In this paper, we propose S uppression-E nhancing M ask based attention and I nteractive C
hannel transformati ON (SEMICON) to learn binary hash codes for dealing with large-scale …

Two-tower models are a prevalent matching framework for recommendation, which have
been widely deployed in industrial applications. The success of two-tower matching …

Image retrieval with fine-grained categories is an extremely challenging task due to the high
intraclass variance and low interclass variance. Most previous works have focused on …

Existing fine-grained hashing methods typically lack code interpretability as they compute
hash code bits holistically using both global and local features. To address this limitation we …

Fine-grained image retrieval is a fundamental and challenging problem in computer vision
due to the intra-class diversities and inter-class confusions. Existing hashingbased …

The goal of unsupervised cross-modal hashing (UCMH) is to map different modalities into a
semantic-preserving hamming space without requiring label supervision. Existing deep …

Most fine-grained hashing methods focus solely on designing stronger feature extraction
strategies to obtain fine-grained features, without considering how to preserve discriminative …

Unsupervised video hashing aims to learn a nonlinear hashing function to map videos into a
similarity-preserving hamming space without label supervision. Different from static images …

In this paper, a new fine-grained image classification (FGIC) network with feature
relationship enhancement of multiple stages is established. After the engaging of scene text …

Large-scale fine-grained image retrieval aims to learn compact discriminative feature
representations based on mining the subtle distinctions between visually similar objects …