Contextual Classification of Image Patches with Latent Aspect Models
We present a novel approach for contextual classification of image patches in complex visual scenes, based on the use of histograms of quantized features and probabilistic aspect models. Our approach uses context in two ways: (1) by using the fact that specific learned aspects correlate with the sem...
Main Authors: | Florent Monay, Pedro Quelhas, Jean-Marc Odobez, Daniel Gatica-Perez |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2009-02-01
|
Series: | EURASIP Journal on Image and Video Processing |
Online Access: | http://dx.doi.org/10.1155/2009/602920 |
Similar Items
-
Contextual Classification of Image Patches with Latent Aspect Models
by: Quelhas Pedro, et al.
Published: (2009-01-01) -
A Latent Source Model for Patch-Based Image Segmentation
by: Shah, Devavrat, et al.
Published: (2018) -
Contextual Graph Attention Network for Aspect-Level Sentiment Classification
by: Yuqing Miao, et al.
Published: (2022-07-01) -
Patch-based Segmentation of Latent Fingerprint Images Using Convolutional Neural Network
by: Asif Iqbal Khan, et al.
Published: (2019-01-01) -
Latent Demand and Time Contextual Constraints to Outdoor Recreation in Sweden
by: Daniel Wolf-Watz, et al.
Published: (2011-12-01)