Sciweavers

242 search results - page 7 / 49
» Learning human actions via information maximization
Sort
View
98
Voted
AAAI
2012
13 years 2 months ago
Dynamic Matching via Weighted Myopia with Application to Kidney Exchange
In many dynamic matching applications—especially high-stakes ones—the competitive ratios of prior-free online algorithms are unacceptably poor. The algorithm should take distr...
John P. Dickerson, Ariel D. Procaccia, Tuomas Sand...
88
Voted
ICML
2009
IEEE
16 years 14 days ago
Robust feature extraction via information theoretic learning
In this paper, we present a robust feature extraction framework based on informationtheoretic learning. Its formulated objective aims at simultaneously maximizing the Renyi's...
Xiaotong Yuan, Bao-Gang Hu
86
Voted
CVPR
2008
IEEE
16 years 1 months ago
Action recognition by learning mid-level motion features
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
Alireza Fathi, Greg Mori
ICRA
2005
IEEE
138views Robotics» more  ICRA 2005»
15 years 5 months ago
The Role of Motion Information in Learning Human-Robot Joint Attention
— To realize natural human-robot interactions and investigate the developmental mechanism of human communication, an effective approach is to construct models by which a robot im...
Yukie Nagai
CVPR
2007
IEEE
16 years 1 months ago
Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitabl...
Alessandro Bissacco, Ming-Hsuan Yang, Stefano Soat...