activity
20142019
most citedTruncated Cauchy Non-negative Matrix Factorization

110 citations · 113 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG2019★ 110 cited

Truncated Cauchy Non-negative Matrix Factorization

Naiyang Guan, Tongliang Liu, Yangmuzi Zhang +2

Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because…

cs.CV2016

Generating Discriminative Object Proposals via Submodular Ranking

Yangmuzi Zhang, Zhuolin Jiang, Xi Chen +1

A multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical se…

cs.CV2016★ 2 cited

Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics

Xiyang Dai, Sameh Khamis, Yangmuzi Zhang +1

Sparse representations have been successfully applied to signal processing, computer vision and machine learning. Currently there is a trend to learn sparse models directly on stru…

cs.CV2015

Layer-Specific Adaptive Learning Rates for Deep Networks

Bharat Singh, Soham De, Yangmuzi Zhang +2

The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in…

cs.CV2014★ 1 cited

What makes an Image Iconic? A Fine-Grained Case Study

Yangmuzi Zhang, Diane Larlus, Florent Perronnin

A natural approach to teaching a visual concept, e.g. a bird species, is to show relevant images. However, not all relevant images represent a concept equally well. In other words,…