Bienvenue chez nous !
Logo Ex Libris
 Laissez-vous inspirer ! 

Visual Attributes

  • Livre Relié
  • 364 Nombre de pages
(0) Donner la première évaluation
Évaluations
(0)
(0)
(0)
(0)
(0)
Afficher toutes les évaluations
This unique text/reference provides a detailed overview of the latest advances in machine learning and computer vision related to ... Lire la suite
CHF 179.00
Impression sur demande - l'exemplaire sera recherché pour vous.
Pas de droit de retour !
Commande avec livraison dans une succursale

Description

This unique text/reference provides a detailed overview of the latest advances in machine learning and computer vision related to visual attributes, highlighting how this emerging field intersects with other disciplines, such as computational linguistics and human-machine interaction. Topics and features: presents attribute-based methods for zero-shot classification, learning using privileged information, and methods for multi-task attribute learning; describes the concept of relative attributes, and examines the effectiveness of modeling relative attributes in image search applications; reviews state-of-the-art methods for estimation of human attributes, and describes their use in a range of different applications; discusses attempts to build a vocabulary of visual attributes; explores the connections between visual attributes and natural language; provides contributions from an international selection of world-renowned scientists, covering both theoretical aspects and practical applications.



The first book to introduce the topic of visual attributes, and cover emerging concepts such as zero-shot learning

Covers theoretical aspects of visual attribute learning, as well as practical computer vision applications

Includes contributions from world-renowned scientists in machine learning and computer vision, and at the intersection with computational linguistics and human-machine interaction



Auteur

Dr. Rogerio Schmidt Feris is a manager at IBM T.J. Watson Research Center, New York, USA, where he leads research in computer vision and machine learning.

Dr. Christoph H. Lampert is a professor at the Institute of Science and Technology Austria, where he serves as the Principal Investigator of the Computer Vision and Machine Learning Group.

Dr. Devi Parikh is an assistant professor in the School of Interactive Computing at Georgia Tech, USA, where she leads the Computer Vision Lab.



Contenu
Introduction to Visual Attributes Rogerio Feris, Christoph Lampert, and Devi Parikh Part I: Attribute-Based Recognition An Embarrassingly Simple Approach to Zero-Shot Learning Bernardino Romera-Paredes and Philip H. S. Torr In the Era of Deep Convolutional Features: Are Attributes still Useful Privileged Data? Viktoriia Sharmanska and Novi Quadrianto Divide, Share, and Conquer: Multi-Task Attribute Learning with Selective Sharing Chao-Yeh Chen, Dinesh Jayaraman, Fei Sha, and Kristen Grauman Part II: Relative Attributes and their Application to Image Search Attributes for Image Retrieval Adriana Kovashka and Kristen Grauman Fine-Grained Comparisons with Attributes Aron Yu and Kristen Grauman Localizing and Visualizing Relative Attributes Fanyi Xiao and Yong Jae Lee Part III: Describing People Based on Attributes Deep Learning Face Attributes for Detection and Alignment Chen Change Loy, Ping Luo, and Chen Huang Visual Attributes for Fashion Analytics Si Liu, Lisa Brown, Qiang Chen, Junshi Huang, Luoqi Liu, and Shuicheng Yan Part IV: Defining a Vocabulary of Attributes A Taxonomy of Part and Attribute Discovery Techniques Subhransu Maji The SUN Attribute Database: Organizing Scenes by Affordances, Materials, and Layout Genevieve Patterson and James Hays Part V: Attributes and Language Attributes as Semantic Units Between Natural Language and Visual Recognition Marcus Rohrbach Grounding the Meaning of Words with Visual Attributes Carina Silberer

Informations sur le produit

Titre: Visual Attributes
Éditeur:
Code EAN: 9783319500751
ISBN: 978-3-319-50075-1
Format: Livre Relié
Editeur: Springer, Berlin
Genre: Informatique
nombre de pages: 364
Poids: 756g
Taille: H23mm x B249mm x T166mm
Année: 2017
Auflage: 1st ed. 2017

Autres articles de cette série  "Advances in Computer Vision and Pattern Recognition"