wfeng@tju.edu.cn
新世纪优秀人才
教授
通用随机场模型与应用研究

---

非监督式的中文新闻主题协同分割技术研究

---

敦煌莫高窟风险监测与评估关键技术研究

---

基于表观形貌特征的古代壁画典型病害微小变化监测技术

---

无障碍语言交流系统总体设计与关键技术攻关

---

基于视频分割的实时环境光序列采样的研究

---

图像分割与新闻故事分割中的类别自确定方法研究

---

基于图像内容的单体群体行为检测研究

---

基于自相似随机场模型的通用图像分割方法研究
一种自适应音频感知强度调整方法

---

利用离散立方体全景图实时合成连续平滑全景视频的方法

---

一种具有尺度无关特性的快速多模态图像协同分割方法

---

一种基于概率图模型的中文新闻主题协同分割方法

---

一种用于优化图像处理与视觉算法中控制参数的方法

---

一种基于结构的图节点相似度并行计算方法

---

一种表示超像素以及度量超像素之间相似性的方法

---

一种内容感知的环境光采样方法

---

最大粘聚性的超像素网格的快速目标检测与分割方法

---

一种基于柔性语义相似性度量的中文新闻故事分割方法

---

一种数据驱动的中文词语义相似度计算方法

---

面向文物亚微米级变化检测的相机三点重定位方法

---

面向文物微小变化检测的相机四点重定位方法

---

一种协同本征图像分解方法

---

基于多尺度L0稀疏约束的本征图像分解方法

---

一种单幅图像螺旋对称中心快速检测方法

---

基于匹配特征三元组的单幅图像螺旋对称结构检测方法

---

一种基于全局字典特征的古代壁画病害标识方法

---

一种交互式古代壁画病害标识方法

---

最大粘聚超像素网格化方法与超像素级图像处理方法

---

基于自适应的自回归模型的高光谱图像超分辨率方法

---

一种基于融合的图像超像素网格化方法

---

一种基于相似性传播的多目标协同显著区域检测方法

---

一种基于融合的图像超像素网格化方法

---

利用离散立方体全景图实时合成连续平滑全景视频的方法
一种自适应音频感知强度调整方法

---

利用离散立方体全景图实时合成连续平滑全景视频的方法

---

一种具有尺度无关特性的快速多模态图像协同分割方法

---

一种基于概率图模型的中文新闻主题协同分割方法

---

一种用于优化图像处理与视觉算法中控制参数的方法

---

一种基于结构的图节点相似度并行计算方法

---

一种表示超像素以及度量超像素之间相似性的方法

---

一种内容感知的环境光采样方法

---

最大粘聚性的超像素网格的快速目标检测与分割方法

---

一种基于柔性语义相似性度量的中文新闻故事分割方法

---

一种数据驱动的中文词语义相似度计算方法

---

面向文物亚微米级变化检测的相机三点重定位方法

---

面向文物微小变化检测的相机四点重定位方法

---

一种协同本征图像分解方法

---

基于多尺度L0稀疏约束的本征图像分解方法

---

一种单幅图像螺旋对称中心快速检测方法

---

基于匹配特征三元组的单幅图像螺旋对称结构检测方法

---

一种基于全局字典特征的古代壁画病害标识方法

---

一种交互式古代壁画病害标识方法

---

最大粘聚超像素网格化方法与超像素级图像处理方法

---

基于自适应的自回归模型的高光谱图像超分辨率方法

---

一种基于融合的图像超像素网格化方法

---

一种基于相似性传播的多目标协同显著区域检测方法

---

一种基于融合的图像超像素网格化方法

---

利用离散立方体全景图实时合成连续平滑全景视频的方法
L0 co-intrinsic images decom- position

---

Contrast enhancement based single image dehaz- ing via TV-L1 minimization

---

Maximum cohesive grid of superpixels for fast object localization

---

Image co-saliency detection by propagating superpixel affinities

---

Measuring semantic similarity by contextual word connections in Chinese news story segmentation

---

lexical story cosegmentation of Chinese broadcast news

---

Scalable image co-segmentation using color and covariance Features

---

Image co-saliency detection by propagating superpixel affinities

---

Maximum cohesive grid of superpixels for fast object localization

---

Feature selection based saliency object detection

---

Bag of squares: a reliable model of measuring superpixel similarity

---

Minimizing Sparse Higher Order Energy Functions of Discrete Variables

---

A tighter lower bound estimate for dynamic time warping,

---

Intrinsic image decomposition by hierarchical L0 sparsity

---

vtGraphNet: Learning Weakly-Supervised Scene Graph for Complex Visual Grounding

---

Exemplar-based Image Saliency and Co-saliency Detection

---

Fast Learning of Spatially Regularized and Content Aware Correlation Filter for Visual Tracking

---

Dynamic Saliency-Aware Regularization for Correlation Filter-Based Object Tracking

---

Selective Spatial Regularization by Reinforcement Learned Decision Making for Object Tracking

---

Active Camera Relocalization from a Single Reference Image without Hand-Eye Calibration

---

Story Co-Segmentation of Chinese Broadcast News Using Weakly-Supervised Semantic Similarity

---

Unsupervised Measure of Chinese Lexical Semantic Similarity Using Correlated Graph Model for News Story Segmentation

---

Color feature reinforcement for co-saliency detection without single saliency residuals

---

Tone-mapped mean-shift based environment map sampling

---

Topic segmentation on spoken documents using self-validated acoustic cuts

---

Layered modeling and generation of Pollock's drip style

---

SPHORB: A fast and robust binary feature on the sphere

---

Topic segmentation on spoken documents using self-validated acoustic cuts

---

NestDE: Generic parameters tuning for automatic story segmentation

---

NestDE: Generic parameters tuning for automatic story segmentation

---

Self-Adaptively Weighted Co-Saliency Detection via Rank Constraint

---

Spiral symmetry centroid detection

---

Spiral symmetry centroid detection

---

An efficient algorithm for camera pose estimation in environment of Dunhuang Mogao Grottoes

---

A spectral- multiplicity-tolerant approach to robust graph matching

---

Efficient semisuper- vised MEDLINE document clustering with MeSH-semantic and global-content constraints

---

Cube2Video: Navigate between cubic panoramas in real-time

---

Video Motion Estimation with Temporal Coherence

---

Pitch-density-based features and an SVM binary tree approach for multi-class audio classification in broadcast news

---

Real-time hand gesture recognition using motion tracking

---

Cascade Markov random fields for stroke extraction of Chinese characters

---

Maximum Lexical Cohesion for Fine-Grained News Story Segmentation

---

Self-validated labeling of Markov random fields for image segmentation

---

Audio-visual human recognition using semi-supervised spectral learning and hidden Markov models

---

A Subword Normalized Cut Approach to Automatic Story Segmentation of Chinese Broadcast News

---

Multicue Graph Mincut for Image Segmentation

---

Multi-Scale TextTiling for Automatic Story Segmentation in Chinese Broadcast News

---

Perceptual image preview

---

Region-level image authentication using Bayesian structural content abstraction

---

Spectral Multiplicity Tolerant Inexact Graph Matching

---

Self-Validated and Spatially Coherent Clustering with Net-Structured MRF and Graph Cuts

---

Bayesian Structural Content Abstraction for Region-Level Image Authentication

---

一种基于MASM的口形轮廓特征提取方法及听觉语音识别

---

Bayesian Structural Content Abstraction for Image Authentication

---

Non-Rigid Object Detection and Segmentation in Video Sequence Using 3D Mean Shift Analysis