Sciweavers

836 search results - page 36 / 168
» Object Recognition with Informative Features and Linear Clas...
Sort
View
ICCV
2007
IEEE
14 years 9 months ago
Vector Quantizing Feature Space with a Regular Lattice
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
Tinne Tuytelaars, Cordelia Schmid
ICPR
2010
IEEE
14 years 6 days ago
Symbol Classification Using Dynamic Aligned Shape Descriptor
Shape representation is a difficult task because of several symbol distortions, such as occlusions, elastic deformations, gaps or noise. In this paper, we propose a new descriptor ...
Alicia Fornés, Sergio Escalera, Josep Llados, Ern...
MVA
2007
207views Computer Vision» more  MVA 2007»
13 years 9 months ago
View-invariant Human Action Recognition Based on Factorization and HMMs
of the fundamental challenges of human action recognition is accounting for the variability that arises during video capturing. For a specific action class, the 2D observations of...
Xi Li, Kazuhiro Fukui
MIR
2010
ACM
167views Multimedia» more  MIR 2010»
14 years 2 months ago
Improving automatic music classification performance by extracting features from different types of data
This paper discusses two sets of automatic musical genre classification experiments. Promising research directions are then proposed based on the results of these experiments. The...
Cory McKay, Ichiro Fujinaga
SIGIR
2010
ACM
13 years 11 months ago
Multilabel classification with meta-level features
Effective learning in multi-label classification (MLC) requires an ate level of abstraction for representing the relationship between each instance and multiple categories. Curren...
Siddharth Gopal, Yiming Yang