Deep Variational and Structural Hashing

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 42; no. 3; pp. 580 - 595
• Main Authors: Liong, Venice Erin, Lu, Jiwen, Duan, Ling-Yu, Tan, Yap-Peng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Binary codes; Binary system; Codes; Convolution; cross-modal retrieval; deep learning; fast similarity search; hashing; Multimedia; Probabilistic logic; Quantization (signal); Representations; Retrieval; Scalable image search; Semantics; Training; Visualization

In this paper, we propose a deep variational and structural hashing (DVStH) method to learn compact binary codes for multimedia retrieval. Unlike most existing deep hashing methods which use a series of convolution and fully-connected layers to learn binary features, we develop a probabilistic frame...