Sciweavers

CVPR
2012
IEEE
13 years 9 months ago
Three things everyone should know to improve object retrieval
The objective of this work is object retrieval in large scale image datasets, where the object is specified by an image query and retrieval should be immediate at run time in the...
Relja Arandjelovic, Andrew Zisserman
CVPR
2012
IEEE
13 years 9 months ago
Parameter-free/Pareto-driven procedural 3D reconstruction of buildings from ground-level sequences
In this paper we address multi-view reconstruction of urban environments using 3D shape grammars. Our formulation expresses the solution to the problem as a shape grammar parse tr...
Loïc Simon, Olivier Teboul, Panagiotis Koutso...
CVPR
2012
IEEE
13 years 9 months ago
Segmentation using superpixels: A bipartite graph partitioning approach
Grouping cues can affect the performance of segmentation greatly. In this paper, we show that superpixels (image segments) can provide powerful grouping cues to guide segmentation...
Zhenguo Li, Xiao-Ming Wu, Shih-Fu Chang
CVPR
2012
IEEE
13 years 9 months ago
Consistent depth maps recovery from a trinocular video sequence
In this paper, we propose a novel dense depth recovery method for a trinocular video sequence. Specifically, we contribute a novel trinocular stereo matching model, which can eff...
Wenzhuo Yang, Guofeng Zhang, Hujun Bao, Jiwon Kim,...
CVPR
2012
IEEE
13 years 9 months ago
On multiple foreground cosegmentation
In this paper, we address a challenging image segmentation problem called multiple foreground cosegmentation (MFC), which concerns a realistic scenario in general Webuser photo se...
Gunhee Kim, Eric P. Xing
CVPR
2012
IEEE
13 years 9 months ago
Memory constrained face recognition
Real-time recognition may be limited by scarce memory and computing resources for performing classification. Although, prior research has addressed the problem of training classif...
Ashish Kapoor, Simon Baker, Sumit Basu, Eric Horvi...
CVPR
2012
IEEE
13 years 9 months ago
Video segmentation by tracing discontinuities in a trajectory embedding
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
Katerina Fragkiadaki, Geng Zhang, Jianbo Shi
CVPR
2012
IEEE
13 years 9 months ago
Social roles in hierarchical models for human activity recognition
We present a hierarchical model for human activity recognition in entire multi-person scenes. Our model describes human behaviour at multiple levels of detail, ranging from low-le...
Tian Lan, Leonid Sigal, Greg Mori
CVPR
2012
IEEE
13 years 9 months ago
See all by looking at a few: Sparse modeling for finding representative objects
We consider the problem of finding a few representatives for a dataset, i.e., a subset of data points that efficiently describes the entire dataset. We assume that each data poi...
Ehsan Elhamifar, Guillermo Sapiro, René Vid...
CVPR
2012
IEEE
13 years 9 months ago
Real time robust L1 tracker using accelerated proximal gradient approach
Recently sparse representation has been applied to visual tracker by modeling the target appearance using a sparse approximation over a template set, which leads to the so-called ...
Chenglong Bao, Yi Wu, Haibin Ling, Hui Ji