https://scholars.lib.ntu.edu.tw/handle/123456789/581062
標題: | TAGNet: Triplet-Attention Graph Networks for Hashtag Recommendation | 作者: | Chen, Yu-Chi Lai, Kuan-Ting Liu, Dong MING-SYAN CHEN |
關鍵字: | Networks (circuits); Video signal processing; Content information; Graph networks; Image graphs; Large-scale dataset; Multi modality; Recommendation methods; Similar image; Visual similarity; Large dataset | 公開日期: | 2021 | 卷: | 32 | 期: | 3 | 起(迄)頁: | 1148-1159 | 來源出版物: | IEEE Transactions on Circuits and Systems for Video Technology | 摘要: | Hashtag is an important advertising tool and a musthave feature for social media nowadays. In the past, many hashtag recommendation methods have been proposed from different perspectives of images, texts, and users. However, most previous works consider neither the mutual influence between multi-modalities, nor the visual similarity between images. In this paper, we devise a novel model, named Triplet-Attention Graph Network (TAGNet). The rationale behind our method is that visually similar images share some common hashtags. Therefore, we build an image graph, and apply a new Aggregated Graph Convolution (AGC) module to propagate information in a collective way. Furthermore, it is noted that text and user also have rich content information within posts, and we hence propose a Triplet Attention (TA) module to incorporate multi-modalities into node features. Experiments on the large-scale dataset collected from Instagram show that TAGNet achieved significant improvement in recall rate over the best state-of-the-art method. IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104612583&doi=10.1109%2fTCSVT.2021.3074599&partnerID=40&md5=80110dc0d090f8afff360890fd4a69e0 https://scholars.lib.ntu.edu.tw/handle/123456789/581062 |
ISSN: | 10518215 | DOI: | 10.1109/TCSVT.2021.3074599 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。