Automatic large scale video object recognition
作者： Jay Yagnik , Ming Zhao
DOI:
关键词: Representation (systemics) 、 Feature vector 、 Object (computer science) 、 Cognitive neuroscience of visual object recognition 、 Dimensionality reduction 、 Computer science 、 Set (abstract data type) 、 Pattern recognition 、 Computer vision 、 Association (object-oriented programming) 、 Consistency (database systems) 、 Artificial intelligence
摘要: An object recognition system performs a number of rounds dimensionality reduction and consistency learning on visual content items such as videos still images, resulting in set feature vectors that accurately predict the presence represented by given name within an item. The are stored association with which they represent indication produced them. can be used for various purposes, quickly determining item containing representation name.
lens.org 参考文章(37)
Peter K. Willett, Robert S. Lynch, Automatic feature selection system for data containing missing values ,(2000)
Yuri Owechko, Swarup Medasani, Object recognition using a congnitive swarm vision framework with attention mechanisms ,(2006)
Shang-Hung Lin, Sun-Yuan Kung, Long-Ji Lin, Ming Fang, Neural network for locating and recognizing a deformable object ,(1995)
Juan Carlos Niebles, Bohyung Han, Andras Ferencz, Li Fei-Fei, Extracting Moving People from Internet Videos european conference on computer vision. pp. 527- 540 ,(2008) , 10.1007/978-3-540-88693-8_39
Stephane Chiocchetti, George H. Forman, Preparing data for machine learning ,(2004)
Peter K. Willett, Robert S. Lynch, Data clustering method for bayesian data reduction ,(2006)
Toshio Kamei, Face meta-data generation and face similarity calculation ,(2002)
Mehran Sahami, Daphne Koller, Hierarchically Classifying Documents Using Very Few Words international conference on machine learning. pp. 170- 178 ,(1997)
Sally A. Goldman, Yan Zhou, Enhancing Supervised Learning with Unlabeled Data international conference on machine learning. pp. 327- 334 ,(2000)
Andreas Girgensohn, Lynn Wilcox, Jonathan T. Foote, Methods and apparatuses for interactive similarity searching, retrieval and browsing of video ,(2004)