Search For:

Displaying 1-50 out of 165 total
User intention modeling for interactive image retrieval
Found in: Multimedia and Expo, IEEE International Conference on
By Jingyu Cui, Fang Wen, Xiaoou Tang
Issue Date:July 2010
pp. 1517-1522
We propose three innovative interactive methods to let computer better understand user intention in content-based image retrieval: 1. Smart intention list induces user intention, thereby improves search results by intention-specific search schema; 2. Refer...
 
Limits of Learning-Based Superresolution Algorithms
Found in: Computer Vision, IEEE International Conference on
By Zhouchen Lin, Junfeng He, Xiaoou Tang, Chi-Keung Tang
Issue Date:October 2007
pp. 1-8
Learning-based superresolution (SR) are popular SR techniques that use application dependent priors to infer the missing details in low resolution images (LRIs). However, their performance still deteriorates quickly when the magnification factor is moderat...
 
Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xianbiao Qi,Rong Xiao,Chun-Guang Li,Yu Qiao,Jun Guo,Xiaoou Tang
Issue Date:November 2014
pp. 1-1
Designing effective features is a fundamental problem in computer vision. However, it is usually difficult to achieve a great tradeoff between discriminative power and robustness. Previous works shown that spatial co-occurrence can boost the discriminative...
 
Web Image Re-Ranking UsingQuery-Specific Semantic Signatures
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xiaogang Wang, Shi Qiu, Ke Liu, Xiaoou Tang
Issue Date:April 2014
pp. 810-823
Image re-ranking, as an effective way to improve the results of web-based image search, has been adopted by current commercial search engines such as Bing and Google. Given a query keyword, a pool of images are first retrieved based on textual information....
 
Complex 3D General Object Reconstruction from Line Drawings
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Linjie Yang,Jianzhuang Liu,Xiaoou Tang
Issue Date:December 2013
pp. 1433-1440
An important topic in computer vision is 3D object reconstruction from line drawings. Previous algorithms either deal with simple general objects or are limited to only manifolds (a subset of solids). In this paper, we propose a novel approach to 3D recons...
 
Hidden Factor Analysis for Age Invariant Face Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Dihong Gong,Zhifeng Li,Dahua Lin,Jianzhuang Liu,Xiaoou Tang
Issue Date:December 2013
pp. 2872-2879
Age invariant face recognition has received increasing attention due to its great potential in real world applications. In spite of the great progress in face recognition techniques, reliably recognizing faces across ages remains a difficult task. The faci...
 
Mining Motion Atoms and Phrases for Complex Action Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Limin Wang,Yu Qiao,Xiaoou Tang
Issue Date:December 2013
pp. 2680-2687
This paper proposes motion atom and phrase as a mid-level temporal ``part'' for representing and classifying complex action. Motion atom is defined as an atomic part of action, and captures the motion information of action video in a short temporal scale. ...
 
Deep Learning Identity-Preserving Face Space
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Zhenyao Zhu,Ping Luo,Xiaogang Wang,Xiaoou Tang
Issue Date:December 2013
pp. 113-120
Face recognition with large pose and illumination variations is a challenging problem in computer vision. This paper addresses this challenge by proposing a new learning based face representation: the face identity-preserving (FIP) features. Unlike convent...
 
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ping Luo,Xiaogang Wang,Xiaoou Tang
Issue Date:December 2013
pp. 2864-2871
Recent works have shown that facial attributes are useful in a number of applications such as face recognition and retrieval. However, estimating attributes in images with large variations remains a big challenge. This challenge is addressed in this paper....
 
Visual Semantic Complex Network for Web Images
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Shi Qiu,Xiaogang Wang,Xiaoou Tang
Issue Date:December 2013
pp. 3623-3630
This paper proposes modeling the complex web image collections with an automatically generated graph structure called visual semantic complex network (VSCN). The nodes on this complex network are clusters of images with both visual and semantic consistency...
 
Hybrid Deep Learning for Face Verification
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yi Sun,Xiaogang Wang,Xiaoou Tang
Issue Date:December 2013
pp. 1489-1496
This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for face verification in wild conditions. A key contribution of this work is to directly learn relational visual features, which indicate identity similar...
 
Face Recognition via Archetype Hull Ranking
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yuanjun Xiong,Wei Liu,Deli Zhao,Xiaoou Tang
Issue Date:December 2013
pp. 585-592
The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing ...
 
Pedestrian Parsing via Deep Decompositional Network
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ping Luo,Xiaogang Wang,Xiaoou Tang
Issue Date:December 2013
pp. 2648-2655
We propose a new Deep Decompositional Network (DDN) for parsing pedestrian images into semantic regions, such as hair, head, body, arms, and legs, where the pedestrians can be heavily occluded. Unlike existing methods based on template matching or Bayesian...
 
Face Recognition Using Face Patch Networks
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Chaochao Lu,Deli Zhao,Xiaoou Tang
Issue Date:December 2013
pp. 3288-3295
When face images are taken in the wild, the large variations in facial pose, illumination, and expression make face recognition challenging. The most fundamental problem for face recognition is to measure the similarity between faces. The traditional measu...
 
Guided Image Filtering
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kaiming He,Jian Sun,Xiaoou Tang
Issue Date:June 2013
pp. 1397-1409
In this paper, we propose a novel explicit image filter called guided filter. Derived from a local linear model, the guided filter computes the filtering output by considering the content of a guidance image, which can be the input image itself or another ...
 
Image Transformation Based on Learning Dictionaries across Image Spaces
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kui Jia, Xiaogang Wang, Xiaoou Tang
Issue Date:February 2013
pp. 367-380
In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of paired images. The framework can be used for applications such as image super-reso...
 
Hierarchical face parsing via deep learning
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Ping Luo, Xiaogang Wang, Xiaoou Tang
Issue Date:June 2012
pp. 2480-2487
This paper investigates how to parse (segment) facial components from face images which may be partially occluded. We propose a novel face parser, which recasts segmentation of face components as a cross-modality data transformation problem, i.e., transfor...
 
Example-based 3D object reconstruction from line drawings
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Tianfan Xue, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2012
pp. 302-309
Recovering 3D geometry from a single 2D line drawing is an important and challenging problem in computer vision. It has wide applications in interactive 3D modeling from images, computer-aided design, and 3D object retrieval. Previous methods of 3D reconst...
 
Synthesizing oil painting surface geometry from a single photograph
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Wei Luo, Zheng Lu, Xiaogang Wang, Ying-Qing Xu,M. Ben-Ezra, Xiaoou Tang,M. S. Brown
Issue Date:June 2012
pp. 885-892
We present an approach to synthesize the subtle 3D relief and texture of oil painting brush strokes from a single photograph. This task is unique from traditional synthesize algorithms due to its mixed modality between the input and output; i.e., our goal ...
 
Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Bolei Zhou, Xiaogang Wang, Xiaoou Tang
Issue Date:June 2012
pp. 2871-2878
In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors characterize the intrinsic dynamics of the crowd. From the agent-based modeli...
 
IntentSearch: Capturing User Intention for One-Click Internet Image Search
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xiaoou Tang,Ke Liu,Jingyu Cui,Fang Wen,Xiaogang Wang
Issue Date:July 2012
pp. 1342-1353
Web-scale image search engines (e.g., Google image search, Bing image search) mostly rely on surrounding text features. It is difficult for them to interpret users' search intention only by query keywords and this leads to ambiguous and noisy search result...
 
Optical flow estimation using learned sparse model
Found in: Computer Vision, IEEE International Conference on
By Kui Jia, Xiaogang Wang, Xiaoou Tang
Issue Date:November 2011
pp. 2391-2398
Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dense flow field, appropriate spatial constraints have to be enforced. Recent advances exploit higher order spatial regularization, and achieve the top performa...
 
Content-based photo quality assessment
Found in: Computer Vision, IEEE International Conference on
By Wei Luo, Xiaogang Wang,Xiaoou Tang
Issue Date:November 2011
pp. 2206-2213
Automatically assessing photo quality from the perspective of visual aesthetics is of great interest in high-level vision research and has drawn much attention in recent years. In this paper, we propose content-based photo quality assessment using regional...
 
Random field topic model for semantic region analysis in crowded scenes from tracklets
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bolei Zhou, Xiaogang Wang, Xiaoou Tang
Issue Date:June 2011
pp. 3441-3448
In this paper, a Random Field Topic (RFT) model is proposed for semantic region analysis from motions of objects in crowded scenes. Different from existing approaches of learning semantic regions either from optical flows or from complete trajectories, our...
 
A global sampling method for alpha matting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kaiming He,C. Rhemann,C. Rother, Xiaoou Tang, Jian Sun
Issue Date:June 2011
pp. 2049-2056
Alpha matting refers to the problem of softly extracting the foreground from an image. Given a trimap (specifying known foreground/background and unknown pixels), a straightforward way to compute the alpha value is to sample some known foreground and backg...
 
Coupled information-theoretic encoding for face photo-sketch recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wei Zhang, Xiaogang Wang, Xiaoou Tang
Issue Date:June 2011
pp. 513-520
Automatic face photo-sketch recognition has important applications for law enforcement. Recent research has focused on transforming photos and sketches into the same modality for matching or developing advanced classification algorithms to reduce the modal...
 
An associate-predict model for face recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qi Yin, Xiaoou Tang, Jian Sun
Issue Date:June 2011
pp. 497-504
Handling intra-personal variation is a major challenge in face recognition. It is difficult how to appropriately measure the similarity between human faces under significantly different settings (e.g., pose, illumination, and expression). In this paper, we...
 
Symmetric piecewise planar object reconstruction from a single image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tianfan Xue, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2011
pp. 2577-2584
Recovering 3D geometry from a single view of an object is an important and challenging problem in computer vision. Previous methods mainly focus on one specific class of objects without large topological changes, such as cars, faces, or human bodies. In th...
 
Query-specific visual semantic spaces for web image re-ranking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiaogang Wang, Ke Liu, Xiaoou Tang
Issue Date:June 2011
pp. 857-864
Image re-ranking, as an effective way to improve the results of web-based image search, has been adopted by current commercial search engines. Given a query keyword, a pool of images are first retrieved by the search engine based on textual information. By...
 
Single Image Haze Removal Using Dark Channel Prior
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kaiming He,Jian Sun,Xiaoou Tang
Issue Date:December 2011
pp. 2341-2353
In this paper, we propose a simple but effective image prior—dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of outdoor haze-free images. It is based on a key observation—most local patches in out...
 
Learning Semi-Riemannian Metrics for Semisupervised Feature Extraction
Found in: IEEE Transactions on Knowledge and Data Engineering
By Wei Zhang, Zhouchen Lin, Xiaoou Tang
Issue Date:April 2011
pp. 600-611
Discriminant feature extraction plays a central role in pattern recognition and classification. Linear Discriminant Analysis (LDA) is a traditional algorithm for supervised feature extraction. Recently, unlabeled data have been utilized to improve LDA. How...
 
Fast matting using large kernel matting Laplacian matrices
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kaiming He, Jian Sun, Xiaoou Tang
Issue Date:June 2010
pp. 2165-2172
Image matting is of great importance in both computer vision and graphics applications. Most existing state-of-the-art techniques rely on large sparse matrices such as the matting Laplacian [12]. However, solving these linear systems is often time-consumin...
 
Face recognition with learning-based descriptor
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zhimin Cao, Qi Yin, Xiaoou Tang, Jian Sun
Issue Date:June 2010
pp. 2707-2714
We present a novel approach to address the representation issue and the matching issue in face recognition (verification). Firstly, our approach encodes the micro-structures of the face by a new learning-based encoding method. Unlike many previous manually...
 
Object cut: Complex 3D object reconstruction through line drawing separation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tianfan Xue, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2010
pp. 1149-1156
This paper proposes an approach called object cut to tackle an important problem in computer vision, 3D object reconstruction from single line drawings. Given a complex line drawing representing a solid object, our algorithm finds the places, called cuts, ...
 
Isoperimetric cut on a directed graph
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mo Chen, Ming Liu, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2010
pp. 2109-2116
In this paper, we propose a novel probabilistic view of the spectral clustering algorithm. In our framework, the spectral clustering algorithm can be viewed as assigning class labels to samples to minimize the Bayes classification error rate by using a ker...
 
Learning to Detect a Salient Object
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tie Liu, Zejian Yuan, Jian Sun, Jingdong Wang, Nanning Zheng, Xiaoou Tang, Heung-Yeung Shum
Issue Date:February 2011
pp. 353-367
In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center...
 
Decomposition of Complex Line Drawings with Hidden Lines for 3D Planar-Faced Manifold Object Reconstruction
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jianzhuang Liu, Yu Chen, Xiaoou Tang
Issue Date:January 2011
pp. 3-15
Three-dimensional object reconstruction from a single 2D line drawing is an important problem in computer vision. Many methods have been presented to solve this problem, but they usually fail when the geometric structure of a 3D object becomes complex. In ...
 
Constrained clustering via spectral regularization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zhenguo Li, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2009
pp. 421-428
We propose a novel framework for constrained spectral clustering with pairwise constraints which specify whether two objects belong to the same cluster or not. Unlike previous methods that modify the similarity matrix with pairwise constraints, we adapt th...
 
Single image haze removal using dark channel prior
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kaiming He, Jian Sun, Xiaoou Tang
Issue Date:June 2009
pp. 1956-1963
In this paper, we propose a simple but effective image prior - dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of the haze-free outdoor images. It is based on a key observation - most local patche...
 
3D reconstruction of curved objects from single 2D line drawings
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yingze Wang, Yu Chen, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2009
pp. 1834-1841
An important research area in computer vision is developing algorithms that can reconstruct the 3D surface of an object represented by a single 2D line drawing. Previous work on 3D reconstruction from single 2D line drawings focuses on objects with planar ...
 
Responses to the Comments on “Plane-Based Optimization for 3D Object Reconstruction from Single Line Drawings”
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jianzhuang Liu, Liangliang Cao, Zhenguo Li, Xiaoou Tang
Issue Date:September 2009
pp. 1726-1728
We disagree with the comments made by Varley [1] on our previous paper [2]. In this paper, we respond to his comments and show that they are not correct.
 
Responses to the Comments on “What the Back of the Object Looks Like: 3D Reconstruction from Line Drawings without Hidden Lines”
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Liangliang Cao, Jianzhuang Liu, Xiaoou Tang
Issue Date:August 2009
pp. 1535-1536
Varley [1] made comments on our paper in [2] section by section. We answer them in this response paper.
 
Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guangcan Liu, Zhouchen Lin, Yong Yu, Xiaoou Tang
Issue Date:May 2010
pp. 910-924
In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmentation can be regarded as a special data clustering problem where both class-sp...
 
Face Photo-Sketch Synthesis and Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xiaogang Wang, Xiaoou Tang
Issue Date:November 2009
pp. 1955-1967
In this paper, we propose a novel face photo-sketch synthesis and recognition method using a multiscale Markov Random Fields (MRF) model. Our system has three components: 1) given a face photo, synthesizing a sketch drawing; 2) given a face sketch drawing,...
 
2D Shape Matching by Contour Flexibility
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chunjing Xu, Jianzhuang Liu, Xiaoou Tang
Issue Date:January 2009
pp. 180-186
In computer vision, shape matching is a challenging problem, especially when articulation and deformation of parts occur. These variations may be insignificant in terms of human recognition, but often cause a matching algorithm to give results that are inc...
 
Nonparametric Discriminant Analysis for Face Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhifeng Li, Dahua Lin, Xiaoou Tang
Issue Date:April 2009
pp. 755-761
In this paper, we develop a new framework for face recognition based on nonparametric discriminant analysis (NDA) and multi-classifier integration. Traditional LDA-based methods suffer a fundamental limitation originating from the parametric nature of scat...
 
Transductive object cutout
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingyu Cui, Qiong Yang, Fang Wen, Qiying Wu, Changshui Zhang, Luc Van Gool, Xiaoou Tang
Issue Date:June 2008
pp. 1-8
In this paper, we address the issue of transducing the object cutout model from an example image to novel image instances. We observe that although object and background are very likely to contain similar colors in natural images, it is much less probable ...
 
Misalignment-robust face recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Huan Wang, Shuicheng Yan, Thomas Huang, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2008
pp. 1-6
In this paper, we study the problem of subspace-based face recognition under scenarios with spatial misalignments and/or image occlusions. For a given subspace, the embedding of a new datum and the underlying spatial misalignment parameters are simultaneou...
 
L<inf>1</inf> regularized projection pursuit for additive model learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiao Zhang, Lin Liang, Xiaoou Tang, Heung-Yeung Shum
Issue Date:June 2008
pp. 1-8
In this paper, we present a L<inf>1</inf> regularized projection pursuit algorithm for additive model learning. Two new algorithms are developed for regression and classification respectively: sparse projection pursuit regression and sparse Jen...
 
Sketching in the air: A vision-based system for 3D object design
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu Chen, Jianzhuang Liu, Xiaoou Tang
Issue Date:June 2008
pp. 1-6
3D object design has many applications including flexible 3D sketch input in CAD, computer game, webpage content design, image based object modeling, and 3D object retrieval. Most current 3D object design tools work on a 2D drawing plane such as computer s...
 
 1  2 Next >>