Английская грамматика
<<  По русскому междометие как часть речи Content-Based Image Retrieval using the Bag-of-Words Concept  >>
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Analogy to documents
Analogy to documents
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
A clarification: definition of “BoW”
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
Part 1: Bag-of-words models
1.Feature detection and representation
1.Feature detection and representation
1.Feature detection and representation
1.Feature detection and representation
1.Feature detection and representation
1.Feature detection and representation
Learning and Recognition
Learning and Recognition
Learning and Recognition
Learning and Recognition
Csurka et al
Csurka et al
Csurka et al
Csurka et al
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: Hierarchical Bayesian text models
Case #2: the pLSA model
Case #2: the pLSA model
Case #2: the pLSA model
Case #2: the pLSA model
Case #2: Learning the pLSA parameters
Case #2: Learning the pLSA parameters
Demo
Demo
Demo: feature detection
Demo: feature detection
Demo: learnt parameters
Demo: learnt parameters
Discriminative methods based on ‘bag of words’ representation
Discriminative methods based on ‘bag of words’ representation
Discriminative methods based on ‘bag of words’ representation
Discriminative methods based on ‘bag of words’ representation
Discriminative methods based on ‘bag of words’ representation
Discriminative methods based on ‘bag of words’ representation
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Summary: Pyramid match kernel
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid Match (Grauman & Darrell 2005)
Pyramid match kernel
Pyramid match kernel
Pyramid match kernel
Pyramid match kernel
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Example pyramid match
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
Object recognition results
?
?
?
?
?
?
?
?
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
What about spatial info
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Invariance issues
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Model properties
Картинки из презентации «Part 1: Bag-of-words models» к уроку английского языка на тему «Английская грамматика»

Автор: Rob Fergus. Чтобы познакомиться с картинкой полного размера, нажмите на её эскиз. Чтобы можно было использовать все картинки для урока английского языка, скачайте бесплатно презентацию «Part 1: Bag-of-words models.ppt» со всеми картинками в zip-архиве размером 10265 КБ.

Part 1: Bag-of-words models

содержание презентации «Part 1: Bag-of-words models.ppt»
Сл Текст Сл Текст
1Part 1: Bag-of-words models. by Li 34Maximize likelihood of data using EM.
Fei-Fei (Princeton). Observed counts of word i in document j. M
2Related works. Early “bag of words” … number of codewords N … number of
models: mostly texture recognition Cula images. Slide credit: Josef Sivic.
& Dana, 2001; Leung & Malik 2001; 35Demo. Course website.
Mori, Belongie & Malik, 2001; Schmid 36task: face detection – no labeling.
2001; Varma & Zisserman, 2002, 2003; 37Demo: feature detection. Output of
Lazebnik, Schmid & Ponce, 2003; crude feature detector Find edges Draw
Hierarchical Bayesian models for documents points randomly from edge set Draw from
(pLSA, LDA, etc.) Hoffman 1999; Blei, Ng uniform distribution to get scale.
& Jordan, 2004; Teh, Jordan, Beal 38Demo: learnt parameters. Codeword
& Blei, 2004 Object categorization distributions per theme (topic). Theme
Csurka, Bray, Dance & Fan, 2004; distributions per image. Learning the
Sivic, Russell, Efros, Freeman & model: do_plsa(‘config_file_1’) Evaluate
Zisserman, 2005; Sudderth, Torralba, and visualize the model:
Freeman & Willsky, 2005; Natural scene do_plsa_evaluation(‘config_file_1’).
categorization Vogel & Schiele, 2004; 39Demo: recognition examples.
Fei-Fei & Perona, 2005; Bosch, 40Demo: categorization results.
Zisserman & Munoz, 2006. Performance of each theme.
3 41Learning and Recognition. Generative
4Analogy to documents. Of all the method: - graphical models Discriminative
sensory impressions proceeding to the method: - SVM. category models (and/or)
brain, the visual experiences are the classifiers.
dominant ones. Our perception of the world 42Discriminative methods based on ‘bag
around us is based essentially on the of words’ representation. Decision
messages that reach the brain from our boundary. Zebra. Non-zebra.
eyes. For a long time it was thought that 43Discriminative methods based on ‘bag
the retinal image was transmitted point by of words’ representation. Grauman &
point to visual centers in the brain; the Darrell, 2005, 2006: SVM w/ Pyramid Match
cerebral cortex was a movie screen, so to kernels Others Csurka, Bray, Dance &
speak, upon which the image in the eye was Fan, 2004 Serre & Poggio, 2005.
projected. Through the discoveries of 44Summary: Pyramid match kernel. optimal
Hubel and Wiesel we now know that behind partial matching between sets of features.
the origin of the visual perception in the Grauman & Darrell, 2005, Slide credit:
brain there is a considerably more Kristen Grauman.
complicated course of events. By following 45Pyramid Match (Grauman & Darrell
the visual impulses along their path to 2005). Histogram intersection. Slide
the various cell layers of the optical credit: Kristen Grauman.
cortex, Hubel and Wiesel have been able to 46Pyramid Match (Grauman & Darrell
demonstrate that the message about the 2005). Histogram intersection. Slide
image falling on the retina undergoes a credit: Kristen Grauman.
step-wise analysis in a system of nerve 47Pyramid match kernel. Weights
cells stored in columns. In this system inversely proportional to bin size
each cell has its specific function and is Normalize kernel values to avoid favoring
responsible for a specific detail in the large sets. Slide credit: Kristen Grauman.
pattern of the retinal image. 48Example pyramid match. Level 0. Slide
5A clarification: definition of “BoW”. credit: Kristen Grauman.
Looser definition Independent features. 49Example pyramid match. Level 1. Slide
6A clarification: definition of “BoW”. credit: Kristen Grauman.
Looser definition Independent features 50Example pyramid match. Level 2. Slide
Stricter definition Independent features credit: Kristen Grauman.
histogram representation. 51Example pyramid match. pyramid match.
7 optimal match. Slide credit: Kristen
82. 1. 3. Representation. Grauman.
91.Feature detection and 52Summary: Pyramid match kernel. optimal
representation. partial matching between sets of features.
101.Feature detection and difficulty of a match at level i. number
representation. Regular grid Vogel & of new matches at level i. Slide credit:
Schiele, 2003 Fei-Fei & Perona, 2005. Kristen Grauman.
111.Feature detection and 53Object recognition results. ETH-80
representation. Regular grid Vogel & database 8 object classes (Eichhorn and
Schiele, 2003 Fei-Fei & Perona, 2005 Chapelle 2004) Features: Harris detector
Interest point detector Csurka, et al. PCA-SIFT descriptor, d=10. 84%. 85%. 84%.
2004 Fei-Fei & Perona, 2005 Sivic, et Kernel. Complexity. Recognition rate.
al. 2005. Match [Wallraven et al.]. Bhattacharyya
121.Feature detection and affinity [Kondor & Jebara]. Pyramid
representation. Regular grid Vogel & match. Slide credit: Kristen Grauman.
Schiele, 2003 Fei-Fei & Perona, 2005 54Object recognition results. Caltech
Interest point detector Csurka, Bray, objects database 101 object classes
Dance & Fan, 2004 Fei-Fei & Features: SIFT detector PCA-SIFT
Perona, 2005 Sivic, Russell, Efros, descriptor, d=10 30 training images /
Freeman & Zisserman, 2005 Other class 43% recognition rate (1% chance
methods Random sampling (Vidal-Naquet performance) 0.002 seconds per match.
& Ullman, 2002) Segmentation based Slide credit: Kristen Grauman.
patches (Barnard, Duygulu, Forsyth, de 55
Freitas, Blei, Jordan, 2003). 56? What about spatial info?
131.Feature detection and 57What about spatial info? Feature level
representation. Detect patches [Mikojaczyk Spatial influence through correlogram
and Schmid ’02] [Mata, Chum, Urban & features: Savarese, Winn and Criminisi,
Pajdla, ’02] [Sivic & Zisserman, ’03]. CVPR 2006.
Compute SIFT descriptor [Lowe’99]. 58What about spatial info? Feature level
Normalize patch. Slide credit: Josef Generative models Sudderth, Torralba,
Sivic. Freeman & Willsky, 2005, 2006 Niebles
141.Feature detection and & Fei-Fei, CVPR 2007.
representation. 59What about spatial info? Feature level
152. Codewords dictionary formation. Generative models Sudderth, Torralba,
162. Codewords dictionary formation. Freeman & Willsky, 2005, 2006 Niebles
Vector quantization. Slide credit: Josef & Fei-Fei, CVPR 2007.
Sivic. 60What about spatial info? Feature level
172. Codewords dictionary formation. Generative models Discriminative methods
Fei-Fei et al. 2005. Lazebnik, Schmid & Ponce, 2006.
18Image patch examples of codewords. 61Invariance issues. Scale and rotation
Sivic et al. 2005. Implicit Detectors and descriptors. Kadir
193. Image representation. codewords. and Brady. 2003.
frequency. 62Invariance issues. Scale and rotation
202. 1. 3. Representation. Occlusion Implicit in the models Codeword
21Learning and Recognition. category distribution: small variations (In theory)
models (and/or) classifiers. Theme (z) distribution: different
22Learning and Recognition. Generative occlusion patterns.
method: - graphical models Discriminative 63Invariance issues. Scale and rotation
method: - SVM. category models (and/or) Occlusion Translation Encode (relative)
classifiers. location information Sudderth, Torralba,
232 generative models. Na?ve Bayes Freeman & Willsky, 2005, 2006 Niebles
classifier Csurka Bray, Dance & Fan, & Fei-Fei, 2007.
2004 Hierarchical Bayesian text models 64Invariance issues. Scale and rotation
(pLSA and LDA) Background: Hoffman 2001, Occlusion Translation View point (in
Blei, Ng & Jordan, 2004 Object theory) Codewords: detector and descriptor
categorization: Sivic et al. 2005, Theme distributions: different view
Sudderth et al. 2005 Natural scene points. Fergus, Fei-Fei, Perona &
categorization: Fei-Fei et al. 2005. Zisserman, 2005.
24First, some notations. wn: each patch 65Model properties. Intuitive Analogy to
in an image wn = [0,0,…1,…,0,0]T w: a documents.
collection of all N patches in an image w 66Model properties. Intuitive Analogy to
= [w1,w2,…,wN] dj: the jth image in an documents Analogy to human vision.
image collection c: category of the image Olshausen and Field, 2004, Fei-Fei and
z: theme or topic of the patch. Perona, 2005.
25Case #1: the Na?ve Bayes model. c. w. 67Model properties. Intuitive generative
N. Csurka et al. 2004. models Convenient for weakly- or
26Csurka et al. 2004. un-supervised, incremental training Prior
27Csurka et al. 2004. information Flexibility (e.g. HDP). Li,
28Case #2: Hierarchical Bayesian text Wang & Fei-Fei, CVPR 2007. Sivic,
models. Probabilistic Latent Semantic Russell, Efros, Freeman, Zisserman, 2005.
Analysis (pLSA). Latent Dirichlet 68Model properties. Intuitive generative
Allocation (LDA). Hoffman, 2001. Blei et models Discriminative method
al., 2001. Computationally efficient. Grauman et al.
29Case #2: Hierarchical Bayesian text CVPR 2005.
models. Probabilistic Latent Semantic 69Model properties. Intuitive generative
Analysis (pLSA). Sivic et al. ICCV 2005. models Discriminative method Learning and
30Case #2: Hierarchical Bayesian text recognition relatively fast Compare to
models. Latent Dirichlet Allocation (LDA). other methods.
Fei-Fei et al. ICCV 2005. 70Weakness of the model. No rigorous
31Case #2: the pLSA model. geometric information of the object
32Case #2: the pLSA model. Slide credit: components It’s intuitive to most of us
Josef Sivic. that objects are made of parts – no such
33Case #2: Recognition using pLSA. Slide information Not extensively tested yet for
credit: Josef Sivic. View point invariance Scale invariance
34Case #2: Learning the pLSA parameters. Segmentation and localization unclear.
Part 1: Bag-of-words models.ppt
http://900igr.net/kartinka/anglijskij-jazyk/part-1-bag-of-words-models-252492.html
cсылка на страницу

Part 1: Bag-of-words models

другие презентации на тему «Part 1: Bag-of-words models»

«English words» - 1) Go and wotch a match 2) Go to a disko 3) Go shopping 4) Go for a picnic 5) Go sightseeng 6) Go and see a frend 7) Go to a party 8)I had a terible time 9) Go skiing 10) Go for a meel in a restaurant. That is all! Match the expressions to others with similar meanings. Is it True or False? 1) FALSE — watch 2) FALSE — disco 3) TRUE 4) TRUE 5) FALSE — sightseeing 6) FALSE — friend 7) TRUE 8) FALSE — terrible 9) TRUE 10) FALSE — meal.

«Прямая и косвенная речь в английском» - Time expressions. Past Simple. Dad says he’s lost his voice. Цель. Simple. Прямая и косвенная речь. Глагол придаточного предложения. Правила согласования времен. Изменение модальных глаголов в косвенной речи. Direct speech and reported (indirect) speech. Say the following statements in reported speech.

«Сложное дополнение» - Every time I walk out the door. Сложное дополнение с инфинитивом. Состав сложного дополнения. Русский язык. Объектные местоимения. Английский язык. Том сел в свою машину. She dropped her bag. Разница. Примеры. Сложное дополнение. Глаголы восприятия.

«Британские корпуса» - C.Гринбаум. Международные семинары. Устные тексты МКА . Cоздание корпусов. Корпусная лингвистика. История и настоящее. Британские учебные словари. British National Corpus. Соединенное королевство. Устные тексты. Тексты МКА. Британский компонент. COBUILD. Образование. Международные дела. Британские корпуса и словари.

«Гнев на английском» - Деепричастие. Rage. Fury. Имя существительное. Анализ английских текстов. Эмоции. Причастие. Wrath. Anger. Имя прилагательное. Наречие. Причастие. Лексико-семантическое поле. Гнев/ярость. Злость.

«Грамматика английского языка» - English Grammar in Use Intermediate. Comparisons. Prepositions after verbs and nouns. Prepositions of time, place and movement. Expressions of time and preference. Order of adjectives. Comparative and superlative adjectives. Participles. Грамматика английского языка. Question tags. Grammar and Vocabulary for First Certificate.

Английская грамматика

28 презентаций об английской грамматике
Урок

Английский язык

29 тем
Картинки