000789887 000__ 03789cam\a2200505Ii\4500
000789887 001__ 789887
000789887 005__ 20230306143346.0
000789887 006__ m\\\\\o\\d\\\\\\\\
000789887 007__ cr\cn\nnnunnun
000789887 008__ 170619t20172017si\a\\\\ob\\\\000\0\eng\d
000789887 019__ $$a990714045$$a991562449
000789887 020__ $$a9789811048401$$q(electronic book)
000789887 020__ $$a9811048401$$q(electronic book)
000789887 020__ $$z9789811048395
000789887 035__ $$aSP(OCoLC)ocn990267777
000789887 035__ $$aSP(OCoLC)990267777$$z(OCoLC)990714045$$z(OCoLC)991562449
000789887 040__ $$aN$T$$beng$$erda$$epn$$cN$T$$dN$T$$dGW5XE$$dEBLCP$$dYDX$$dOCLCF$$dUAB
000789887 049__ $$aISEA
000789887 050_4 $$aTK7882.P3
000789887 08204 $$a006.3$$223
000789887 1001_ $$aWang, Hongxing,$$eauthor.
000789887 24510 $$aVisual pattern discovery and recognition /$$cHongxing Wang, Chaoqun Weng, Junsong Yuan.
000789887 264_1 $$aSingapore :$$bSpringer,$$c[2017]
000789887 264_4 $$c©2017
000789887 300__ $$a1 online resource :$$bcolor illustrations.
000789887 336__ $$atext$$btxt$$2rdacontent
000789887 337__ $$acomputer$$bc$$2rdamedia
000789887 338__ $$aonline resource$$bcr$$2rdacarrier
000789887 4901_ $$aSpringerBriefs in computer science,$$x2191-5776
000789887 504__ $$aIncludes bibliographical references.
000789887 5050_ $$aPreface; Acknowledgements; Contents; 1 Introduction; 1.1 Overview; 1.2 Discovering Spatial Co-occurrence Patterns; 1.3 Discovering Feature Co-occurrence Patterns; 1.4 Outline of the Book; References; 2 Context-Aware Discovery of Visual Co-occurrence Patterns; 2.1 Introduction; 2.2 Multi-context-aware Clustering; 2.2.1 Regularized k-means Formulation with Multiple Contexts; 2.2.2 Self-learning Optimization; 2.3 Experiments; 2.3.1 Spatial Visual Pattern Discovery; 2.3.2 Image Region Clustering Using Multiple Contexts; 2.4 Summary of this Chapter; References
000789887 5058_ $$a3 Hierarchical Sparse Coding for Visual Co-occurrence Discovery3.1 Introduction; 3.2 Spatial Context-Aware Multi-feature Sparse Coding; 3.2.1 Learning Spatial Context-Aware Visual Phrases; 3.2.2 Learning Multi-feature Fused Visual Phrases; 3.3 Experiments; 3.3.1 Spatial Visual Pattern Discovery; 3.3.2 Scene Clustering; 3.3.3 Scene Categorization; 3.4 Summary of this Chapter; References; 4 Feature Co-occurrence for Visual Labeling; 4.1 Introduction; 4.2 Multi-feature Collaboration for Transductive Learning; 4.2.1 Spectral Embedding of Multi-feature Data
000789887 5058_ $$a4.2.2 Embedding Co-occurrence for Data Representation4.2.3 Transductive Learning with Feature Co-occurrence Patterns; 4.2.4 Collaboration Between Pattern Discovery and Label Propagation; 4.3 Experiments; 4.3.1 Experimental Setting; 4.3.2 Label Propagation on Synthetic Data; 4.3.3 Digit Recognition; 4.3.4 Object Recognition; 4.3.5 Body Motion Recognition; 4.3.6 Scene Recognition; 4.4 Summary of this Chapter; References; 5 Visual Clustering with Minimax Feature Fusion; 5.1 Introduction; 5.2 Minimax Optimization for Multi-feature Spectral Clustering
000789887 5058_ $$a5.2.1 Spectral Embedding for Regularized Data-Cluster Similarity Matrix5.2.2 Minimax Fusion; 5.2.3 Minimax Optimization; 5.3 Experiments; 5.3.1 Datasets and Experimental Setting; 5.3.2 Baseline Algorithms; 5.3.3 Evaluation Metrics; 5.3.4 Experimental Results; 5.3.5 Convergence Analysis; 5.3.6 Sensitivity of Parameters; 5.4 Summary of this Chapter; References; 6 Conclusion; References
000789887 506__ $$aAccess limited to authorized users.
000789887 588__ $$aOnline resource; title from PDF title page (viewed June 20, 2017).
000789887 650_0 $$aPattern recognition systems.
000789887 650_0 $$aComputer vision.
000789887 7001_ $$aWeng, Chaoqun,$$eauthor.
000789887 7001_ $$aYuan, Junsong,$$eauthor.
000789887 830_0 $$aSpringerBriefs in computer science.
000789887 852__ $$bebk
000789887 85640 $$3SpringerLink$$uhttps://univsouthin.idm.oclc.org/login?url=http://link.springer.com/10.1007/978-981-10-4840-1$$zOnline Access$$91397441.1
000789887 909CO $$ooai:library.usi.edu:789887$$pGLOBAL_SET
000789887 980__ $$aEBOOK
000789887 980__ $$aBIB
000789887 982__ $$aEbook
000789887 983__ $$aOnline
000789887 994__ $$a92$$bISE