Supportive and Self Attentions for Image Caption

Jen Tzung Chien, Ting An Lin

研究成果: Conference contribution同行評審

4 引文 斯高帕斯(Scopus)

摘要

Attention over an observed image or natural sentence is run by spotting or locating the region or position of interest for pattern classification. The attention parameter is seen as a latent variable, which was indirectly calculated by minimizing the classification loss. Using such an attention mechanism, the target information may not be correctly identified. Therefore, in addition to minimizing the classification error, we can directly attend the region of interest by minimizing the reconstruction error due to supporting data. Our idea is to learn how to attend through the so-called supportive attention when the supporting information is available. A new attention mechanism is developed to conduct the attentive learning for translation invariance which is applied for image caption. The derived information is helpful for generating caption from input image. Moreover, this paper presents an association network which does not only implement the word-to-image attention, but also carry out the image-to-image attention via self attention. The relations between image and text are sufficiently represented. Experiments on MS-COCO task show the benefit of the proposed supportive and self attentions for image caption with the keyvalue memory network.

原文English
主出版物標題2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1713-1718
頁數6
ISBN(電子)9789881476883
出版狀態Published - 7 12月 2020
事件2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Virtual, Auckland, New Zealand
持續時間: 7 12月 202010 12月 2020

出版系列

名字2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings

Conference

Conference2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020
國家/地區New Zealand
城市Virtual, Auckland
期間7/12/2010/12/20

指紋

深入研究「Supportive and Self Attentions for Image Caption」主題。共同形成了獨特的指紋。

引用此