Composed Image Retrieval via Cross Relation Network With Hierarchical Aggregation Transformer

Composing Text and Image to Image Retrieval (CTI-IR) aims at finding the target image, which matches the query image visually along with the query text semantically. However, existing works ignore the fact that the reference text usually serves multiple functions, e.g., modification and auxiliary. T...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 02., Seite 4543-4554
1. Verfasser: Yang, Qu (VerfasserIn)
Weitere Verfasser: Ye, Mang, Cai, Zhaohui, Su, Kehua, Du, Bo
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article