Termín obdržení zásilky
Česká pošta Pondělí 03.06
PPL Pondělí 03.06
Osobní odběr Úterý 04.06
Termíny jsou pouze orientační a mohou se lišit podle zvoleného typu platby. O Průběhu zásilky Vás budeme informovat e-mailem.
Při nákupu většího množství produktů negarantujeme dodání do zobrazeného data

Structural, Syntactic, and Statistical Pattern Recognition

Structural, Syntactic, and Statistical Pattern Recognition
47 %

1021  Kč 1 941 Kč

Sleva až 70% u třetiny knih
Classification and Clustering.- Image annotation using a semantic hierarchy.- Malignant Brain Tumor Classification using the Random Forest Method.- Rotationally Invariant Bark Recognition.- Dynamic voting in multi-view learning for radiomics applications.- Iterative Deep Subspace Clustering.- A scalable spectral clustering algorithm based on landmark-embedding and cosine similarity.- Deep Learning and Neural Networks.- On Fast Sample Preselection for Speeding up Convolutional Neural Network Training.- UAV First View Landmark Localization via Deep Reinforcement Learning.- Context Free Band Reduction Using a Convolutional Neural Network.- Local Patterns and Supergraph for Chemical Graph Classification with Convolutional Networks.- Learning Deep Embeddings via Margin-based Discriminate Loss.- Dissimilarity Representations and Gaussian Processes.- Protein Remote Homology Detection using Dissimilarity-based Multiple Instance Learning.- Local Binary Patterns based on Subspace Representation of Image Patch for Face Recognition.- An image-based representation for graph classification.- Visual Tracking via Patch-based Absorbing Markov Chain.- Gradient Descent for Gaussian Processes Variance Reduction.- Semi and Fully Supervised Learning Methods.- Sparsification of Indefinite Learning Models.- Semi-supervised Clustering Framework Based on Active Learning for Real Data.- Supervised Classification Using Feature Space Partitioning.- Deep Homography Estimation with Pairwise Invertibility Constraint.- Spatio-temporal Pattern Recognition and Shape Analysis.- Graph Time Series Analysis using Transfer Entropy.- Analyzing Time Series from Chinese Financial Market Using A Linear-Time Graph Kernel.- A Preliminary Survey of Analyzing Dynamic Time-varying Financial Networks Using Graph Kernels.- Few-Example Affine Invariant Ear Detection in the Wild.- Line Voronoi Diagram using Elliptical Distances.- Structural Matching.- Modelling the Generalised Median Correspondence through an Edit Distance.- Learning the Graph Edit Distance edit costs based on an embedded model.- Ring Based Approximation of Graph Edit Distance.- Graph Edit Distance in the exact context.- The VF3-Light Subgraph Isomorphism Algorithm: when doing less is more effective.- A Deep Neural Network Architecture to Estimate Node Assignment Costs for the Graph Edit Distance.- Error-Tolerant Geometric Graph Similarity.- Learning Cost Functions for Graph Matching.- Multimedia Analysis and Understanding.- Matrix Regression-based Classification for Face Recognition.- Plenoptic Imaging for Seeing Through Turbulence.- Weighted Local Mutual Information for 2D-3D Registration in Vascular Interventions.- Cross-model Retrieval with Reconstruct Hashing.- Deep Supervised Hashing with Information Loss.- Single Image Super Resolution via Neighbor Reconstruction.- An Efficient Method for Boundary Detection from Hyperspectral Imagery.- Graph-Theoretic Methods.- Bags of Graphs for Human Action Recognition.- Categorization of RNA Molecules using Graph Methods.- Quantum Edge Entropy for Alzheimer's Disease Analysis.- Approximating GED using a Stochastic Generator and Multistart IPFP.- Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks.- On Association Graph Techniques for Hypergraph Matching.- Directed Network Analysis using Transfer Entropy Component Analysis.- A Mixed Entropy Local-Global Reproducing Kernel for Attributed Graphs.- Dirichlet Densifiers: Beyond Constraining the Spectral Gap.
Autor:
Nakladatel: Springer, Berlin
Rok vydání: 2018
Jazyk : Angličtina
Vazba: Paperback / softback
Mohlo by se vám také líbit..