Part 1: Bag-of-words models by Li Fei-Fei (Princeton) Related works Early “bag o

Part 1: Bag-of-words models by Li Fei-Fei (Princeton) Related works Early “bag o www.phwiki.com

Part 1: Bag-of-words models by Li Fei-Fei (Princeton) Related works Early “bag o

Davis, George, News Director has reference to this Academic Journal, PHwiki organized this Journal Part 1: Bag-of-words models by Li Fei-Fei (Princeton) Related works Early “bag of words” models: mostly texture recognition Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003; Hierarchical Bayesian models as long as documents (pLSA, LDA, etc.) Hoffman 1999; Blei, Ng & Jordan, 2004; Teh, Jordan, Beal & Blei, 2004 Object categorization Csurka, Bray, Dance & Fan, 2004; Sivic, Russell, Efros, Freeman & Zisserman, 2005; Sudderth, Torralba, Freeman & Willsky, 2005; Natural scene categorization Vogel & Schiele, 2004; Fei-Fei & Perona, 2005; Bosch, Zisserman & Munoz, 2006

Hanover College US www.phwiki.com

This Particular University is Related to this Particular Journal

Analogy to documents Of all the sensory impressions proceeding to the brain, the visual experiences are the dominant ones. Our perception of the world around us is based essentially on the messages that reach the brain from our eyes. For a long time it was thought that the retinal image was transmitted point by point to visual centers in the brain; the cerebral cortex was a movie screen, so to speak, upon which the image in the eye was projected. Through the discoveries of Hubel in addition to Wiesel we now know that behind the origin of the visual perception in the brain there is a considerably more complicated course of events. By following the visual impulses along their path to the various cell layers of the optical cortex, Hubel in addition to Wiesel have been able to demonstrate that the message about the image falling on the retina undergoes a step-wise analysis in a system of nerve cells stored in columns. In this system each cell has its specific function in addition to is responsible as long as a specific detail in the pattern of the retinal image. A clarification: definition of “BoW” Looser definition Independent features A clarification: definition of “BoW” Looser definition Independent features Stricter definition Independent features histogram representation

Representation 1. 2. 3. 1.Feature detection in addition to representation

1.Feature detection in addition to representation Regular grid Vogel & Schiele, 2003 Fei-Fei & Perona, 2005 1.Feature detection in addition to representation Regular grid Vogel & Schiele, 2003 Fei-Fei & Perona, 2005 Interest point detector Csurka, et al. 2004 Fei-Fei & Perona, 2005 Sivic, et al. 2005 1.Feature detection in addition to representation Regular grid Vogel & Schiele, 2003 Fei-Fei & Perona, 2005 Interest point detector Csurka, Bray, Dance & Fan, 2004 Fei-Fei & Perona, 2005 Sivic, Russell, Efros, Freeman & Zisserman, 2005 Other methods R in addition to om sampling (Vidal-Naquet & Ullman, 2002) Segmentation based patches (Barnard, Duygulu, Forsyth, de Freitas, Blei, Jordan, 2003)

1.Feature detection in addition to representation Normalize patch Detect patches [Mikojaczyk in addition to Schmid ’02] [Mata, Chum, Urban & Pajdla, ’02] [Sivic & Zisserman, ’03] Compute SIFT descriptor [Lowe’99] Slide credit: Josef Sivic 1.Feature detection in addition to representation 2. Codewords dictionary as long as mation

2. Codewords dictionary as long as mation Vector quantization Slide credit: Josef Sivic 2. Codewords dictionary as long as mation Fei-Fei et al. 2005 Image patch examples of codewords Sivic et al. 2005

3. Image representation frequency codewords Representation 1. 2. 3. category models ( in addition to /or) classifiers Learning in addition to Recognition

category models ( in addition to /or) classifiers Learning in addition to Recognition Generative method: – graphical models Discriminative method: – SVM Naïve Bayes classifier Csurka Bray, Dance & Fan, 2004 Hierarchical Bayesian text models (pLSA in addition to LDA) Background: Hoffman 2001, Blei, Ng & Jordan, 2004 Object categorization: Sivic et al. 2005, Sudderth et al. 2005 Natural scene categorization: Fei-Fei et al. 2005 2 generative models wn: each patch in an image wn = [0,0, 1, ,0,0]T w: a collection of all N patches in an image w = [w1,w2, ,wN] dj: the jth image in an image collection c: category of the image z: theme or topic of the patch First, some notations

Davis, George KAFF-FM News Director www.phwiki.com

w N c Case 1: the Naïve Bayes model Csurka et al. 2004 Csurka et al. 2004 Csurka et al. 2004

Hoffman, 2001 Case 2: Hierarchical Bayesian text models Blei et al., 2001 Probabilistic Latent Semantic Analysis (pLSA) Latent Dirichlet Allocation (LDA) Case 2: Hierarchical Bayesian text models Probabilistic Latent Semantic Analysis (pLSA) Sivic et al. ICCV 2005 Case 2: Hierarchical Bayesian text models Latent Dirichlet Allocation (LDA) Fei-Fei et al. ICCV 2005

No rigorous geometric in as long as mation of the object components It’s intuitive to most of us that objects are made of parts – no such in as long as mation Not extensively tested yet as long as View point invariance Scale invariance Segmentation in addition to localization unclear Weakness of the model

Davis, George News Director

Davis, George is from United States and they belong to KAFF-FM and they are from  Flagstaff, United States got related to this Particular Journal. and Davis, George deal with the subjects like International News; Local News; National News; Regional News

Journal Ratings by Hanover College

This Particular Journal got reviewed and rated by Hanover College and short form of this particular Institution is US and gave this Journal an Excellent Rating.