Sciweavers

CVPR
2012
IEEE
13 years 9 months ago
Batch mode Adaptive Multiple Instance Learning for computer vision tasks
Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance label...
Wen Li, Lixin Duan, Ivor Wai-Hung Tsang, Dong Xu
CVPR
2012
IEEE
13 years 9 months ago
Part-based multiple-person tracking with partial occlusion handling
Single camera-based multiple-person tracking is often hindered by difficulties such as occlusion and changes in appearance. In this paper, we address such problems by proposing a...
Guang Shu, Afshin Dehghan, Omar Oreifej, Emily Han...
CVPR
2012
IEEE
13 years 9 months ago
Multitarget data association with higher-order motion models
We present an iterative approximate solution to the multidimensional assignment problem under general cost functions. The method maintains a feasible solution at every step, and i...
Robert T. Collins
CVPR
2012
IEEE
13 years 9 months ago
Probabilistic tensor voting for robust perceptual grouping
We address the problem of unsupervised segmentation and grouping in 2D and 3D space, where samples are corrupted by noise, and in the presence of outliers. The problem has attract...
Dian Gong, Gérard G. Medioni
193
Voted
CVPR
2012
IEEE
13 years 9 months ago
Boosting algorithms for simultaneous feature extraction and selection
The problem of simultaneous feature extraction and selection, for classifier design, is considered. A new framework is proposed, based on boosting algorithms that can either 1) s...
Mohammad J. Saberian, Nuno Vasconcelos