Sciweavers

2267 search results - page 31 / 454
» Images as Bags of Pixels
Sort
View
ICTAI
2006
IEEE
14 years 2 months ago
MI-Winnow: A New Multiple-Instance Learning Algorithm
We present MI-Winnow, a new multiple-instance learning (MIL) algorithm that provides a new technique to convert MIL data into standard supervised data. In MIL each example is a co...
Sharath R. Cholleti, Sally A. Goldman, Rouhollah R...
ICMLA
2008
13 years 10 months ago
Image Segmentation as Learning on Hypergraphs
In this paper, we propose to use hypergraphs as the model for images and pose image segmentation as a machine learning problem in which some pixels (called seeds) are labeled as t...
Lei Ding, Alper Yilmaz
ICIP
2010
IEEE
13 years 6 months ago
View synthesis based on Conditional Random Fields and graph cuts
We propose a novel method to synthesize intermediate views from two stereo images and disparity maps that is robust to errors in disparity map. The proposed method computes a plac...
Lam C. Tran, Christopher J. Pal, Truong Q. Nguyen
NPL
2006
172views more  NPL 2006»
13 years 8 months ago
Adapting RBF Neural Networks to Multi-Instance Learning
In multi-instance learning, the training examples are bags composed of instances without labels, and the task is to predict the labels of unseen bags through analyzing the training...
Min-Ling Zhang, Zhi-Hua Zhou
DCC
2001
IEEE
14 years 8 months ago
Compression of the Layered Depth Image
A layered depth image (LDI) is a new popular representation and rendering method for objects with complex geometries. Similar to a 2D image, the LDI consists of an array of pixels...
Jiangang Duan, Jin Li