Search Results for author: Jing-Yan Wang

Found 12 papers, 0 papers with code

Low-Rank Deep Convolutional Neural Network for Multi-Task Learning

no code implementations12 Apr 2019 Fang Su, Hai-Yang Shang, Jing-Yan Wang

Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty, so that the useful features learned by the lower layers can be selected.

Multi-Task Learning

Your 2 is My 1, Your 3 is My 9: Handling Arbitrary Miscalibrations in Ratings

no code implementations13 Jun 2018 Jing-Yan Wang, Nihar B. Shah

A popular approach to address this issue is to assume simplistic models of miscalibration (such as linear biases) to de-bias the scores.

Cross-domain attribute representation based on convolutional neural network

no code implementations17 May 2018 Guohui Zhang, Gaoyuan Liang, Fang Su, Fanxin Qu, Jing-Yan Wang

We proposed to embed the attributes of dif-ferent domains by a shared convolutional neural network (CNN), learn a domain-independent CNN model to represent the information shared by dif-ferent domains by matching across domains, and a domain-specific CNN model to represent the information of each domain.

Transfer Learning

Domain transfer convolutional attribute embedding

no code implementations26 Mar 2018 Fang Su, Jing-Yan Wang

In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain.

General Classification Person Re-Identification +1

A novel image tag completion method based on convolutional neural network

no code implementations2 Mar 2017 Yanyan Geng, Guohui Zhang, Weizhi Li, Yi Gu, Ru-Ze Liang, Gaoyuan Liang, Jingbin Wang, Yanbin Wu, Nitin Patil, Jing-Yan Wang

In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN).

Image Retrieval TAG

Learning convolutional neural network to maximize Pos@Top performance measure

no code implementations27 Sep 2016 Yanyan Geng, Ru-Ze Liang, Weizhi Li, Jingbin Wang, Gaoyuan Liang, Chenhao Xu, Jing-Yan Wang

The CNN model is used to represent the multi-instance data point, and a classifier function is used to predict the label from the its CNN representation.

POS

Image tag completion by local learning

no code implementations18 Aug 2015 Jing-Yan Wang, Yihua Zhou, Haoxiang Wang, Xiaohong Yang, Feng Yang, Austin Peterson

The problem of tag completion is to learn the missing tags of an image.

TAG

Discriminative Sparse Coding on Multi-Manifold for Data Representation and Classification

no code implementations19 Aug 2012 Jing-Yan Wang

Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditional codebooks and codes to maximize the manifold margins of different classes.

General Classification

Joint-ViVo: Selecting and Weighting Visual Words Jointly for Bag-of-Features based Tissue Classification in Medical Images

no code implementations19 Aug 2012 Jing-Yan Wang

Automatically classifying the tissues types of Region of Interest (ROI) in medical imaging has been an important application in Computer-Aided Diagnosis (CAD), such as classification of breast parenchymal tissue in the mammogram, classify lung disease patterns in High-Resolution Computed Tomography (HRCT) etc.

General Classification

Adaptive Graph via Multiple Kernel Learning for Nonnegative Matrix Factorization

no code implementations19 Aug 2012 Jing-Yan Wang, Mustafa Abduljabbar

In this paper, we propose a novel idea which engages a Multiple Kernel Learning approach into refining the graph structure that reflects the factorization of the matrix and the new data space.

Information Retrieval

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