The Pyramid Match Kernel: Efficient Learning with Sets of Features
The Journal of Machine Learning Research
Image retrieval on large-scale image databases
Proceedings of the 6th ACM international conference on Image and video retrieval
Representing shape with a spatial pyramid kernel
Proceedings of the 6th ACM international conference on Image and video retrieval
Constructing visual phrases for effective and efficient object-based image retrieval
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection
International Journal of Computer Vision
Spirittagger: a geo-aware tag suggestion tool mined from flickr
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Semantic lattices for multiple annotation of images
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Weakly Supervised Object Localization with Stable Segmentations
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
A Multimodal Constellation Model for Object Category Recognition
MMM '09 Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia Modeling
Unsupervised modeling of objects and their hierarchical contextual interactions
Journal on Image and Video Processing - Special issue on patches in vision
Contextual classification of image patches with latent aspect models
Journal on Image and Video Processing - Special issue on patches in vision
Places clustering of full-length film key-framesusing latent aspect modeling over SIFT matches
IEEE Transactions on Circuits and Systems for Video Technology
OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning
International Journal of Computer Vision
Per-sample multiple kernel approach for visual concept learning
Journal on Image and Video Processing - Special issue on selected papers from multimedia modeling conference 2009
Scene categorization using boosted back-propagation neural networks
PCM'10 Proceedings of the 11th Pacific Rim conference on Advances in multimedia information processing: Part I
A novel approach for robust surveillance video content abstraction
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
A multimodal constellation model for object image classification
Journal on Image and Video Processing - Special issue on selected papers from multimedia modeling conference 2009
Semantics extraction from images
Knowledge-driven multimedia information extraction and ontology evolution
Not far away from home: a relational distance-based approach to understanding images of houses
ILP'10 Proceedings of the 20th international conference on Inductive logic programming
Semantic hierarchies for image annotation: A survey
Pattern Recognition
A robust approach for object recognition
PCM'06 Proceedings of the 7th Pacific Rim conference on Advances in Multimedia Information Processing
An intrinsic semantic framework for recognizing image objects
Multimedia Tools and Applications
Learning structured visual dictionary for object tracking
Image and Vision Computing
International Journal of Computer Vision
Multimedia Tools and Applications
Hi-index | 0.00 |
"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are modeled as basic building blocks of an image, analogous to words in text documents. In most previous works using the "bag of words" models (e.g. [4, 20, 7]), the local patches are assumed to be independent with each other. In this paper, we relax the independence assumption and model explicitly the inter-dependency of the local regions. Similarly to previous work , we represent images as a collection of patches, each of which belongs to a latent "theme" that is shared across images as well as categories. We learn the theme distributions and patch distributions over the themes in a hierarchical structure [22]. In particular, we introduce a linkage structure over the latent themes to encode the dependencies of the patches. This structure enforces the semantic connections among the patches by facilitating better clustering of the themes. As a result, our models for object categories tend to be more discriminative than the ones obtained under the independent patch assumption. We show highly competitive categorization results on both the Caltech 4 and Caltech 101 object category datasets. By examining the distributions of the latent themes for each object category, we construct an object taxonomy using the 101 object classes from the Caltech 101 datasets.