关于VIPA

浙江大学视觉智能与模式分析组（VIPA）是一个兴趣驱动的课题组，研究方向包括视觉感知增强、视觉嵌入、基于视觉的人机交互以及机器学习。

研究方向

我们实验室的研究内容主要包含四个方面：视觉感知增强、视觉嵌入、基于视觉的人机交互与机器学习。 视觉感知增强方面，我们主要针对高动态范围场景建模、颜色度量准则与管理、基于深度图像的计算机视觉等方面开展新的研究；视觉嵌入方面，我们研究物体的检测、追踪与识别，图像/视频的语义分割与标注，下一代编码/解码的生成技术；基于视觉的人机交互方面，我们志于研究人体行为与表情识别，视线估计以及机器人模仿学习；机器学习方面，我们致力于搭建知识与数据鸿沟间的桥梁，研究知识融合、自动化特征工程与图表征的新技术。

视觉感知增强

视觉嵌入

基于视觉的HCI

机器学习

公开资源

以下列出的数据和代码由VIPA成员开发或收集

数据

代码

新闻

1005月2019

论文"Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning"被IJCAI 2019收录.

1005月2019

论文"Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers"被IJCAI 2019收录.

1005月2019

论文"SPAGAN: Shortest Path Graph Attention Network"被IJCAI 2019收录.

0805月2019

论文"Edge-Sensitive Human Cutout with Hierarchical Granularity and Loopy Matting Guidance"被IEEE TRANSACTIONS ON IMAGE PROCESSING 收录.

0705月2019

论文"Interpretable Partitioned Embedding for Intelligent Multi-item Fashion Outfit Composition" 被ACM TOMM收录.

查看更多

论著

SPAGAN: Shortest Path Graph Attention Network

Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, Dacheng Tao
IJCAI 2019

Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers

Jingwen Ye, Xinchao Wang, Yixin Ji, Kairi Ou, Mingli Song
IJCAI 2019

Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning

Sihui Luo, Xinchao Wang, Gongfan Fang, Yao Hu, Dapeng Tao, Mingli Song
IJCAI 2019

Edge-Sensitive Human Cutout with Hierarchical Granularity and Loopy Matting Guidance

Jingwen Ye, Yongcheng Jing, Xinchao Wang, Kairi Ou, Dacheng Tao, Mingli Song
IEEE TRANSACTIONS ON IMAGE PROCESSING

Interpretable Partitioned Embedding for Intelligent Multi-item Fashion Outfit Composition

Zunlei Feng, Zhenyun Yu, Yongcheng Jing, Sai Wu, Mingli Song, Yezhou Yang, JunXiao Jiang
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More

Jingwen Ye, Yixin Ji, Xinchao Wang, Kairi Ou, Dapeng Tao, Mingli Song
CVPR 2019

Amalgamating Knowledge towards Comprehensive Classification

Chengchao Shen, Xinchao Wang, Jie Song, Li Sun, Mingli Song
AAAI 2019

Interpretable Partitioned Embedding for Customized Multi-item Fashion Outfit Composition

Zunlei Feng, Zhenyun Yu, Yezhou Yang, Yongcheng Jing, Junxiao Jiang, Mingli Song
ICMR 2018

Efficacy and Safety of Botulinum Toxin Type A Injection in Patients with Bilateral Trapezius Hypertrophy

R. Zhou, H. Wu, X. Zhang, L. Ye, H. Shan, X. Song, M. Song, S. Zheng
Aesthetic Plastic Surgery

Robust,Efficient Depth Reconstruction with Hierarchical Confidence-Based Matching

Li Sun, Ke Chen, Mingli Song, Dacheng Tao, Gang Chen, Chun Chen
IEEE Transactions on Image Processing

AllFocus: Patch based video out-of-focus blur reconstruction

Yinting Wang, Zhenyang Wang, Dapeng Tao, Shaojie Zhuo, Xianghua Xu, Shiliang Pu, Mingli Song
IEEE Transactions on Circuits and Systems for Video Technology

Capture-to-display delay measurement for visual communication applications

Haoming Chen, Chao Wei, Mingli Song, Ming-Ting Sun, Kevin Lau
APSIPA Transactions on Signal and Information Processing

Robust 3D Face Landmark Localization based on Local Coordinate Coding

M. Song, D. Tao, S. Sun, C. Chen and S. J. Maybank
IEEE Transactions on Image Processing (T-IP)

Discovering Discriminative Graphlets for Aerial Image Categories Recognition

L. Zhang, Y. Han, Y. Yang, M. Song, S. Yan, Q. Tian
IEEE Transactions on Image Processing (T-IP)

Three-Dimensional Face Reconstruction From a Single Image by a Coupled RBF Network

M. Song, et al.
IEEE Transactions on Image Processing (T-IP)

Feature Level Analysis for 3D Facial Expression Recognition

T. Sha, M. Song, et al.
Neurocomputing

Color to Gray: Visual Cue Preservation

M. Song, et al.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

Polar Field based Implicit Surface Reconstruction

Y. Lin, C. Chen, M. Song, et al.
Journal of CAD/CG

Bayesian Tensor Approach for 3D Face Modelling

D. Tao, M. Song, et al.
IEEE Transactions on CSVT (T-CSVT)

A Generic Framework for Efficient 2D and 3D Facial Expression Analogy

M. Song, et al.
IEEE Transactions on Multimedia (T-MM)

Painterly Rendering with Vector Field based Feature Extraction

C. Pang, M. Song, et al
ICAT2006

An Efficient Method of Face Texture Mapping Directed to Portable Devices

M. Song, et al.
IEEE Transactions on Multimedia (T-MM)

Audio-Visual based Emotion Recognition-A New Approach

M. Song, et al.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2004)

3D Realistic Talking Face Co-Driven by Text and Speech

M. Song, et al.
IEEE International Conference on Systems

Action Parsing Driven Video Summarization Based on Reinforcement Learning

 J. Lei, Q. Luan, X. Liu, D. Tao, M. Song
IEEE Transactions on Circuits and Systems for Video Technology

Scale Insensitive and Focus Driven Mobile Screen Defect Detection in Industry

 J. Lei, X. Gao, Z. Feng, H. Qiu, M. Song
Neurocomputing

Survey of Deep Neural Network Model Compression

  J. Lei, X. Gao, J. Song, X. Wang, M. Song
Journal of Software (Chinese)

A Spring-Electric Graph Model for Socialized Group Photography

Y. S. Rawat, M. Song, M. S. Kankanhali
IEEE Transactions on Multimedia

Dual Swap Disentangling

Z. Feng, X. Wang, C. Ke, A. Zeng, D. Tao, M. Song
NIPS 2018

Intra-class structure aware networks for screen defect detection

C. Shen, J. Song, S. Song, L. Sun, S. Luo, M. Song
ICONIP 2018

DeepSIC: Deep Semantic Image Compression    

S. Luo, Y. Yang, Y. Yin, C. Shen, Y. Zhao, M. Song
ICONIP 2018

Stroke Controllable Fast Style Transfer with Adaptive Receptive Field

Y. Jing, Y. Liu, Y. Yang, Z. Feng, Y. Yu, D. Tao, M. Song
ECCV 2018

Selective Zero-Shot Classification with Augmented Attribute

J. Song, C. Shen, J. Lei, A.-X. Zeng, K. Ou, D. Tao, M. Song
ECCV 2018

Understanding the prediction process of Deep Networks by Forests

J. Lei, Z. Wang, Z. Feng, M. Song, J. Bu
IEEE International Conference on Multimedia Big Data

DEEPSSH: Deep Semantic Structured Hashing for Explainable Person Re-Identification

Y. Zhao, S. Luo, Y. Yang, M. Song
IEEE International Conference on Image Processing

Transductive Unbiased Embedding for Zero-Shot Learning

J. Song, C. Shen, Y. Yang, Y. Liu, M. Song
CVPR 2018

Finer-Net: Cascaded Human Parsing with Hierarchical Granularity

J. Ye, Y. Jing, J. Lei, Z. Feng, M. Song
ICME 2018

Towards Deeper Insights into Deep Learning from Imbalanced Data

J. Song, Y. Shen, Y. Jing, M. Song
CCCV 2017

Action Parsing Driven Video Summarization based on Reinforcement Learning

J. Lei, Q. Luan, X. Song, X. Liu, M. Song
ChinaMM 2017

Graph-based color gamut mapping using neighbor metric

Zunlei Feng, Jie Lei, Yongcheng Jing, Mingli Song, et al.
International Conference on Multimedia and Expo 2017

Algorithm-Dependent Generalization Bounds for Multi-Task Learning

Tongliang Liu, Dacheng Tao, Stephen Maybank, Mingli Song
IEEE Transactions on Pattern Analysis and Machine Intelligence

Event-based Large Scale Surveillance Video Summarization

X. Song, L. Sun, J. Lei, G. Yuan, M. Song
Neurocomputing

Manifold Ranking-Based Matrix Factorization for Saliency Detection

D. Tao, J. Cheng, M. Song, X. Lin
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

Coupled Dictionary Learning for the Detail-Enhanced Synthesis of 3-D Facial Expressions

H. Liang, R. Liang, M. Song, X. He
IEEE Transactions on Cybernetics (T-CYB)

DeepChart: Combining deep convolutional networks and deep belief networks in chart classification

Binbin Tang, Xiao Liu, Jie Lei, Mingli Song Dapeng Tao, Shuifa Sun, Fangmin Dong
Signal Processing

WHICH FACE IS MORE ATTRACTIVE?

Jie Lei, Zunlei Feng, Mingli Song, Dacheng Tao
ICIP 2016

Category Driven Deep Recurrent Neural Network For Video Summarization

Xinhui Song, Mingli Song, Ke Chen, Li Sun, Jie Lei
ICME 2016 Workshops

Learning deep classifiers with deep features

Jie Lei, Xinhui Song, Li Sun, Mingli Song, Na Li, Chun Chen
ICME 2016

Algorithm-Dependent Generalization Bounds for Multi-Task Learning

Tongliang Liu, Dacheng Tao, Stephen Maybank, Mingli Song
IEEE Transactions on Pattern Analysis and Machine Intelligence

Random Shape Prior Forest For Multi-Class Object Segmentation

X. Liu, M. Song, et al.
IEEE Transactions on Image Processing (T-IP)

Where2Stand: A Human Position Recommendation System for Souvenir Photography

Y. Wang, M. Song, et al.
ACM Transactions on Intelligent System and Technology (TIST)

Multi-Task Proximal Support Vector Machine

Ya Li, Xinmei Tian, Mingli Song, Dacheng Tao
Pattern Recognition (PR)

MEMS scanning micromirror for optical coherence tomography

M. Strathman, Y. Liu, E. G. Keeler, M. Song, U. Baran, J. Xi, M.-T. Sun, R. Wang, X. Li and L. Y. Lin
Biomedical Optical Express

Random Forest Construction with Robust Semi-supervised Node Splitting

X. Liu, M. Song, et al.
IEEE Transactions on Image Processing (T-IP)

Whole-Body Humanoid Robot Imitation with Pose Similarity Evaluation

J. Lei, M. Song, et al.
Signal Processing

Learning to Track Multiple Targets

X. Liu, D. Tao, M. Song, et al.
IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

Chart Classification by Combining Deep Convolutional Networks and Deep Belief Networks

X. Liu, B. Tang, Z. Wang, X. Xu, S. Pu, D. Tao, M. Song
ICDAR 2015

Video Tonal Stabilization Color States Smoothing

Y. Wang, D. Tao, M. Song, et al.
IEEE Transactions on Image Processing (T-IP)

Real-Time Gaze Estimation with Online Calibration

L. Sun, M. Song, Z. Liu, M.-T. Sun
IEEE Multimedia

Low-Level and High-Level Prior Learning for Visual Saliency Estimation

M. Song, C. Chen, S. Wang, Y. Yang
Information Sciences (INS)

Weakly supervised photo cropping,

L. Zhang, M. Song, Y. Yang, Q. Zhao, X. Liu, C. Zhao, and N. Sebe
IEEE Transactions on Multimedia (T-MM)

Recognizing architecture styles by hierarchical sparse coding of blocklets

L. Zhang, M. Song, X. Liu, L. Sun, C. Chen, J. Bu
Information Sciences (INS)

Motionlet LLC Coding for Discriminative Human Pose Estimation

L. Sun, M. Song, C. Chen, D. Tao, J. Bu, C. Chen
Multimedia Tools and Applications

Realtime Gaze Estimation with Online Calibration

L. Sun, M. Song, Z. Liu, M. Sun
ICME 2014

Video Summarization Based on Nonnegative Linear Reconstruction

Q. Luan, M. Song, C. Chen, et al.
ICME 2014

Nearest Neighbor-based Label Transfer for Weakly Supervised Multiclass Video Segmentation

X. Liu, D. Tao, M. Song, J. Bu, and C. Chen
CVPR 2014

Semi-Supervised Coupled Dictionary Learning for Person Re-identification

X. Liu, M. Song, D. Tao, J. Bu and C. Chen
CVPR 2014

Colorization for Gray Scale Facial Image by Locality-Constrained Linear Coding

Y. Liang, M. Song, et al.
Journal of Signal Processing System

Color-to-Gray based on Chance of Happening Preservation

M. Song, D. Tao, J. Bu, C. Chen, Y. Yang
Neurocomputing

Joint Sparse Learning for 3-D Facial Expression Generation

M. Song, D. Tao, S. Sun, C. Chen, J. Bu
IEEE Transactions on Image Processing (T-IP)

Grassmann Multimodal Implicit Feature Selection Multimedia Systems

L. Zhang, D. Tao, X. Liu, M. Song, C. Chen
Multimedia System Journal

Morphological Quantitative Criteria and Aesthetic Evaluation of Eight Female Han Face Types

Q. Zhao, R. Zhou, X. Zhang, H. Sun, X. Lu, D. Xia, M. Song
Aesthetic Plastic Surgery

Probabilistic Graphlet Transfer for Photo Cropping

L. Zhang, M. Song, et al
IEEE Transactions on Image Processing (T-IP)

Fast Multi-view Segment Graph Kernel for Object Classification

L. Zhang, M. Song, et al.
Signal Processing

A Capture-to-Display Delay Measurement System for Visual Communication Applications

C. Wei, H. Chen, M. Song, M.-T. Sun
APSIPA 2013

Personalized 3-D Facial Expression Synthesis based on Landmark Constrain

H. Liang, M. Song, R. Liang
APSIPA 2013

Probabilistic Graphlet Cut: Exploring Spatial Structure Cue for Weakly Supervised Image Segmentation

L. Zhang, M. Song, Z. Liu, X. Liu, J. Bu, C. Chen
CVPR 2013

Semi-supervised Node Splitting for Random Forest Construction

X. Liu, M. Song, D. Tao, Z. Liu, L. Zhang, J. Bu, C. Chen
CVPR 2013

LF-EME: Local Features with Elastic Manifold Embedding for Human Action Recognition

X. Deng, X. Liu, M. Song, et al.
Neurocomputing

Attribute-Restricted Latent Topic Model for Human Identity Recognition in Sparse Camera Network

X. Liu, M. Song, et al.
Pattern Recognition (PR)

Video-based non-uniform object motion blur estimation and deblurring

X. Deng, Y. Shen, M. Song, et al.
Neurocomputing

Image-based sketch-to-photo synthesis via online coupled dictionary learning

M. Song, et al.
Information Sciences (INS)

Probabilistic Exposure Fusion

M. Song, et al.
IEEE Transactions on Image Processing (T-IP)

Sparse Coding for Flexible and Robust 3D Facial Expression Synthesis

Y. Lin, M. Song, et al.
IEEE Computer Graphics and Applications

Graph based transductive learning for cartoon correspondence construction

J. Yu, W. Bian, M. Song, et al.
Neurocomputing

Learning High-Level Concepts by Training A Deep Network on Eye Fixations

C. Shen, M. Song, Q. Zhao
Deep Learning and Unsupervised Feature Learning NIPS Workshop

Face Sketch-to-Photo Synthesis from Simple Line Drawing

Y. Liang, M. Song, et al
Asia Pacific Signal and Information Processing Association (APSIPA)

Colorization for Gray Scale Facial Image by Locality-constrained Linear Coding

Y. Liang, M. Song, et al
Pacific Rim Conference on Multimedia (PCM2012)

Pose Estimation with Motionlet LLC Coding

L. Sun, M. Song, et al.
Pacific Rim Conference on Multimedia (PCM2012)

Learning Visual Saliency based on Object's Relative Relationship

S. Wang, Q. Zhao, M. Song
Neural Information Processing (ICONIP2012)

Joint Shot Boundary Detection and Key Frame Extraction

X. Liu, M. Song
International Conference on Pattern Recognition (ICPR2012)

Spatial Graphlet Matching Kernel for Recognizing Aerial Image Categories

L. Zhang, M. Song, et al.
International Conference on Pattern Recognition (ICPR2012)

Realtime Object Matching with Robust Dominant Orientation Templates

C. Hong, J. Zhu, M. Song, et al.
International Conference on Pattern Recognition (ICPR2012)

Detecting Discontinuities for Surface Reconstruction

Y. Wang, J. Bu, N. Li, M. Song, et al.
International Conference on Pattern Recognition (ICPR2012)

An efficient approach to content-based object retrieval in videos

C. Hong, N. Li, M. Song, et al.
Neurocomputing

Natural Grayscale Image Colorization via Local Sparse Coding

K. Hao, M. Song, et al.
Journal of CAD/CG

3D Facial Expression Synthesis based on Nonlinear Co-learning

X. Huang, Y. Lin, M. Song, et al.
Journal of CAD/CG

Real-time Speech-driven Animation of Expressive Talking Faces

J. Liu, M. You, C. Chen, M. Song
International Journal of General System

Automatic Image Cropping using Sparse Coding

J. She, D. Wang, M. Song
First Asian Conference on Pattern Recognition(ACPR2011)

Large-scale Outdoor Scene Classification by Boosting a Set of Highly Discriminative and Low Redundant Graphlets

L. Zhang, M. Song, et al.
ICDM Workshops

Opponent and Feedback: Visual Attention Captured

S. Wang, M. Song, et al.
Neural Information Processing (ICONIP2011)

Describing Human Identity using Attributes

Z. Zhou, J. Bu, L. Zhang, M. Song, et al.
Neural Information Processing (ICONIP2011)

Integrating Local Features into Discriminative Graphlets for Scence Classification

L. Zhang, W. Bian, M. Song, et al.
Neural Information Processing (ICONIP 2011)

Feature Relationships Hypergraph for Multimodal Recognition

L. Zhang, M. Song, et al.
Neural Information Processing (ICONIP 2011)

Fast Multi-view Graph Kernels for Object Classifcation

L. Zhang, M. Song
Australasian Conference on Artificial Intelligence (AI 2011)

kPose: a new representation for action recognition

Z. Zhou, M. Song, et al.
Asian Conference on Computer Vision (ACCV 2011)

Image Ratio Features for Facial Expression Recognition Application

M. Song, et al.
IEEE Transactions on System

Visual Context Boosting for Eye Detection

M. Song, et al.
Journal of CAD/CG

Random Project Tree and Multiview Embedding for Large-scale Image Retrieval

B. Xie, M. Song, et al.
International Conference on Neural Information Processing (ICONIP2010)

Color to Gray: Attention Preservation

Y. Yang, M. Song et al.
Pacific-Rim Symposium on Image and Video Technology (PSIVT2010)

A Level-set based Tracking Approach for Surveillance Video with Fusion and Occlusion

C. Hong, N. Li, M. Song, et al.
Pacific-Rim Symposium on Image and Video Technology(PSIVT2010)

Large-scale Dictionary Learning for Local Coordinate Coding

B. Xie, M. Song, et al.
British Machine Vision Conference (BMVC2010)

Face Aging by Sparse Representation

H. Huang, Y. Lin, M. Song, et al.
Pacific Rim Conference on Multimedia(PCM2010)

What is the Chance of Happening: A New Way to Predict Where People Look

Y. Yang, M. Song, et al.
European Conference on Computer Vision (ECCV2010)

Dual-RBF based Surface Reconstruction

Y. Lin, C. Chen, M. Song, et al.
The Visual Computer

Tone Mapping for HDR Image using a Probabilistic Model

M. Song, et al.
Journal of Software

Feature Selection for Accelerating Speech based Emotion Recognition

L. Zhang, M. Song, et al.
ACM Multimedia(MM2009)

Visual Attention Analysis using Classic Theory of Gravitational Field

Y. Yang, M. Song, et al.
ACM Multimedia(MM2009)

Viewpoint Independent Vehicle Speed Estimation from Uncalibrated Traffic Surveillance Cameras, International Conference on System

H. Mao, C. Ye, M. Song, et al.
Man & Cybernetics (SMC2009)

Implicit Surface Reconstruction with An Analogy of Polar Field Model

Y. Lin, C. Chen, M. Song, et al.
Pacific-Rim Symposium on Image and Video Technology 2009 (PSIVT2009)

Avatar Motion Control by Natural Body Movement Via Camera

N. Li, C. Chen, Q. Wang, M. Song
Neurocomputing

Gaussian mixture model based approach on color transfer

M. Song, et al.
Journal of CAD/CG

A robust multimodal approach for emotion recognition

M. Song, et al.
Neurocomputing

Local Laplacian for Face Detail Transfer

M. Song, et al.
Journal of CAD/CG

Speech emotion classification on a Riemannian manifold

C. Ye, J. Liu, C. Chen, M. Song, et al.
Pacific Rim Conference on Multimedia (PCM2008)

EigenExpress Approach in Recognition of Facial Expression using GPU

Q. Wu, M. Song, et al.
ECCV 2006 workshop on Human-Computer Interaction, Lecture Notes in Computer Science

Multiple-Reference-Frame Based Fast Motion Estimation & Mode Decision for H

J. Bu, L. Mo, C. Chen, Z. Yang, M. Song
ICIP06

Subtle Facial Expression Modeling with Vector Field Decomposition

M. Song, et al.
IEEE International Conference on Image Processing (ICIP06)

Real-Time Facial Expression Mapping for High Resolution 3D Meshes

M. Song, et al.
Computer Graphics International (CGI 2006), Lecture Notes in Computer Science

Sketch based Facial Expression Recognition using Graphics Hardware

J. Bu, M. Song, et al.
ACII05

成员

教授

宋明黎
教授

博士后

孙立
博士后
雷杰
博士后

博士研究生

冯尊磊
博士生
罗思慧
博士生
宋杰
博士生
沈成超
博士生
叶静雯
博士生
赵雅
博士生
郑铜亚
博士生
余娜
博士生
郝韵致
博士生

硕士研究生

静永程
硕士生
沈赟
硕士生
张永航
硕士生
潘妍
硕士生
汪哲
硕士生
许睿
硕士生
薛梦琦
硕士生
王海阳
硕士生
谢帅
硕士生
潘文雯
硕士生
尹艳玲
硕士生

本科生

陈毅
本科生
戴麒斌
本科生
方共凡
本科生
何永明
本科生
季意昕
本科生
刘顺宇
本科生
张哲铖
本科生
应昊键
本科生
刘静林
本科生
毛文森
本科生
萧芷晴
本科生
张习远
本科生
符畅
本科生

联系我们

地址

浙江省杭州市西湖区浙大路38号

浙江大学玉泉校区

曹光彪西楼404室

视觉智能和模式识别实验室