159
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for...
157
click to vote
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
Naive Bayes Nearest Neighbor (NBNN) has recently been proposed as a powerful, non-parametric approach for object classification, that manages to achieve remarkably good results t...
136
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
Bag-of-words (BoW) methods are a popular class of object recognition methods that use image features (e.g., SIFT) to form visual dictionaries and subsequent histogram vectors to r...
131
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
Visual tracking plays an important role in many computer vision tasks. A common assumption in previous methods is that the video frames are blur free. In reality, motion blurs are...
147
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
161
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exp...
178
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
This paper proposes a very general max-margin learning framework for distance-based clustering. To this end, it formulates clustering as a high order energy minimization problem w...
136
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
It has been shown repeatedly that iterative relevance feedback is a very efficient solution for content-based image retrieval. However, no existing system scales gracefully to hu...
131
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
Automatically assessing photo quality from the perspective of visual aesthetics is of great interest in high-level vision research and has drawn much attention in recent years. In...
155
Voted
ICCV
2011
IEEE
14 years 3 months ago
2011
IEEE
Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear...