Search For:

Displaying 1-20 out of 20 total
The Best of Both Worlds: Combining 3D Deformable Models with Active Shape Models
Found in: Computer Vision, IEEE International Conference on
By Christian Vogler, Zhiguo Li, Atul Kanaujia, Siome Goldenstein, Dimitris Metaxas
Issue Date:October 2007
pp. 1-7
Reliable 3D tracking is still a difficult task. Most parametrized 3D deformable models rely on the accurate extraction of image features for updating their parameters, and are prone to failures when the underlying feature distribution assumptions are inval...
 
PR: More than Meets the Eye
Found in: Computer Vision, IEEE International Conference on
By Anderson Rocha, Siome Goldenstein
Issue Date:October 2007
pp. 1-8
In this paper, we introduce a new image descriptor for broad Image Categorization, the Progressive Randomization (PR), that uses perturbations on the values of the Least Significant Bits (LSB) of images. We show that different classes of images have a dist...
 
Invisible work in standard bibliometric evaluation of computer science
Found in: Communications of the ACM
By Cleo Billa, Jacques Wainer, Jacques Wainer, Jacques Wainer, Siome Goldenstein, Siome Goldenstein, Siome Goldenstein
Issue Date:May 2011
pp. 141-146
Most of a computer scientist's production can go uncounted if a standard bibliographic service is used.
     
Large-Scale Image Phylogeny: Tracing Image Ancestral Relationships
Found in: IEEE MultiMedia
By Zanoni Dias,Siome Goldenstein,Anderson Rocha
Issue Date:July 2013
pp. 58-70
Similar to organisms that evolve in biology, a document can change slightly overtime, and each new version may, in turn, generate other versions. Multimedia phylogeny investigates the history and evolutionary process of digital objects and includes finding...
 
Automatic Tracking of Indoor Soccer Players Using Videos from Multiple Cameras
Found in: 2012 XXV SIBGRAPI - Conference on Graphics, Patterns and Images (SIBGRAPI)
By Erikson Morais,Siome Goldenstein,Anselmo Ferreira,Anderson Rocha
Issue Date:August 2012
pp. 174-181
Indoor soccer has been of tactical and scientific interest, with applications dedicated to analyze tactical and physiological factors and also physical training. In both cases, the analysis is based on player tracking, done with human supervision. This pap...
 
Solving Image Puzzles with a Simple Quadratic Programming Formulation
Found in: 2012 XXV SIBGRAPI - Conference on Graphics, Patterns and Images (SIBGRAPI)
By Fernanda A. Andalo. Gabriel Taubin,Siome Goldenstein
Issue Date:August 2012
pp. 63-70
We present a new formulation to automatically solve jigsaw puzzles considering only the information contained on the image. Our formulation maps the problem of solving a jigsaw puzzle to the maximization of a constrained quadratic function that can be solv...
 
Crowd Simulation: Improving Pedestrians' Dynamics by the Application of Lattice-Gas Concepts to the Social Force Model
Found in: Graphics, Patterns and Images, SIBGRAPI Conference on
By Priscila Saboia,Siome Goldenstein
Issue Date:August 2011
pp. 41-47
The social force (SF) model has been successfully applied to the simulation of flows of pedestrians. Nevertheless, in some scenarios with low density, experiments show that the simulated individuals do not behave as expected, working as irrational particle...
 
Automatic Produce Classification from Images Using Color, Texture and Appearance Cues
Found in: Graphics, Patterns and Images, SIBGRAPI Conference on
By Anderson Rocha, Daniel C. Hauagge, Jacques Wainer, Siome Goldenstein
Issue Date:October 2008
pp. 3-10
We propose a system to solve a multi-class produce categorization problem. For that, we use statistical color, texture, and structural appearance descriptors (bag-of-features). As the best combination setup is not known for our problem, we combine several ...
 
The Unseen Challenge data sets
Found in: Computer Vision and Pattern Recognition Workshop
By Anderson Rocha, Siome Goldenstein, Walter Scheirer, Terrance Boult
Issue Date:June 2008
pp. 1-8
Nowadays, it is paramount to study and develop robust algorithms to detect the very existence of hidden messages in digital images. In this paper, we provide two data sets for the Unseen Challenge of the First IEEE Workitorial on Vision of the Unseen (WVU)...
 
When Occlusions are Outliers
Found in: Computer Vision and Pattern Recognition Workshop
By Siome Goldenstein, Christian Vogler
Issue Date:June 2006
pp. 98
In many tracking applications, the deformable object of interest suffers from frequent occlusions. Traditional augmenting methods use templates and measures of similarity to recover from occlusions. In this paper, we break with these methods. Instead, we m...
 
Adaptive Deformable Models
Found in: Graphics, Patterns and Images, SIBGRAPI Conference on
By Siome Goldenstein, Christian Vogler, Luiz Velho
Issue Date:October 2004
pp. 380-387
Deformable models are a powerful tool in both computer graphics and computer vision. The description and implementation of the deformations have to be simultaneously flexible and powerful, otherwise the technique may not satisfy the requirements of all the...
 
Outlier Rejection in Deformable Model Tracking
Found in: Computer Vision and Pattern Recognition Workshop
By Siome Goldenstein, Christian Vogler, Jorge Stolfi, Vladimir Pavlovic, Dimitris Metaxas
Issue Date:July 2004
pp. 19
Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The core of the approach consists of using low-level vision algorithms, such as edg...
 
3D Facial Tracking from Corrupted Movie Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Siome Goldenstein, Christian Vogler, Dimitris Metaxas
Issue Date:July 2004
pp. 880-885
<p>In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and the values of the parameters that describe the evolution of the fac...
 
Affine Arithmetic Based Estimation of Cue Distributions in Deformable Model Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Siome Goldenstein, Christian Vogler, Dimitris Metaxa
Issue Date:December 2001
pp. 1098
In this paper we describe a statistical method for the integration of an unlimited number of cues within a deformable model framework. We treat each cue as a random variable, each of which is the sum of a large number of local contributions with unknown pr...
 
Time Warping of Audio Signals
Found in: Computer Graphics International Conference
By Siome Goldenstein, Jonas Gomes
Issue Date:June 1999
pp. 52
This paper describes a technique to obtain a time dilation or contraction of an audio signal. Different Computer Graphics applications can take advantage of this technique. In real-time networked VR applications, such as teleconference or games, audio migh...
 
Video Phylogeny: Recovering near-duplicate video relationships
Found in: Information Forensics and Security, IEEE International Workshop on
By Zanoni Dias,Anderson Rocha,Siome Goldenstein
Issue Date:December 2011
pp. 1-6
To keep pace with the increasing popularity of image and video sharing services, several research groups have focused on the development of systems to identify similar copies images and videos on the internet. Although these techniques allow us to identify...
 
Adapted Dynamic Meshes for Deformable Surfaces
Found in: Graphics, Patterns and Images, SIBGRAPI Conference on
By Fernando de Goes, Felipe P. G. Bergo, Alexandre X. Falcao, Siome Goldenstein
Issue Date:October 2006
pp. 213-220
Deformable objects play an important role in many applications, such as animation and simulation. Effective computation with deformable surfaces can be achieved through the use of dynamic meshes. In this paper, we introduce a framework for constructing and...
 
Directed Acyclic Graph Representation of Deformable Models
Found in: Motion and Video Computing, IEEE Workshop on
By Siome Goldenstein, Christian Vogler, Dimitris Metaxas
Issue Date:December 2002
pp. 84
Deformable models are a useful tool in computer vision and computer graphics. A deformable model is a curve (in two dimensions) or a surface (in three dimensions), whose shape, position, and orientation are controlled through a set of parameters. Deformabl...
 
How productivity and impact differ across computer science subareas
Found in: Communications of the ACM
By Anderson Rocha, Jacques Wainer, Michael Eckmann, Siome Goldenstein
Issue Date:August 2013
pp. 67-73
How to understand evaluation criteria for CS researchers.
     
Making colors worth more than a thousand words
Found in: Proceedings of the 2008 ACM symposium on Applied computing (SAC '08)
By Anderson Rocha, Jurandy Almeida, Ricardo Torres, Siome Goldenstein
Issue Date:March 2008
pp. 28-34
Content-based image retrieval (CBIR) is a challenging task. Common techniques use only low-level features. However, these solutions can lead to the so-called 'semantic gap' problem: images with high feature similarities may be different in terms of user pe...
     
 1