Learning hash functions for approximate nearest neighbor search of high-dimensional data
has received a surge of interests in recent years. Most existing methods are often concerned …

Recently, deep Hamming hashing methods have been proposed for Hamming space
retrieval which enables constant-time search by hash table lookups instead of linear scan …

Deep representation learning is a subfield of machine learning that focuses on learning
meaningful and useful representations of data through deep neural networks. However …

The goal of supervised hashing is to construct hash map**s from collections of images
and semantic annotations such that semantically relevant images are embedded nearby in …

Recently, massive multimedia data (especially images) is moved to the cloud environment
for analysis and retrieval, which makes data security issue become particularly significant …

In this article, we propose SemanticHash, a simple and effective deep neural network model,
to leverage semantic word embeddings (eg, BERT) in hash codes learning. Both images …

As an approximate nearest neighbor search technique, hashing has been widely applied in
large-scale image retrieval due to its excellent efficiency. Most supervised deep hashing …

Abstract In recent years, Convolutional Neural Networks (CNNs) have shown promising
performance on image hashing retrieval. However, due to the information-discarded nature …

Contrastive self-supervised learning has shown to learn representations transferable to a
variety of downstream applications, eg, object detection and classification. While utilizing a …

An important characteristic of the recent decade is the dramatic growth in the use and
generation of data. From collections of images, documents and videos, to genetic data, and …