Sciweavers

7928 search results - page 1379 / 1586
» Human-Like Learning Methods for a
Sort
View
TMM
2010
199views Management» more  TMM 2010»
15 years 1 months ago
Video Annotation Through Search and Graph Reinforcement Mining
Abstract--Unlimited vocabulary annotation of multimedia documents remains elusive despite progress solving the problem in the case of a small, fixed lexicon. Taking advantage of th...
Emily Moxley, Tao Mei, Bangalore S. Manjunath
ICASSP
2011
IEEE
14 years 10 months ago
Beyond bag of words: Combining generative and discriminative models for natural scene categorization
This paper proposes a simple yet new and effective framework by combining generative model and discriminative model for natural scene categorization. A state-of-the-art approach f...
Zhen Li, Kim-Hui Yap, Xiao-Ming Chen
ICASSP
2011
IEEE
14 years 10 months ago
A supervised approach to movie emotion tracking
In this paper, we present experiments on continuous time, continuous scale affective movie content recognition (emotion tracking). A major obstacle for emotion research has been t...
Nikos Malandrakis, Alexandros Potamianos, Georgios...
ICASSP
2011
IEEE
14 years 10 months ago
A hierarchical generative model for Generic Audio Document Categorization
In this paper, we call the pattern classification problem that consists in assigning a category label to a long audio signal based on its semantic content as Generic Audio Documen...
Zhi Zeng, Shuwu Zhang
ICASSP
2011
IEEE
14 years 10 months ago
Nonstationary and temporally correlated source separation using Gaussian process
Blind source separation (BSS) is a process to reconstruct source signals from the mixed signals. The standard BSS methods assume a fixed set of stationary source signals with the ...
Hsin-Lung Hsieh, Jen-Tzung Chien
« Prev « First page 1379 / 1586 Last » Next »