173
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. By efficiently handling different scales and transferring computation from tes...
188
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
192
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We introduce two novel methods to improve the performance of wide area video surveillance applications by using scene features. First, we evaluate the drift in intrinsic and extri...
165
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
This paper focus on understanding human visual system when it decodes or recognizes facial expressions. Results presented can be exploited by the computer vision research communit...
174
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
134
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We address the problem of multi-person dataassociation-based tracking (DAT) in semi-crowded environments from a single camera. Existing trackletassociation-based methods using pur...
251
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Recent studies on visual tracking have shown significant improvement in accuracy by handling the appearance variations of the target object. Whereas most studies present schemes ...
178
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically an...
206
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor w...
178
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In real-world applications of visual recognition, many factors—such as pose, illumination, or image quality—can cause a significant mismatch between the source domain on whic...