Augmented Visual-semantic Embeddings for Image and Sentence Matching | |
Chen, Zerui1,3; Huang, Yan1,3; Wang, Liang1,2,3,4 | |
2019-07 | |
会议名称 | International Conference on Image Processing |
会议日期 | 2019.9.22-2019.9.25 |
会议地点 | Taipei |
摘要 | The task of image and sentence matching has witnessed significant progress recently, but it is still challenging arising from the tremendous semantic gap between a pixel-level image and its matched sentences. Due to limited training data, it is rather challenging to optimize the visual-semantic embeddings. In this work, we propose to augment visual-semantic embeddings via enlarging the training dataset. With more data, models can learn discriminative features with highquality semantic concepts. More specifically, we augment data by generating sentences for given images. Our method consists of two steps. At first, to enlarge the training dataset, given an image, we perform image captioning. Instead of introducing redundancy to our augmented dataset, we hope that our generated sentences are in diverse style and maintain its fidelity at the same time. Therefore, we consult to generative adversarial networks (GANs) which can produce more flexible expressions compared to methods based on the maximum likelihood principle. Then, we augment visualsemantic embeddings with the augmented training dataset and obtain the model for the task of image and sentence matching. Experiments on the popular benchmark demonstrate the effectiveness of our method by achieving superior results compared to our baseline. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44428 |
专题 | 模式识别实验室 |
通讯作者 | Chen, Zerui |
作者单位 | 1.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR) 2.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA) 3.University of Chinese Academy of Sciences (UCAS) 4.Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR) |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chen, Zerui,Huang, Yan,Wang, Liang. Augmented Visual-semantic Embeddings for Image and Sentence Matching[C],2019. |
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 | ||
chen2019.pdf(503KB) | 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