Search Results for author: Zongxuan Liu

Found 2 papers, 0 papers with code

Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning

no code implementations12 Oct 2023 ShiYang Yan, Zongxuan Liu, Lin Xu

Compared to the conventional Euclidean embedding in most of the previously developed models, Hyperbolic embedding can be more effective in representing the hierarchical data structure.

Contrastive Learning Image Retrieval +3

Deep Variational Luenberger-type Observer for Stochastic Video Prediction

no code implementations12 Feb 2020 Dong Wang, Feng Zhou, Zheng Yan, Guang Yao, Zongxuan Liu, Wennan Ma, Cewu Lu

Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features.

Representation Learning Video Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.