Sciweavers

328 search results - page 35 / 66
» On Approximating Multidimensional Probability Distributions ...
Sort
View
AVSS
2008
IEEE
14 years 3 months ago
Object and Scene-Centric Activity Detection Using State Occupancy Duration Modeling
We propose a video event analysis framework based on object segmentation and tracking, combined with a Hidden Semi-Markov Model (HSMM) that uses state occupancy duration modeling....
Murtaza Taj, Andrea Cavallaro
TNN
2008
177views more  TNN 2008»
13 years 8 months ago
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting...
Yoshua Bengio, Jean-Sébastien Senecal
GECCO
2007
Springer
210views Optimization» more  GECCO 2007»
14 years 2 months ago
Markov chain models of bare-bones particle swarm optimizers
We apply a novel theoretical approach to better understand the behaviour of different types of bare-bones PSOs. It avoids many common but unrealistic assumptions often used in an...
Riccardo Poli, William B. Langdon
INTERSPEECH
2010
13 years 3 months ago
Extractive summarization using a latent variable model
Extractive multi-document summarization is the task of choosing sentences from a set of documents to compose a summary text in response to a user query. We propose a generative ap...
Asli Çelikyilmaz, Dilek Hakkani-Tür
CVPR
2007
IEEE
14 years 10 months ago
Optimizing Distribution-based Matching by Random Subsampling
We boost the efficiency and robustness of distributionbased matching by random subsampling which results in the minimum number of samples required to achieve a specified probabili...
Alex Po Leung, Shaogang Gong