AnANet: Association and Alignment Network for Modeling Implicit Relevance in Cross-Modal Correlation Classification
文献类型：期刊论文
| 作者 | Xu, Nan2,3 ; Wang, Junyan2; Tian, Yuan1,3; Zhang, Ruike1,3; Mao, Wenji1,3
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2023 |
| 卷号 | 25页码:7867-7880 |
| ISSN号 | 1520-9210 |
| 关键词 | Association and alignment network classification scheme cross-modal correlation implicit relevance |
| DOI | 10.1109/TMM.2022.3229960 |
| 通讯作者 | Mao, Wenji(wenji.mao@ia.ac.cn) |
| 英文摘要 | With the explosive increase of multimodal data, cross-modal correlation classification has become an important research topic and is in great demand in many cross-modal applications. A variety of classification schemes and predictive models have been built based on the existing cross-modal correlation categorization. However, these classification schemes typically follow the prior assumption that the paired cross-modal samples are strictly related, and thus pay great attention to the fine-grained relevant types of cross-modal correlation, ignoring the high volume of implicitly relevant data which are often wrongly classified into irrelevant types. Even more, previous predictive models fall short of reflecting the essence of cross-modal correlation according to their definitions, especially in the modeling of network structure. Thus in this paper, by comprehensively investigating the current image-text correlation classification research, we redefine a new classification scheme for cross-modal correlation based on the implicit and explicit relevance. To predict the types of image-text correlation based on our proposed definition, we further devise the Association and Alignment Network (namely AnANet) to model the implicit and explicit relevance, which captures both the implicit association of global discrepancy and commonality between image and text and explicit alignment of cross-modal local relevance. Experimental studies on our constructed new image-text correlation dataset verify the effectiveness of our proposed model. |
| 资助项目 | Ministry of Science and Technology of China[2020AAA0108405] ; National Natural Science Foundation of China[62206287] ; National Natural Science Foundation of China[11832001] ; National Natural Science Foundation of China[71621002] |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:001121212400020 |
| 资助机构 | Ministry of Science and Technology of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55434]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Mao, Wenji |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 2.Beijing Wenge Technol Co Ltd, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xu, Nan,Wang, Junyan,Tian, Yuan,et al. AnANet: Association and Alignment Network for Modeling Implicit Relevance in Cross-Modal Correlation Classification[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:7867-7880. |
| APA | Xu, Nan,Wang, Junyan,Tian, Yuan,Zhang, Ruike,&Mao, Wenji.(2023).AnANet: Association and Alignment Network for Modeling Implicit Relevance in Cross-Modal Correlation Classification.IEEE TRANSACTIONS ON MULTIMEDIA,25,7867-7880. |
| MLA | Xu, Nan,et al."AnANet: Association and Alignment Network for Modeling Implicit Relevance in Cross-Modal Correlation Classification".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):7867-7880. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。