W
Wang-Cheng Kang
Researcher at University of California, San Diego
Publications - 29
Citations - 3414
Wang-Cheng Kang is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Recommender system & Hash function. The author has an hindex of 15, co-authored 27 publications receiving 2196 citations. Previous affiliations of Wang-Cheng Kang include University of California & Nanjing University.
Papers
More filters
Proceedings ArticleDOI
Self-Attentive Sequential Recommendation
Wang-Cheng Kang,Julian McAuley +1 more
TL;DR: In this article, a self-attention based sequential model (SASRec) is proposed, which uses an attention mechanism to identify which items are'relevant' from a user's action history, and use them to predict the next item.
Posted Content
Feature Learning based Deep Supervised Hashing with Pairwise Labels
TL;DR: Experiments show that the proposed deep pairwise-supervised hashing method (DPSH), to perform simultaneous feature learning and hashcode learning for applications with pairwise labels, can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.
Proceedings Article
Feature learning based deep supervised hashing with pairwise labels
TL;DR: Deep Pairwise-Supervised Hashing (DPSH) as mentioned in this paper performs simultaneous feature learning and hash-code learning for applications with pairwise labels and outperforms other methods to achieve the state-of-the-art performance in image retrieval.
Proceedings ArticleDOI
Translation-based Recommendation
TL;DR: This paper proposes a unified method, TransRec, to model such third-order relationships for large-scale sequential prediction, and embeds items into a 'transition space' where users are modeled as translation vectors operating on item sequences.
Proceedings Article
Column sampling based discrete supervised hashing
TL;DR: A novel method, called column sampling based discrete supervised hashing (COSDISH), to directly learn the discrete hashing code from semantic information and can outperform the state-of-the-art methods in real applications like image retrieval.