Neighborhood Contrastive Transformer for Change Captioning

doi:10.1109/TMM.2023.3254162

CSpace

	Neighborhood Contrastive Transformer for Change Captioning
	Tu, Yunbin 1; Li, Liang 2,3; Su, Li 1; Lu, Ke 4,5; Huang, Qingming 1
	2023
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	25 页码:9518-9529
摘要	Change captioning is to describe the semantic change between a pair of similar images in natural language. It is more challenging than general image captioning, because it requires capturing fine-grained change information while being immune to irrelevant viewpoint changes, and solving syntax ambiguity in change descriptions. In this paper, we propose a neighborhood contrastive transformer to improve the model's perceiving ability for various changes under different scenes and cognition ability for complex syntax structure. Concretely, we first design a neighboring feature aggregating to integrate neighboring context into each feature, which helps quickly locate the inconspicuous changes under the guidance of conspicuous referents. Then, we devise a common feature distilling to compare two images at neighborhood level and extract common properties from each image, so as to learn effective contrastive information between them. Finally, we introduce the explicit dependencies between words to calibrate the transformer decoder, which helps better understand complex syntax structure during training. Extensive experimental results demonstrate that the proposed method achieves the state-of-the-art performance on three public datasets with different change scenarios.
关键词	Change captioning neighborhood contrastive transformer syntax dependencies
DOI	10.1109/TMM.2023.3254162
收录类别	SCI
语种	英语
资助项目	National Key Ramp;D Program of China
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:001133324200036
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38416
专题	中国科学院计算技术研究所
通讯作者	Li, Liang; Su, Li
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Hangzhou Dianzi Univ, Lishui Inst, Lishui 323000, Zhejiang, Peoples R China 4.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 101408, Peoples R China 5.Peng Cheng Lab, Shenzhen 518055, Guangdong, Peoples R China
推荐引用方式 GB/T 7714	Tu, Yunbin,Li, Liang,Su, Li,et al. Neighborhood Contrastive Transformer for Change Captioning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:9518-9529.
APA	Tu, Yunbin,Li, Liang,Su, Li,Lu, Ke,&Huang, Qingming.(2023).Neighborhood Contrastive Transformer for Change Captioning.IEEE TRANSACTIONS ON MULTIMEDIA,25,9518-9529.
MLA	Tu, Yunbin,et al."Neighborhood Contrastive Transformer for Change Captioning".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):9518-9529.