Sciweavers

1131 search results - page 151 / 227
» Generalization Improvement in Multi-Objective Learning
Sort
View
87
Voted
CVPR
2010
IEEE
15 years 8 months ago
Face Recognition with Learning-based Descriptor
We present a novel approach to address the representation issue and the matching issue in face recognition (verification). Firstly, our approach encodes the micro-structures of t...
Zhimin Cao, Qi Yin, Jian Sun, Xiaoou Tang
90
Voted
IROS
2009
IEEE
145views Robotics» more  IROS 2009»
15 years 7 months ago
Action-related place-based mobile manipulation
— In mobile manipulation, the position to which the robot navigates has a large influence on the ease with which a subsequent manipulation action can be performed. Whether a man...
Freek Stulp, Andreas Fedrizzi, Michael Beetz
103
Voted
CIKM
2009
Springer
15 years 7 months ago
Adaptive relevance feedback in information retrieval
Relevance Feedback has proven very effective for improving retrieval accuracy. A difficult yet important problem in all relevance feedback methods is how to optimally balance the...
Yuanhua Lv, ChengXiang Zhai
107
Voted
SIGIR
2009
ACM
15 years 7 months ago
Smoothing clickthrough data for web search ranking
Incorporating features extracted from clickthrough data (called clickthrough features) has been demonstrated to significantly improve the performance of ranking models for Web sea...
Jianfeng Gao, Wei Yuan, Xiao Li, Kefeng Deng, Jian...
ICRA
2008
IEEE
191views Robotics» more  ICRA 2008»
15 years 7 months ago
Combining automated on-line segmentation and incremental clustering for whole body motions
Abstract— This paper describes a novel approach for incremental learning of human motion pattern primitives through on-line observation of human motion. The observed motion time ...
Dana Kulic, Wataru Takano, Yoshihiko Nakamura