期刊
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
卷 -, 期 -, 页码 3728-3735出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICPR48806.2021.9413223
关键词
-
类别
资金
- National Key Research and Development Program of China [2016YFB1001000]
- Key Research Program of Frontier Sciences, CAS [ZDBS-LYJSC032]
- Joint Fund for Regional Innovation and Development of NSFC [U19A2083]
- Science and Technology Research and Major Achievements Transformation Project of Strategic Emerging Industries in Hunan Province [2019GK4007]
- Natural Science Foundation of Hunan Province [2020JJ4090, 2020JJ4588]
- Shandong Provincial Key Research and Development Program [2019JZZY010119]
- CAS-AIR
The Improved Visual Semantic Reasoning model (VSR++) addresses the challenges in fine-grained image-text matching by jointly modeling global alignment and local correspondence. With a suitable learning strategy to balance their importance, the model achieves state-of-the-art performance on two benchmark datasets by distinguishing image regions and text words at a fine-grained level.
Image-text matching has made great progresses recently, but there still remains challenges in fine-grained matching. To deal with this problem, we propose an Improved Visual Semantic Reasoning model (VSR++), which jointly models 1) global alignment between images and texts and 2) local correspondence between regions and words in a unified framework. To exploit their complementary advantages, we also develop a suitable learning strategy to balance their relative importance. As a result, our model can distinguish image regions and text words in a fine-grained level, and thus achieves the current state-of-the-art performance on two benchmark datasets.
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