Joint Image-Text Hashing for Fast Large-Scale Cross-Media Retrieval Using Self-Supervised Deep Learning
Joint Image-Text Hashing for Fast Large-Scale Cross-Media Retrieval Using Self-Supervised Deep Learning is a scholarly work, published in 2019 in ''IEEE Transactions on Industrial Electronics''. The main subjects of the publication include discrete optimization, universal hashing, artificial intelligence, hash function, double hashing, theoretical computer science, Multiple object tracking, pattern recognition, question answering, binary numeral system, binary code, benchmark, dynamic perfect hashing, Locality-sensitive hashing, computer science, hash table, feature engineering, regularization, deep learning, and image retrieval. The authors propose a novel supervised hashing method for large-scale cross-media search, termed self-supervised deep multimodal hashing (SSDMH), which learns unified hash codes as well as deep hash functions for different modalities in a self-supervised manner.