Sciweavers

CVPR
2008
IEEE
14 years 11 months ago
Observe-and-explain: A new approach for multiple hypotheses tracking of humans and objects
This paper presents a novel approach for tracking humans and objects under severe occlusion. We introduce a new paradigm for multiple hypotheses tracking, observe-and-explain, as ...
Michael S. Ryoo, Jake K. Aggarwal
CVPR
2008
IEEE
14 years 11 months ago
Color constancy beyond bags of pixels
Estimating the color of a scene illuminant often plays a central role in computational color constancy. While this problem has received significant attention, the methods that exi...
Ayan Chakrabarti, Keigo Hirakawa, Todd Zickler
CVPR
2008
IEEE
14 years 11 months ago
People-tracking-by-detection and people-detection-by-tracking
Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered o...
Mykhaylo Andriluka, Stefan Roth, Bernt Schiele
CVPR
2008
IEEE
14 years 11 months ago
Where am I: Place instance and category recognition using spatial PACT
We introduce spatial PACT (Principal component Analysis of Census Transform histograms), a new representation for recognizing instances and categories of places or scenes. Both pl...
Jianxin Wu, James M. Rehg
CVPR
2007
IEEE
14 years 11 months ago
A Multi-Resolution Dynamic Model for Face Aging Simulation
In this paper we present a dynamic model for simulating face aging process. We adopt a high resolution grammatical face model[1] and augment it with age and hair features. This mo...
Jin-Li Suo, Feng Min, Song Chun Zhu, Shiguang Shan...
CVPR
2007
IEEE
14 years 11 months ago
Integration of Motion Cues in Optical and Sonar Videos for 3-D Positioning
Target-based positioning and 3-D target reconstruction are critical capabilities in deploying submersible platforms for a range of underwater applications, e.g., search and inspec...
Shahriar Negahdaripour, Hamed Pirsiavash, Hicham S...
CVPR
2007
IEEE
14 years 11 months ago
Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitabl...
Alessandro Bissacco, Ming-Hsuan Yang, Stefano Soat...
CVPR
2007
IEEE
14 years 11 months ago
Generative Graphical Models for Maneuvering Object Tracking and Dynamics Analysis
We study the challenging problem of maneuvering object tracking with unknown dynamics, i.e., forces or torque. We investigate the underlying causes of object kinematics, and propo...
Xin Fan, Guoliang Fan
CVPR
2007
IEEE
14 years 11 months ago
3D Face Recognition Founded on the Structural Diversity of Human Faces
We present a systematic procedure for selecting facial fiducial points associated with diverse structural characteristics of a human face. We identify such characteristics from th...
Shalini Gupta, J. K. Aggarwal, Mia K. Markey, Alan...
CVPR
2007
IEEE
14 years 11 months ago
Multi-Object Tracking Using Color, Texture and Motion
In this paper, we introduce a novel real-time tracker based on color, texture and motion information. RGB color histogram and correlogram (autocorrelogram) are exploited as color ...
Matti Pietikäinen, Valtteri Takala