Sciweavers

ICCV
2007
IEEE
15 years 1 months ago
pLSA for Sparse Arrays With Tsallis Pseudo-Additive Divergence: Noise Robustness and Algorithm
We introduce the Tsallis divergence error measure in the context of pLSA matrix and tensor decompositions showing much improved performance in the presence of noise. The focus of ...
Tamir Hazan, Roee Hardoon, Amnon Shashua
ICCV
2007
IEEE
15 years 1 months ago
Discriminative Subsequence Mining for Action Classification
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
Sebastian Nowozin, Gökhan H. Bakir, Koji Tsud...
ICCV
2007
IEEE
15 years 1 months ago
Steerable Random Fields
In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that ...
Stefan Roth, Michael J. Black
ICCV
2007
IEEE
15 years 1 months ago
Unsupervised Joint Alignment of Complex Images
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...
Gary B. Huang, Vidit Jain, Erik G. Learned-Miller
ICCV
2007
IEEE
15 years 1 months ago
Untangling Cycles for Contour Grouping
We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient cont...
Qihui Zhu, Gang Song, Jianbo Shi
ICCV
2007
IEEE
15 years 1 months ago
Scene Modeling Using Co-Clustering
In this paper, we propose a novel approach for scene modeling. The proposed method is able to automatically discover the intermediate semantic concepts. We utilize Maximization of...
Jingen Liu, Mubarak Shah
ICCV
2007
IEEE
15 years 1 months ago
Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts
We present a novel method to reconstruct the 3D shape of a scene from several calibrated images. Our motivation is that most existing multi-view stereovision approaches require so...
Patrick Labatut, Jean-Philippe Pons, Renaud Kerive...
ICCV
2007
IEEE
15 years 1 months ago
Perspectively Invariant Normal Features
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...
Kevin Köser, Reinhard Koch
ICCV
2007
IEEE
15 years 1 months ago
Differential EMD Tracking
Illumination changes cause object appearance to change drastically and many existing tracking algorithms lack the capability to handle this problem. The Earth Mover's Distanc...
Qi Zhao, Shane Brennan, Hai Tao
ICCV
2007
IEEE
15 years 1 months ago
Limits of Learning-Based Superresolution Algorithms
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 pe...
Zhouchen Lin, Junfeng He, Xiaoou Tang, Chi-Keung T...