Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval

Sketch-based image retrieval (SBIR) is a challenging task due to the large cross-domain gap between sketches and natural images. How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR. In this paper, we propose a novel semi-heterogeneo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems for video technology 2020-09, Vol.30 (9), p.3226-3237
Hauptverfasser:	Lei, Jianjun, Song, Yuxin, Peng, Bo, Ma, Zhanyu, Shao, Ling, Song, Yi-Zhe
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment co-attention model cross-domain learning Domains Embedding Feature extraction hybrid-loss mechanism Image color analysis Image edge detection Image management Image retrieval Mapping Representations SBIR Semantics Shape Sketches Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!