Learning Dual Semantic Relations With Graph Attention for Image-Text Matching

Image-Text Matching is one major task in cross-modal information processing. The main challenge is to learn the unified visual and textual representations. Previous methods that perform well on this task primarily focus on not only the alignment between region features in images and the correspondin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on circuits and systems for video technology Ročník 31; číslo 7; s. 2866 - 2879
Hlavní autoři: Wen, Keyu, Gu, Xiaodong, Cheng, Qingrong
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Alignment
Automobiles
Birds
Cross-modal retrieval
Data processing
Feature extraction
graph attention
Hierarchies
Image retrieval
image text matching
Learning
Modules
Representations
semantic relation
Semantic relations
Semantics
Sentences
Task analysis
Visualization
Words (language)
ISSN:1051-8215, 1558-2205
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Image-Text Matching is one major task in cross-modal information processing. The main challenge is to learn the unified visual and textual representations. Previous methods that perform well on this task primarily focus on not only the alignment between region features in images and the corresponding words in sentences, but also the alignment between relations of regions and relational words. However, the lack of joint learning of regional features and global features will cause the regional features to lose contact with the global context, leading to the mismatch with those non-object words which have global meanings in some sentences. In this work, in order to alleviate this issue, it is necessary to enhance the relations between regions and the relations between regional and global concepts to obtain a more accurate visual representation so as to be better correlated to the corresponding text. Thus, a novel multi-level semantic relations enhancement approach named Dual Semantic Relations Attention Network(DSRAN) is proposed which mainly consists of two modules, separate semantic relations module and the joint semantic relations module. DSRAN performs graph attention in both modules respectively for region-level relations enhancement and regional-global relations enhancement at the same time. With these two modules, different hierarchies of semantic relations are learned simultaneously, thus promoting the image-text matching process by providing more information for the final visual representation. Quantitative experimental results have been performed on MS-COCO and Flickr30K and our method outperforms previous approaches by a large margin due to the effectiveness of the dual semantic relations learning scheme.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2020.3030656