activity
20172022
most citedActiveHNE: Active Heterogeneous Network Embedding

9 citations · 33 across the 19 of their papers we have counts for

collaborators

28 papers

cs.IR2022

Long-tail Cross Modal Hashing

Zijun Gao, Jun Wang, Guoxian Yu +3

Existing Cross Modal Hashing (CMH) methods are mainly designed for balanced data, while imbalanced data with long-tail distribution is more general in real-world. Several long-tail…

cs.LG2022

Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoders

Priya Mani, Carlotta Domeniconi

Exemplar-based methods rely on informative data points or prototypes to guide the optimization of learning algorithms. Such data facilitate interpretable model design and predictio…

cs.LG2021

MetaMIML: Meta Multi-Instance Multi-Label Learning

Yuanlin Yang, Guoxian Yu, Jun Wang +3

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances. Curren…

cs.LG20211 cited

Meta Cross-Modal Hashing on Long-Tailed Data

Runmin Wang, Guoxian Yu, Carlotta Domeniconi +1

Due to the advantage of reducing storage while speeding up query time on big heterogeneous data, cross-modal hashing has been extensively studied for approximate nearest neighbor s…

cs.CV2021

Cross-modal Zero-shot Hashing by Label Attributes Embedding

Runmin Wang, Guoxian Yu, Lei Liu +3

Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search. Most CMH solutions ideally assume the labels of training and test…

cs.HC20211 cited

Open-Set Crowdsourcing using Multiple-Source Transfer Learning

Guangyang Han, Guoxian Yu, Lei Liu +3

We raise and define a new crowdsourcing scenario, open set crowdsourcing, where we only know the general theme of an unfamiliar crowdsourcing project, and we don't know its label s…