Search Results for author: Zhen Zuo

Found 7 papers, 0 papers with code

Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association

no code implementations15 May 2016 Bing Wang, Li Wang, Bing Shuai, Zhen Zuo, Ting Liu, Kap Luk Chan, Gang Wang

Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.

Multi-Object Tracking Multi-Task Learning

Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks

no code implementations13 Sep 2015 Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, Bing Wang

In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).

General Classification Image Classification

DAG-Recurrent Neural Networks For Scene Labeling

no code implementations CVPR 2016 Bing Shuai, Zhen Zuo, Gang Wang, Bing Wang

In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded.

General Classification Scene Labeling +1

Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification

no code implementations21 Aug 2015 Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL).

General Classification Image Classification

Integrating Parametric and Non-Parametric Models For Scene Labeling

no code implementations CVPR 2015 Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, Lifan Zhao

We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification.

Benchmark General Classification +2

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