2017-03-08

CFP: IEEE International Conference on Systems, Man, and Cybernetics Special Session on Machine Learning for Vision and Healthcare


Call for Papers

IEEE International Conference on Systems, Man, and Cybernetics

Special Session on Machine Learning for Vision and Healthcare

 

The emergence of visual data, machine learning algorithms, and advancement in hardware has enabled significant breakthrough in vision and healthcare applications.

 

This special issue focuses on new data, machine learning methods, and applications in computer vision and related healthcare problems. The goal of the special issue is the identification of new and exciting problems and applications that leverage the current data and model advancement. It also aims at the development of new data and machine learning methods that address specific problems in vision and healthcare domains.

 

Manuscripts are solicited to address a wide range of topics in data, models, and applications, including but not limited to the following: data collection, data sharing, crowdsourcing, machine learning, deep neural networks, visualization, visual quality assessment, image and video coding, saliency detection, object detection, object and scene recognition, and understanding of human vision and assistive tools for visual and developmental disorders.

 

Perspective authors should follow the instructions given on the IEEE SMC webpages: http://www.smc2017.org/?q=authors, and submit their manuscripts with the submission system at: https://conf.papercept.net/conferences/scripts/start.pl.

 

Important Dates:

April 7, 2017: Manuscript submission

May 25, 2017: Acceptance notification

July 9, 2017: Camera-ready papers due

August 5, 2017: Deadline for early registration

October 5-8: Conference dates

 

Organizers:

Catherine Qi Zhao (qzhao@cs.umn.edu), University of Minnesota

Weifeng Liu (liuwf@upc.edu.cn), China University of Petroleum

Yicong Zhou (yicongzhou@umac.mo), University of Macau

Sunjun Li (shujun.li@surrey.ac.uk), University of Surrey

 

2016-07-12

“p-Laplacian Regularized Sparse Coding for Human Activity Recognition” is formally published.

p-Laplacian Regularized Sparse Coding for Human Activity Recognition

Weifeng Liu 
College of Information and Control Engineering, China University of Petroleum (East China), Qingdao, China 
Zheng-Jun Zha ; Yanjiang Wang ; Ke Lu ; Dacheng Tao

Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called $p$-Laplacian regularized sparse coding (pLSC). The proposed method exploits $p$ -Laplacian regularization to preserve the local geometry. The $p$ -Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper $p$. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper $p$.

2016-04-11

One paper is online on Neurocomputing. Con~ to Hongli!

Hessian Regularization by Patch Alignment Framework

Abstract
In recent years, semi-supervised learning has played a key part in large-scale image management, where usually only a few images are labeled. To address this problem, many representative works have been reported, including transductive SVM, universum SVM, co-training and graph-based methods. The prominent method is the patch alignment framework, which unifies the traditional spectral analysis methods. In this paper, we propose Hessian regression based on the patch alignment framework. In particular, we construct a Hessian using the patch alignment framework and apply it to regression problems. To the best of our knowledge, there is no report on Hessian construction from the patch alignment viewpoint. Compared with the traditional Laplacian regularization, Hessian can better match the data and then leverage the performance. To validate the effectiveness of the proposed method, we conduct human face recognition experiments on a celebrity face dataset. The experimental results demonstrate the superiority of the proposed solution in human face classification.

Keywords
Semi-supervised learning; Hessian; Patch alignment; Least Squares

doi:10.1016/j.neucom.2015.07.152