1837 search results - page 298 / 368 » Learning From Ambiguous Examples |
127
Voted
EMNLP
2009
15 years 13 days ago
2009
Semantic Role Labeling (SRL) has proved to be a valuable tool for performing automatic analysis of natural language texts. Currently however, most systems rely on a large training...
116
Voted
ICMLA
2009
15 years 11 days ago
2009
We describe a generative model for graph edges under specific degree distributions which admits an exact and efficient inference method for recovering the most likely structure. T...
120
Voted
IUI
2012
ACM
13 years 10 months ago
2012
ACM
Recent computer vision approaches are aimed at richer image interpretations that extend the standard recognition of objects in images (e.g., cars) to also recognize object attribu...
158
Voted
CVPR
2008
IEEE
16 years 4 months ago
2008
IEEE
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
151
Voted
NIPS
2008
15 years 4 months ago
2008
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...