Sciweavers

1568 search results - page 45 / 314
» Boosting Object Detection Using Feature Selection
Sort
View
AMFG
2003
IEEE
144views Biometrics» more  AMFG 2003»
15 years 7 months ago
Boosted Audio-Visual HMM for Speech Reading
We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likeliho...
Pei Yin, Irfan A. Essa, James M. Rehg
MVA
2007
133views Computer Vision» more  MVA 2007»
15 years 3 months ago
Selection of Object Recognition Methods According to the Task and Object Category
Service robots need object recognition strategy that can work on various objects in complex backgrounds. Since no single method can work in every situation, we need to combine sev...
Al Mansur, Yoshinori Kuno
118
Voted
CVPR
2008
IEEE
16 years 3 months ago
Structure-perceptron learning of a hierarchical log-linear model
In this paper, we address the problems of deformable object matching (alignment) and segmentation with cluttered background. We propose a novel hierarchical log-linear model (HLLM...
Long Zhu, Yuanhao Chen, Xingyao Ye, Alan L. Yuille
86
Voted
ICPR
2006
IEEE
16 years 3 months ago
Improving human activity detection by combining multi-dimensional motion descriptors with boosting
A new, combined human activity detection method is proposed. Our method is based on Efros et al.'s motion descriptors[2] and Ke et al.'s event detectors[3]. Since both m...
Josef Kittler, Seiji Ishikawa, Takehito Ogata, Wil...
113
Voted
ICCV
2011
IEEE
14 years 1 months ago
Informative Feature Selection for Object Recognition via Sparse PCA
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...
Nikhil Naikal, Allen Y. Yang, S. Shankar Sastry