Sciweavers

CVPR
2008
IEEE
14 years 6 months ago
Pan, zoom, scan - Time-coherent, trained automatic video cropping
We present a method to fully automatically fit videos in 16:9 format on 4:3 screens and vice versa. It can be applied to arbitrary aspect ratios and can be used to make videos sui...
Thomas Deselaers, Philippe Dreuw, Hermann Ney
CVPR
2008
IEEE
14 years 6 months ago
Radiometric calibration using temporal irradiance mixtures
We propose a new method for sampling camera response functions: temporally mixing two uncalibrated irradiances within a single camera exposure. Calibration methods rely on some kn...
Bennett Wilburn, Hui Xu, Yasuyuki Matsushita
CVPR
2008
IEEE
14 years 6 months ago
Pair-activity classification by bi-trajectories analysis
In this paper, we address the pair-activity classification problem, which explores the relationship between two active objects based on their motion information. Our contributions...
Yue Zhou, Shuicheng Yan, Thomas S. Huang
CVPR
2008
IEEE
14 years 6 months ago
Geo-spatial aerial video processing for scene understanding and object tracking
This paper presents an approach to extracting and using semantic layers from low altitude aerial videos for scene understanding and object tracking. The input video is captured by...
Jiangjian Xiao, Hui Cheng, Feng Han, Harpreet S. S...
CVPR
2008
IEEE
14 years 6 months ago
Unsupervised learning of probabilistic object models (POMs) for object classification, segmentation and recognition
We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this a...
Yuanhao Chen, Long Zhu, Alan L. Yuille, HongJiang ...
CVPR
2008
IEEE
14 years 6 months ago
Transductive object cutout
In this paper, we address the issue of transducing the object cutout model from an example image to novel image instances. We observe that although object and background are very ...
Jingyu Cui, Qiong Yang, Fang Wen, Qiying Wu, Chang...
CVPR
2008
IEEE
14 years 6 months ago
Semi-Supervised Discriminant Analysis using robust path-based similarity
Linear Discriminant Analysis (LDA), which works by maximizing the within-class similarity and minimizing the between-class similarity simultaneously, is a popular dimensionality r...
Yu Zhang, Dit-Yan Yeung
CVPR
2008
IEEE
14 years 6 months ago
Semi-supervised SVM batch mode active learning for image retrieval
Active learning has been shown as a key technique for improving content-based image retrieval (CBIR) performance. Among various methods, support vector machine (SVM) active learni...
Steven C. H. Hoi, Rong Jin, Jianke Zhu, Michael R....
CVPR
2008
IEEE
14 years 6 months ago
Active microscopic cellular image annotation by superposable graph transduction with imbalanced labels
Systematic content screening of cell phenotypes in microscopic images has been shown promising in gene function understanding and drug design. However, manual annotation of cells ...
Jun Wang, Shih-Fu Chang, Xiaobo Zhou, Stephen T. C...
CVPR
2008
IEEE
14 years 6 months ago
Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition
In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
Mikel D. Rodriguez, Javed Ahmed, Mubarak Shah