Sciweavers

629 search results - page 50 / 126
» Large Scale Learning of Active Shape Models
Sort
View
ICML
2005
IEEE
15 years 10 months ago
Harmonic mixtures: combining mixture models and graph-based methods for inductive and scalable semi-supervised learning
Graph-based methods for semi-supervised learning have recently been shown to be promising for combining labeled and unlabeled data in classification problems. However, inference f...
Xiaojin Zhu, John D. Lafferty
ISWC
2006
IEEE
15 years 3 months ago
Towards Less Supervision in Activity Recognition from Wearable Sensors
Activity Recognition has gained a lot of interest in recent years due to its potential and usefulness for context-aware wearable computing. However, most approaches for activity r...
Tâm Huynh, Bernt Schiele
BCSHCI
2008
14 years 11 months ago
Provoking creative design: making it scale
Creativity is indispensable for more innovative interactive system development. This tutorial is relevant to anyone involved in large projects that are exploiting new technologies...
Neil A. M. Maiden, Sara Jones
MM
2009
ACM
252views Multimedia» more  MM 2009»
15 years 4 months ago
Localizing volumetric motion for action recognition in realistic videos
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge ca...
Xiao Wu, Chong-Wah Ngo, Jintao Li, Yongdong Zhang
ECCV
2010
Springer
15 years 3 months ago
Convolutional learning of spatio-temporal features
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...