左旺孟 中国
计算机视觉、机器学习
教授||博士生导师
目前就职计算机科学与技术学院
所在学科 计算机科学与技术
永久地址 http://homepage.hit.edu.cn/wangmengzuo

基本信息

   左旺孟,男,汉族,1977年生。哈尔滨工业大学计算机学院教师,主要从事计算机视觉、机器学习与生物特征识别等方面的研究

我的新闻

CFP: Neurocomputing Special Issue on Smart Computing for Large Scale Visual Data Sensing and Processing
发布时间:2015-01-03
简单介绍:

We organized a Neurocomputing Special Issue on Smart Computing for Large Scale Visual Data Sensing and Processing: 

Papers can be submitted via the online submission system for Neurocomputing (http://ees.elsevier.com/neucom/). Preparation of the manuscript must follow the Guide for Authors which is available there.

Important Dates
    Submission Deadline: Jan. 31, 2015
    First Round Decisions: Mar. 31, 2015
    Revisions Deadline: Apr. 30, 2015
    Final Round Decisions: Jun. 30, 2015
    Expected Online Publication: Sep. 2015

For more info, please visit:

http://www.journals.elsevier.com/neurocomputing/call-for-papers/special-issue-on-smart-computing-for-large-scale-visual-data/

 

 

 

 

 

 

Zhihua's paper was accepted by Information Sciences
发布时间:2014-09-05
简单介绍:

Zhihua Chen, Wangmeng Zuo*, Qinghua Hu. Kernel Sparse Representation for Time Series Classification, Information Sciences, 2014 (Accept). (Extention of KSVD and LC-KSVD to kernelized versions and applications to time series classification)

Shuhang's paper was accepted by NIPS 2014
发布时间:2014-09-17
简单介绍:

Shuhang Gu, Lei Zhang, Wangmeng Zuo, and Xiangchu Feng, “Projective Dictionary Pair Learning for Pattern Classification,” In NIPS 2014. (One of the most efficient method for both training and testing.)

Faqiang's Paper was accepted by IEEE T-NNLS
发布时间:2014-09-30
简单介绍:

Faqiang Wang, Wangmeng Zuo, Lei Zhang, Deyu Meng, and David Zhang, A Kernel Classification Framework for Metric Learning, IEEE Trans. Neural Networks and Learning Systems, 2014. (Kernel perspective and formulation can provide a number efficient algorithms on metric learning.)

Zhaoxin's paper was accepted by Image and Vision Computing
发布时间:2014-11-16
简单介绍:

Zhaoxin Li, Kuanquan Wang, Wenyan Jia, Hsin-Chen Chen, Wangmeng Zuo, Deyu Meng , Mingui Sun, Multiview Stereo and Silhouette Fusion via Minimizing Generalized Reprojection Error, Image and Vision Computing, 2014 (Our first paper on multiview stero. We proposed a two-phase optimization method for generalized reprojection error minimization. In terms of accuracy and completeness, our TwGREM achieves high rank on the Middlebury evaluation page for dino sparse and temple sparse.)

 

Peng's paper was accepted by IEEE JBHI
发布时间:2014-11-17
简单介绍:

Wangmeng Zuo, Peng Wang, David Zhang. Comparison of three different types of wrist pulse signals by their physical meanings and diagnosis performance, IEEE Journal of Biomedical and Health Informatics, 2014 (Accept). (A comprehensive analysis and comparative study on three major types of wrist pulse signals.)

CFP: Pattern Recognition Special Issue on Compositional Models and Structured Learning for Visual Recognition
发布时间:2015-01-17
简单介绍:

Webpage

In the last ten years, computer vision and pattern recognition has experienced a resurgence of research on compositional and hierarchical models, such as And-Or graphs, deformable part-based models, kernelized and latent variable models. The virtue of compositional and hierarchical models (CHMs) lies in their expressive power to model diverse and complex visual patterns. Meanwhile, a set of structured learning and optimization methods are intensively discussed to facilitate training and inference with compositional models, which usually integrate latent structures to specify the task-specific compositional configurations and contextual relations. These methods, such as latent support vector machines, conditional random fields, and structural sparse coding, enable inference with rich internal structures and pursue a good mapping between observations and output structured predictions. Compared with the neural networks, which have also attracted much attention recently, CHMs and structured learning methods provide alternative approaches to explicitly handle the variations of data with latent variables, and demonstrate their potential in several high-level vision tasks, e.g., object detection and recognition, scene parsing, and action/activity understanding.

In order to pursue first-class research along this direction, we would like to organize a special issue titled "Compositional Model and Structured Learning for Visual Recognition" in the journal of Pattern Recognition.

The issue will be aimed at accepting papers on the following topics but not limited to:

  1. Object recognition and detection by learning and inference with compositional and hierarchical models. The proposed approaches are encouraged to evaluate on several public benchmarks in computer vision such as PASCAL VOC, ImageNet, Caltech101, and Caltech256.
  2. Image segmentation and labeling with supervised or unsupervised learning methods, which incorporate multiple contextual object models. Some exemplar benchmarks are LabelMe, PASCAL VOC, Fashionista‍, and SUN databases.
  3. Understanding human actions or activities from videos with spatio-temporal models. The new models will show good performance on capturing well large category variations that is one key challenge in complex action/activity modeling. By using depth sensors, more rich information can be utilized for these tasks.
  4. Models, algorithms, and applications of sparse representation and dictionary learning. The proposed approaches are expected to improve the efficiency and effectiveness of the classification performance, and provide new insight for modeling structure and dependencies between vocabularies.
  5. New applications and systems address real challenges in the intelligent processing and understanding of visual data (e.g. fashion understanding, medical image recognition, graphics, etc).‍

The main timelines for this issue are set as follows,

  • Paper submission due: July. 30, 2015
  • First notification: Nov. 30, 2015
  • Revision: Jan. 15, 2016
  • Final decision: Feb. 30, 2016

Submission Details:

All submissions for this special issue are required to follow the same format as regular full-length Pattern Recognition papers. The submission website for this special issue is located at: http://ees.elsevier.com/pr/. Please ensure to select 'SI : CHM-Vision' as the 'Article Type'.

Guest Editors:

Professor Liang Lin
Sun Yat-Sen University
linliang@ieee.org

Associate Professor Jason Corso
University of Michigan
jcorso@buffalo.edu

Associate Professor Wangmeng Zuo
Harbin Institute of Technology
wmzuo@hit.edu.cn

Chair Professor David Zhang
The Hong Kong Polytechnic University
csdzhang@comp.polyu.edu.hk

Dr Benjamin Yao
Amazon.com
benjamy@amazon.com

Two papers were accepted by CVPR 2015.
发布时间:2015-03-30
简单介绍:

[1] Wangmeng Zuo, Dongwei Ren, Shuhang Gu, Liang Lin, Lei Zhang,  Discriminative Learning of Iteration-wise Priors for Blind Deconvolution, CVPR 2015.

[2] Chenglong Li, Liang Lin, Wangmeng Zuo, Jin Tang, Shuicheng Yan, SOLD: Sub-Optimal Low-Rank Decomposition for Efficient Video Segmentation, CVPR 2015.
 
维智、陈丽、长春、保全硕士顺利毕业
发布时间:2015-07-13
简单介绍:

恭喜陈丽获得校优秀硕士论文金奖。

潘峰、予康、晓宇、李穆、守峰、勇飞、马良、金智顺利通过本科毕设答辩
发布时间:2015-07-13
简单介绍:

恭喜潘峰、予康、晓宇、李穆、守峰、勇飞、马良、金智8位同学通过本科毕设答辩。

恭喜潘峰同学获得2015届校百优本科毕业设计(论文)。

Two papers were accepted by ICCV 2015
发布时间:2015-09-10
简单介绍:
272: Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising
1383: Convolutional Sparse Coding for Image Super-resolution
 
Congratulations to Shuhang and Jun!
Kai's super-resolution paper was accepted by IEEE SPL
发布时间:2015-11-23
简单介绍:

Kai Zhang, Baoquan Wang, Wangmeng Zuo*, Hongzhi Zhang, Lei Zhang, Joint Learning of Multiple Regressors for Single Image Super-Resolution, IEEE Signal Processing Letters, 2015 (An efficient and effective approach for single image super-resolution by joint learning of partitions and regressors ).

 

Congratulation to Kai!

Zhaoxin's MVS paper was accepted by IEEE TIP
发布时间:2015-12-03
简单介绍:

Zhaoxin Li, Kuanquan Wang, Wangmeng Zuo, Deyu Meng, Lei Zhang. Detail-preserving and Content-aware Variational multi-view stereo reconstruction. IEEE Trans. Image Processing, 2016 (best results among all published methods on the Middlebury dino ring and dino sparse datasets).

荣誉称号

2008年 哈尔滨工业大学优秀博士学位论文

2009年 教育部全国百篇优秀博士学位论文提名奖

2012年 教育部新世纪优秀人才
 


 

工作经历

时间 工作经历
2007.8 - 2010.10 讲师
2010.10 - 副教授
2013.4 - 博导
2015.12 教授

 

教育经历

  1. 1995年-1999年,哈尔滨工业大学 材料科学系,学士
  2. 1999年-2001年,哈尔滨工业大学 材料学专业,硕士
  3. 2001年-2007年,哈尔滨工业大学 计算机应用技术专业,博士

主要任职

IET Biometrics Associate Editor


   
VALSE在线理事会 理事
中国计算机学会(CCF) 高级会员
IEEE & IEEE CS Senior Member

 

Copyright © 2016 哈尔滨工业大学网络与信息中心