International Journal of Computer Vision
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Metric for Distributions with Applications to Image Databases
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Probabilistic Kernels for the Classification of Auto-Regressive Visual Processes
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Local Binary Pattern Descriptors for Dynamic Texture Recognition
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
Proceedings of the 24th international conference on Machine learning
Representing shape with a spatial pyramid kernel
Proceedings of the 6th ACM international conference on Image and video retrieval
Dynamic texture recognition using volume local binary patterns
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
Dynamic texture recognition using normal flow and texture regularity
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II
Shift-Invariant dynamic texture recognition
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
IEEE Transactions on Signal Processing
A phase-based approach to the estimation of the optical flow field using spatial filtering
IEEE Transactions on Neural Networks
Volume local phase quantization for blur-insensitive dynamic texture classification
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Scale-space texture description on SIFT-like textons
Computer Vision and Image Understanding
Local phase quantization for blur-insensitive image analysis
Image and Vision Computing
Directional space-time oriented gradients for 3d visual pattern analysis
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Texture databases - A comprehensive survey
Pattern Recognition Letters
Hi-index | 0.00 |
The range space of dynamic textures spans spatiotemporal phenomena that vary along three fundamental dimensions: spatial texture, spatial texture layout, and dynamics. By describing each dimension with appropriate spatial or temporal features and by equipping it with a suitable distance measure, elementary distances (one for each dimension) between dynamic texture sequences can be computed. In this paper, we address the problem of dynamic texture (DT) recognition by learning linear combinations of these elementary distances. By learning weights to these distances, we shed light on how "salient" (in a discriminative manner) each DT dimension is in representing classes of dynamic textures. To do this, we propose an efficient maximum margin distance learning (MMDL) method based on the Pegasos algorithm [1], for both classindependent and class-dependent weight learning. In contrast to popular MMDL methods, which enforce restrictive distance constraints and have a computational complexity that is cubic in the number of training samples, we show that our method, called DL-PEGASOS, can handle more general distance constraints with a computational complexity that can be made linear. When class dependent weights are learned, we show that, for certain classes of DTs, spatial texture features are dominantly "salient", while for other classes, this "saliency" lies in their temporal features. Furthermore, DL-PEGASOS outperforms state-of-the-art recognition methods on the UCLA benchmark DT dataset. By learning class independent weights, we show that this benchmark does not offer much variety along the three DT dimensions, thus, motivating the proposal of a new DT dataset, called DynTex++.