Publications (75)
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
Xuqian Xue, Yiming Lei, Qi Cai +2
While contrastive multi-view clustering has achieved remarkable success, it implicitly assumes balanced class distribution. However, real-world multi-view data primarily exhibits c…
Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
Jiaqi Gao, Zhizhong Huang, Yiming Lei +4
Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a la…
LICO: Explainable Models with Language-Image Consistency
Yiming Lei, Zilong Li, Yangyang Li +2
Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is sa…
Hard instance learning for quantum adiabatic prime factorization
Jian Lin, Zhengfeng Zhang, Junping Zhang +1
Prime factorization is a difficult problem with classical computing, whose exponential hardness is the foundation of Rivest-Shamir-Adleman (RSA) cryptography. With programmable qua…
Learning Representation for Clustering via Prototype Scattering and Positive Sampling
Zhizhong Huang, Jie Chen, Junping Zhang +1
Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative…
Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms
Xianye Ben, Yi Ren, Junping Zhang +4
Unlike the conventional facial expressions, micro-expressions are involuntary and transient facial expressions capable of revealing the genuine emotions that people attempt to hide…