Sciweavers

4263 search results - page 387 / 853
» Learning without Coding
Sort
View
ICIP
2009
IEEE
15 years 4 months ago
Automatic scene relighting for video conferencing
This paper describes a new method to automatically improve scene lighting for video conferencing by learning the photometric mapping between a lower exposure and desired exposure ...
Stephen Mangiat, Jerry Gibson
TNN
2010
130views Management» more  TNN 2010»
15 years 1 months ago
Large developing receptive fields using a distributed and locally reprogrammable address-event receiver
A distributed and locally reprogrammable address event receiver has been designed, in which incoming addressevents are monitored simultaneously by all synapses, allowing for arbitr...
Simeon A. Bamford, Alan F. Murray, David J. Willsh...
ICANN
2011
Springer
14 years 10 months ago
Bias of Importance Measures for Multi-valued Attributes and Solutions
Attribute importance measures for supervised learning are important for improving both learning accuracy and interpretability. However, it is well-known there could be bias when th...
Houtao Deng, George C. Runger, Eugene Tuv
AAAI
2011
14 years 6 months ago
Differential Eligibility Vectors for Advantage Updating and Gradient Methods
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
Francisco S. Melo

Publication
336views
13 years 11 months ago
Feature Mining for Localised Crowd Counting
This paper presents a multi-output regression model for crowd counting in public scenes. Existing counting by regression methods either learn a single model for global counting, or...
Ke Chen, Chen Change Loy, Shaogang Gong, Tao Xiang...