental results demonstrate the great superiority of our proposed method over others. |
关键词 | Graph neural networks Compatibility learning multi-modal |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1145/3308558.3313444 |
URL | 查看原文 |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61772528] ; National Natural Science Foundation of China[61871378] ; National Key Research and Development Program of China[2016YFB1001000] |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44382 |
专题 | 模式识别实验室 |
通讯作者 | Shu Wu |
作者单位 | 1.Chinese Acdemy of Science, Institute of Automation 2.University of Chinese Acdemy of Science 3.Chinese Acdemy of Science, Institute of Information Engineering |
推荐引用方式 GB/T 7714 | Zeyu Cui,Zekun Li,Shu Wu,et al. Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks[C]//Association for Computing Machinery. New York, NY, USA,2019:307–317. |
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 | ||
Dressing as a Whole_(3699KB) | 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