Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach (2009)
Qihui Zhu, Liming Wang, Yang Wu, Jianbo Shi
Abstract. We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of...
Saliency Based Opportunistic Search for Object Part Extraction and Labeling (2009)
Yang Wu, Qihui Zhu, Jianbo Shi, Nanning Zheng
Abstract. We study the task of object part extraction and labeling, which seeks to understand objects beyond simply identifiying their bounding boxes. We start from bottom-up segmentation of images...
A “Shape Aware ” Model for semi-supervised Learning of Objects and its Context (2009)
Abhinav Gupta, Jianbo Shi, Larry S. Davis
We present an approach that combines bag-of-words and spatial models to perform semantic and syntactic analysis for recognition of an object based on its internal appearance and its context. We argue...
Xu, Geng, Xia, Jiahong, Hua, Xiaoyang, Zhou, Han, Yu, Chuanzhao, Liu, Zheng, ...
Abstract Background Decreased infiltration of Foxp3+ T regulatory cell (Treg) is considered to be critical for the Th1/Th2 dysregulation of nasal polyps, while the cellular mechanism underlying...
Untangling Cycles for Contour Grouping (2009)
Qihui Zhu, Gang Song, Jianbo Shi
We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient contours to extract them...
Shape from Shading: Recognizing the Mountains through a Global View (2008)
Resolving local ambiguities is an important issue fin" shape jkom shading (SFS). Pixel ambiguities of SFS can be elinzinuted by propagution approaches. However, patch anibiguities still...
Comparing Ensembles of Learners: Detecting Prostate Cancer from High Resolution MRI (2008)
Anant Madabhushi, Jianbo Shi, Michael Feldman, Mark Rosen, John Tomaszewski
Abstract. While learning ensembles have been widely used for various pattern recognition tasks, surprisingly, they have found limited application in problems related to medical image analysis and...
Shape from Shading: Recognizing the Mountains through a Global View (2008)
Resolving local ambiguities is an important issue for shape from shading (SFS). Pixel ambiguities of SFS can be eliminated by propagation approaches. However, patch ambiguities still exist....
Shape from Shading: Recognizing the Mountains through a Global View (2008)
Resolving local ambiguities is an important issue for shape from shading (SFS). Pixel ambiguities of SFS can be eliminated by propagation approaches. However, patch ambiguities still exist. We pose...
A Learnable Spectral Memory Graph for Recognition and Segmentation (2008)
Timothée Cour, Jianbo Shi, Timothée Cour, Jianbo Shi
Image segmentation is often treated as an unsupervised task. Segmentation by human, in contrast, relies heavily on memory to produce an object-like clustering, through a mechanism of controlled...
Anant Madabhushi, Jianbo Shi, Mark Rosen, John E. Tomaszeweski, Michaeld. Feldman
Abstract. Recently there has been a great deal of interest in algorithms for constructing low-dimensional feature-space embeddings of high dimensional data sets in order to visualize inter- and...
Image Matching via Saliency Region Correspondences (2008)
Er Toshev, Jianbo Shi, Kostas Daniilidis
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matching segments....
Naoya Takao, Jianbo Shi, Simon Baker, Iain Matthews, Bart Nabbe
Tele-Graffiti is a system allowing two or more users to communicate remotely via hand-drawn sketches. What one person writes at one site is captured using a video camera, transmitted to the other...
Learning Spectral Graph Segmentation (2008)
Timothee Cour, Nicolas Gogin, Jianbo Shi
We present a general graph learning algorithm for spectral graph partitioning, that allows direct supervised learning of graph structures using hand labeled training examples. The learning algorithm...
this paper I will attempt to study one small aspect of this problem of using learning in vision. In particular I will study how learning might be used for visual hallucination. By visual...
Jitendra Malik, Serge Belongie, Thomas Leung, Jianbo Shi
Abstract. This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so...
Projected Comments Written (2007)
Naoya Takao, Jianbo Shi, Simon Baker, Iain Matthews, Bart Nabbe
Tele-Graffiti is a system allowing two or more users to communicate remotely via hand-drawn sketches. What one person writes at one site is captured using a video camera, transmitted to the other...
Object detection combining recognition and segmentation (2007)
Liming Wang, Jianbo Shi, Gang Song, I-fan Shen
Abstract. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation step and a...
Bottom-up recognition and parsing of the human body (2007)
Praveen Srinivasan, Jianbo Shi
Abstract. Recognizing humans, estimating their pose and segmenting their body parts are key to high-level image understanding. Because humans are highly articulated, the range of deformations they...
Balanced graph matching (2006)
Timothee Cour, Praveen Srinivasan, Jianbo Shi
Graph matching is a fundamental problem in Computer Vision and Machine Learning. We present two contributions. First, we give a new spectral relaxation technique for approximate solutions to matching...
Balanced graph matching (2006)
Timothee Cour, Praveen Srinivasan, Jianbo Shi
Graph matching is a fundamental problem in Computer Vision and Machine Learning. We present two contributions. First, we give a new spectral relaxation technique for approximate solutions to matching...
Spectral Segmentation with Multiscale Graph Decomposition (2005)
Cour, Timothée, Bénézit, Florence, Shi, Jianbo
We present a multiscale spectral image segmentation algorithm. In contrast to most multiscale image processing, this algorithm works on multiple scales of the image in parallel, without iteration, to...
Spectral segmentation with multiscale graph decomposition (2005)
Timothée Cour, Florence Bénézit, Jianbo Shi
We present a multiscale spectral image segmentation algorithm. In contrast to most multiscale image processing, this algorithm works on multiple scales of the image in parallel, without iteration, to...
Detecting Unusual Activity in Video (2004)
Zhong, Hua, Shi, Jianbo, Visontai, Mirko
We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. No complex activity models and no supervised feature selections are used. We...
A Learnable Spectral Memory Graph for Recognition and Segmentation (2004)
Image segmentation is often treated as an unsupervised task. Segmentation by human, in contrast, relies heavily on memory to produce an object-like clustering, through a mechanism of controlled...
Multiple Frame Motion Inference Using Belief Propagation (2004)
We present an algorithm for automatic inference of human upper body motion. A graph model is proposed for inferring human motion, and motion inference is posed as a mapping problem between state...
Segmentation given partial grouping constraints (2004)
We consider data clustering problems where partial grouping is known a priori. We formulate such biased grouping problems as a constrained optimization problem, where structural properties of the...
Segmentation Given Partial Grouping Constraints (2004)
We consider data clustering problems where partial grouping is known a priori. We formulate such biased grouping problems as a constrained optimization problem, where structural properties of the...
Segmentation given partial grouping constraints (2004)
Stella X. Yu, Ieee Computer Society, Jianbo Shi, Ieee Computer Society
Abstract—We consider data clustering problems where partial grouping is known a priori. We formulate such biased grouping problems as a constrained optimization problem, where structural properties...
Multiple frame motion inference using belief propagation (2004)
We present an algorithm for automatic inference of human upper body motion. A graph model is proposed for inferring human motion, and motion inference is posed as a mapping problem between state...
Alexei A. Efros, Volkan Isler, Jianbo Shi, Mirko Visontai
We consider the problem of recovering an underwater image distorted by surface waves. A large amount of video data of the distorted image is acquired. The problem is posed in terms of finding an...
Multiple frame motion inference using belief propagation (2004)
We present an algorithm for automatic inference of human upper body motion. A graph model is proposed for inferring human motion, and motion inference is posed as a mapping problem between state...
Naoya Takao, Jianbo Shi, Simon Baker
One way to build a remote sketching system is to use a video camera to image what each user draws at their site, transmit the video to the other sites, and display it there using an LCD projector....
Multiclass Spectral Clustering (2003)
Stella Yu Jianbo, Stella X. Yu, Jianbo Shi
We propose a principled account on multiclass spectral clustering. Given a discrete clustering formulation, we first solve a relaxed continuous optimization problem by eigendecomposition. We clarify...
Finding (Un)Usual Events in Video (2003)
We propose an algorithm for detecting and categorizing (un)usual human activity in a video which might be a few days long. The proposed approach is unsupervised, and uses the co-occurrence among...
Inferring Human Upper Body Motion Using Belief Propagation (2003)
inference, belief propagation We present an algorithm for automatic inference of human upper body motion in a natural scene. A graph model is proposed for inferring human upper body motion, and...
Steady-State Feedback Analysis of Tele-Graffiti (2003)
Naoya Takao Simon, Simon Baker, Jianbo Shi
this paper. The combination of projectors and cameras in the same system can either be beneficial or a hindrance, depending on what you want to do. In hand-tracking systems for desktop...
Silhouette-based Human Identification from Body Shape and Gait (2002)
Collins, Robert T, Gross, Ralph, Shi, Jianbo
Our goal is to establish a simple baseline method for human identification based on body shape and gait. This baseline recognition method provides a lower bound against which to evaluate more...
Martial Hebert, co-Chair (2002)
Shyjan Mahamud, Takeo Kanade, Jianbo Shi, Pietro Perona
ONR N00014-00-1-0915.
Concurrent object recognition and segmentation by graph partitioning (2002)
Stella X. Yu, Ralph Gross, Jianbo Shi
Segmentation and recognition have long been treated as two separate processes. We propose a mechanism based on spectral graph partitioning that readily combine the two processes into one. A...
Concurrent object recognition and segmentation by graph partitioning (2002)
Stella X. Yu, Ralph Gross, Jianbo Shi
Segmentation and recognition have long been treated as two separate processes. We propose a mechanism based on spectral graph partitioning that readily combine the two processes into one. A...
Concurrent object recognition and segmentation by graph partitioning (2002)
Stella X. Yu, Ralph Gross, Jianbo Shi
Segmentation and recognition have long been treated as two separate processes. We propose a mechanism based on spectral graph partitioning that readily combine the two processes into one. A...
Silhouette-based human identification from body shape and gait (2002)
Robert T. Collins, Ralph Gross, Jianbo Shi
Our goal is to establish a simple baseline method for human identification based on body shape and gait. This baseline recognition method provides a lower bound against which to evaluate more...
Silhouette-based human identification from body shape and gait (2002)
Robert T. Collins, Ralph Gross, Jianbo Shi
Our goal is to establish a simple baseline method for human identification based on body shape and gait. This baseline recognition method provides a lower bound against which to evaluate more...
Robust Tracking and Structure from Motion with Sampling Method (2002)
Peng Chang, Robert Collins, Jianbo Shi, Michael Black
Robust tracking and structure from motion (SFM) are fundamental problems in computer vision that have important applications for robot visual navigation and other computer vision tasks. Al-though the...
Martial Hebert, co-Chair (2002)
Shyjan Mahamud, Takeo Kanade, Jianbo Shi, Pietro Perona
search, discrimination.
Object Recognition using Boosted Discriminants (2001)
Mahamud, Shyjan, Hebert, Martial, Shi, Jianbo
We approach the task of object discrimination as that of learning efficient "codes" for each object class in terms of responses to a set of chosen discriminants. We formulate this approach in an...
Quo vadis face recognition (2001)
Ralph Gross, Jianbo Shi, Jeff Cohn
Within the past decade, major advances have occurred in face recognition. Many systems have emerged that are capable of achieving recognition rates in excess of 90% accuracy under controlled...
The cmu motion of body (mobo) database (2001)
In March 2001 we started to collect the CMU Motion of Body (MoBo) database. To date the database contains 25 individuals walking on a treadmill in the CMU 3D room. The subjects perform four different...
Grouping with directed relationships (2001)
Abstract. Grouping is a global partitioning process that integrates local cues distributed over the entire image. We identify four types of pairwise relationships, attraction and repulsion, each of...
With the optimization of pattern discrimination as a goal, graph partitioning approaches often lack the capability to integrate prior knowledge to guide grouping. In this paper, we consider priors...
Quo vadis face recognition (2001)
Ralph Gross, Jianbo Shi, Jeffrey F. Cohn
Within the past decade, major advances have occurred in face recognition. With few exceptions, however, most research has been limited to training and testing on frontal views. Little is known about...
Object recognition using boosted discriminants (2001)
Shyjan Mahamud, Martial Hebert, Jianbo Shi
We approach the task of object discrimination as that of learning efficient "codes " for each object class in terms of responses to a set of chosen discriminants. We formulate this...
A random walks view of spectral segmentation (2001)
We present a new view of clustering and segmentation by pairwise similarities. We interpret the similarities as edge flows in a Markov random walk and study the eigenvalues and eigenvectors of the...
A random walks view of spectral segmentation (2001)
We present a new view of clustering and segmentation by pairwise similarities. We interpret the similarities as edge ows in a Markov random walk and study the eigenvalues and eigenvectors of the...
Contour and Texture Analysis for Image Segmentation (2001)
Jitendra Malik, Serge Belongie, Thomas Leung, Jianbo Shi
. This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so the cues...
Quo vadis face recognition (2001)
Ralph Gross, Jianbo Shi, Jeff Cohn
Within the past decade, major advances have occurred in face recognition. Many systems have emerged that are capable of achieving recognition rates in excess of 90% accuracy under controlled...
Normalized Cuts and Image Segmentation (2000)
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting...
Normalized Cuts and Image Segmentation (2000)
AbstractÐWe propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at...
Normalized Cuts and Image Segmentation (2000)
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting...
Learning segmentation by random walks (2000)
We present a new view of image segmentation by pairwise similarities. We interpret the similarities as edge ows in a Markov random walk and study the eigenvalues and eigenvectors of the walk's...
Normalized Cuts and Image Segmentation (2000)
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting...
Learning segmentation by random walks (2000)
Abstract We present a new view of image segmentation by pairwise similarities. We interpret the similarities as edge flows in a Markov random walk and study the eigenvalues and eigenvectors of the...
Textons, Contours and Regions: Cue Integration in Image Segmentation (1999)
Jitendra Malik, Serge Belongie, Jianbo Shi, Thomas Leung
This paper makes two contributions. It provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into...
Textons, contours and regions: Cue integration in image segmentation (1999)
Jitendra Malik, Serge Belongie, Jianbo Shi, Thomas Leung
This paper makes two contributions. It provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into...
Perceptual organization and image segmentation /--by Jianbo Shi. (1998)
Thesis (Ph. D. in Computer Science)--University of California, Berkeley, Spring 1998.
Self Inducing Relational Distance and its Application to Image Segmentation (1998)
We propose a new feature distance which is derived from an optimal relational graph matching criterion. Instead of defining an arbitrary similarity measure for grouping, we will use the criterion of...
Image And Video Segmentation: The Normalized Cut Framework (1998)
Jianbo Shi, Serge Belongie, Thomas Leung, Jitendra Malik
In this paper, we propose a segmentation system based on the normalized cut framework proposed by Shi and Malik (1997). The goal is to partition the image from a big picture point of view....
Motion Segmentation and Tracking Using Normalized Cuts (1998)
We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. A weighted graph is constructed on the image sequence by connecting pixels that are in the...
Normalized Cuts and Image Segmentation (1997)
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting...
Normalized Cuts and Image Segmentation (1997)
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting...
No feature-based vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can...
No feature-based vision system can work unless good features can be identi ed and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can...
No feature-based vision system can work until good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can...
No feature-based vision system can work until good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can...
Direction of Heading from Image Deformations (1993)
We propose a method to compute the direction of heading from the differential changes in the angles between the projection rays of pairs of point features. These angles, the image deformations, do...