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

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 7; pp. 2866 - 2879
• Main Authors: Wen, Keyu, Gu, Xiaodong, Cheng, Qingrong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 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)

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...