Lec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA

Size: px
Start display at page:

Download "Lec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA"

Transcription

1 Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 0012 Lec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA Zhu Li Dept of CSEE, UMKC Office: FH560E, Ph: x Z. Li, Image Analysis & Retrv p.1

2 Outline ReCap of Lecture 07 Image Retrieval System BoW VLAD Dense SIFT Fisher Vector Aggregation AKULA Summary Z. Li, Image Analysis & Retrv p.2

3 Precision, Recall, F-measure Precision, TPR = TP/(TP + FP), Recall = TP/(TP + FN), FPR=FP/(TP+FP) F-measure = 2*(precision*recall)/(precision + recall) Precision: is the probability that a retrieved document is relevant. Recall: is the probability that a relevant document is retrieved in a search. Z. Li, Image Analysis & Retrv p.3

4 Curse of Dimensionality Why Aggregation? + Decision Boundary / Indexing.. Z. Li, Image Analysis & Retrv p.4

5 Bag-of-Words: Histogram Coding Codebook: Feature space: R d, k-means to get k centroids, {μ 1, μ 2,, μ k } BoW Hard Encoding: For n feature points,{x 1, x 2,,x n } assignment matrix: kxn, with column only 1-non zero entry Aggregated dimension: k k n Z. Li, Image Analysis & Retrv p.5

6 Kernel Code Book Soft Encoding Kernel Code Book Soft Encoding Kernel Affinity: K x j, μ k = e k x j μ k 2 Assignment Matrix: A j,k = K(x j, μ k )/ k K(x j, μ k ) Encoding: k-dimensional: X(k)= 1 n j A j,k Z. Li, Image Analysis & Retrv p.6

7 VLAD- Vector of Locally Aggregated Descriptors Aggregate feature difference from the codebook Hard assignment by finding the NN of feature {x k } to {μ k } Compute aggregated differences 1 assign descriptors x 2 v k = j,s.t.nn x j =μ k x j μ k 2 compute x- i 5 L2 normalize v k = v k / v k 2 Final feature: k x d 3 v i =sum x- i for cell i v 1 v2 v 3 v 4 v 5 Z. Li, Image Analysis & Retrv p.7

8 VLAD on SIFT Example of aggregating SIFT with VLAD K=16 codebook entries Each cell is a SIFT visualized as centroids in blue, and VLAD difference in red Top row: left image, bottom row: right image, red: code book, blue: encoded VLAD Z. Li, Image Analysis & Retrv p.8

9 Outline ReCap of Lecture 07 Image Retrieval System BoW VLAD Dense SIFT Fisher Vector Aggregation AKULA Summary Z. Li, Image Analysis & Retrv p.9

10 One more trick Recall that SIFT is a powerful descriptor VL_FEAT: vl_dsift A dense description of image by computing SIFT descriptor (no spatial-scale space extrema detection) at predetermined grid Supplement HoG as an alternative texture descriptor Z. Li, Image Analysis & Retrv p.10

11 VL_FEAT: vl_dsift Compute dense SIFT as a texture descriptor for the image [f, dsift]=vl_dsift(single(rgb2gray(im)), step, 2); There s also a FAST option [f, dsift]=vl_dsift(single(rgb2gray(im)), fast, step, 2); Huge amount of SIFT data will be generated Z. Li, Image Analysis & Retrv p.11

12 Fisher Vector Fisher Vector and variations: Winning in image classification: Winning in the MPEG object re-identification: o SCFV(Scalable Coded Fisher Vec) in CDVS Z. Li, Image Analysis & Retrv p.12

13 Codebook: Gaussian Mixture Model (GMM) GMM is a generative model to express data Assuming data is generated from with parameters {w k, μ k, σ k } x k ~ K k=1 w k N(μ k,σ k ) N μ k,σ k = 1 2π d 2 Σ k 1/2 e 1 2 x μ k Σ k 1 (x μ k ) Z. Li, Image Analysis & Retrv p.13

14 A bit of Theory: Fisher Kernel Encode the derivation from the generative model Observed feature set, {x 1, x 2,,x n } in R d, e.g, d=128 for SIFT. How s these observations derivate from the given GMM model with a set of parameter, λ = w k, μ k, σ k? o i.e, how the parameter, e.g, mean will move to best fit the observation? μ 1 μ 4 μ 3 + X1 μ 2 Z. Li, Image Analysis & Retrv p.14

15 A bit of Theory: Fisher Kernel Score function w.r.t. the likelihood function μ λ (X) G λ X = λ log u λ (X): derivative on the log likelihood The dimension of score function is m, where m is the number of generative model parameters, m=3 for GMM Given the observed data X, score function indicate how likelihood function parameter (e.g, mean) should move to better fit the data. Distance/Derivation of two observation X, Y w.r.t the generative model Fisher Info Matrix (roughly the covariance in the Mahanolibis distance) F λ = E X G λ X G λ X Fisher Kernel Distance: normalized by the Fisher Info Matrix: K FK X, Y = G λ X F λ 1 G λ X Z. Li, Image Analysis & Retrv p.15

16 Fisher Vector K FK (X, Y) is a measure of similarity, w.r.t. the generative model Similar to the Mahanolibis distance case, we can decompose this kernel as, K FK X, Y = G λ X F λ 1 G λ X = G λ X L λ L λ G λ X That give us a kernel feature mapping of X to Fisher Vector For observed images features {x t }, can be computed as, Z. Li, Image Analysis & Retrv p.16

17 GMM Fisher Vector Encode the derivation from the generative model Observed feature set, {x 1, x 2,,x n } in R d, e.g, d=128 (!) for SIFT. How s these observations derivate from the given GMM model with a set of parameter, θ = a k, μ k, σ k? GMM Log Likelihood Gradient Let w k = ea k j ea j, Then we have weight mean variance Z. Li, Image Analysis & Retrv p.17

18 GMM Fisher Vector VL_FEAT implementation GMM codebook For a K-component GMM, we only allow 3K parameters, π k, μ k,σ k k = 1.. K}, i.e, iid Gaussian component Σ k = σ k σ k 0 0. σ k Posterior prob of feature point x i to GMM component k Z. Li, Image Analysis & Retrv p.18

19 GMM Fisher Vector VL_FEAT implementation FV encoding Gradient on the mean, for GMM component k, j=1..d In the end, we have 2K x D aggregation on the derivation w.r.t. the means and variances FV = [u 1, u 2,, u K, v 1, v 2,, v K ] Z. Li, Image Analysis & Retrv p.19

20 VL_FEAT GMM/FV API Compute GMM model with VL_FEAT Prepare data: numpoints = 1000 ; dimension = 2 ; data = rand(dimension,n) ; Call vl_gmm: numclusters = 30 ; [means, covariances, priors] = vl_gmm(data, numclusters) ; Visualize: figure ; hold on ; plot(data(1,:),data(2,:),'r.') ; for i=1:numclusters vl_plotframe([means(:,i)' sigmas(1,i) 0 sigmas(2,i)]); end Z. Li, Image Analysis & Retrv p.20

21 VL_FEAT API FV encoding encoding = vl_fisher(datatobeencoded, means, covariances, priors); Bonus points: Encode HoG features with Fisher Vector? randomly collect 2~3 images from each class Stack all HoG features together into an n x 36 data matrix Compute its GMM Use this GMM to encode all image HoG features (other than average) Z. Li, Image Analysis & Retrv p.21

22 Super Vector Aggregation Speaker ID Fisher Vector: Aggregates Features against a GMM Super Vector: Aggregates GMM against GMM Yes, We Can!? Ref: o William M. Campbell, Douglas E. Sturim, Douglas A. Reynolds: Support vector machines using GMM supervectors for speaker verification. IEEE Signal Process. Lett. 13(5): (2006) Z. Li, Image Analysis & Retrv p.22

23 Super Vector from MFCC Motivated from Speaker ID work Speech is a continuous evolution of the vocal tract Need to extract a sequence of spectra or sequence of spectral coefficients Use a sliding window - 25 ms window, 10 ms shift Log X(ω) DCT MFCC Z. Li, Image Analysis & Retrv p.23

24 GMM Model from MFCC GMM on MFCC feature Z. Li, Image Analysis & Retrv p.24 M j s j s j s j s p p 1 ) ( ) ( ) ( ) ( ), ( ) ( x x The acoustic vectors (MFCC) of speaker s is modeled by a prob. density function parameterized by M j s j s j s j s 1 ) ( ) ( ) ( ) ( },, { Gaussian mixture model (GMM) for speaker s: M j s j s j s j s 1 ) ( ) ( ) ( ) ( },, {

25 Universal Background Model UBM GMM Model: The acoustic vectors of a general population is modeled by another GMM called the universal background model (UBM): (ubm) (ubm) p( x ) p( x M j 1 j (ubm) j, (ubm) j ) Parameters of the UBM (ubm) (ubm) (ubm) (ubm) M { j, j, j } j 1 Z. Li, Image Analysis & Retrv p.25

26 MAP Adaption Given the UBM GMM, how is the new observation derivate? The adapted mean is given by: Z. Li, Image Analysis & Retrv p.26

27 Supervector Distance Assuming we have UBM GMM model λ UBM = {P k, μ k, Σ k }, with identical prior and covariance Then for two utterance samples a and b, with GMM models λ a = {P k, μ k a, Σ k }, λ b = {P k, μ k b, Σ k }, The SV distance is, K λ a,λ b = k P k Σ k ( 1 2 ) μ k a It means the means of two models need to be normalized by the UBM covariance induced Mahanolibis distance metric This is also a linear kernel function scaled by the UBM covariances T ( P k Σ k ( 1 2 ) μ k b ) Z. Li, Image Analysis & Retrv p.27

28 Supervector Performance in NIST Speaker ID System 5: Gaussian SV DCF (Detection Cost Function) Z. Li, Image Analysis & Retrv p.28

29 m31491 AKULA Adaptive KLUster Aggregation 2013/10/25 Abhishek Nagar, Zhu Li, Gaurav Srivastava and Kyungmo Park Z. Li, Image Analysis & Retrv p.29

30 Outline Motivation Adaptive Aggregation Results with TM7 Summary Z. Li, Image Analysis & Retrv p.30

31 Motivation Better Aggregation Fisher Vector and VLAD type aggregation depending on a global model AKULA removes this dependence, and directly coding the cluster centroids and sift count SCFV/RVD all having situations where clusters are turned off due to no assignment, this can be avoided in AKULA SIFT detection & selection K-means AKULA description Z. Li, Image Analysis & Retrv p.31

32 Motivation Better Subspace Choice Both SCFV and RVD do fixed normalization and PCA projection based on heuristic. What is the best possible subspace to do the aggregation? Using a boosting scheme to keep adding subspaces and aggregations in an iterative fashion, and tune TPR-FPR to the desired operating points on FPR. Z. Li, Image Analysis & Retrv p.32

33 CE2: AKULA Adaptive KLUster Aggregation AKULA Descriptor: cluster centroids + SIFT count A 1 ={yc 1 1, yc 1 2,, yc 1 k ; pc 1 1, pc 1 2,, pc 1 k }, A 2 ={yc 2 1, yc 2 2,, yc 2 k ; pc 2 1, pc 2 2,, pc 2 k } Distance metric: Min centroids distance, weighted by SIFT count d A 1, A 2 = 1 k 1 d k j=0 min j w min k 1 (j) + 1 k i=0 2 2 d min i w min (i) 1 d min d min j = min 2 i = min i j d j,i d j,i 1 w min j = w j,i, i = argmin i 2 i = w j,i, j = argmin w min j d j,i d j,i Z. Li, Image Analysis & Retrv p.33

34 AKULA implementation in TM7 Inner loop aggregation Dimension is fixed at 8 Numb of clusters, or nc=8, 16, 32, to hit 64, 128, and 256 bytes Quantization: scale by ½ and quantized to int8, sift count is 8 bits, total (nc+1)*dim bytes per aggregation Z. Li, Image Analysis & Retrv p.34

35 AKULA implementation in TM7 Outer loop subspace optimization by boosting Initial set of subspace models {A k } computed from MIR FLICKR data set SIFT extractions by k-means the space to 4096 clusters Iterative search on subspaces to generate AKULA aggregation that can improve performance in precisionrecall Notice that aggregation is de-coupled in subspace iteration, to allow more DoF in aggregation, to find subspaces that provides complimentary info. The algorithm is still being debugged, hence only having 1 st iteration results in TM7 Z. Li, Image Analysis & Retrv p.35

36 AKULA implementation in TM7 Outer loop subspace optimization by boosting Initial set of subspace models {A k } computed from MIR FLICKR data set SIFT extractions by k-means the space to 4096 clusters Iterative search on subspaces to generate AKULA aggregation that can improve performance in precision-recall Notice that aggregation is de-coupled in subspace iteration, to allow more DoF in aggregation, to find subspaces that provides complimentary info. The algorithm is still being debugged, hence only having 1 st iteration results in TM7 Indexing/Hashing is required for AKULA, it involves nc x dim multiplications and additions at this time. A binarization scheme will be considered once its performance is optimized in non-binary form. Z. Li, Image Analysis & Retrv p.36

37 GD Only TPR-FPR: AKULA vs SCFV Data set 1: AKULA (128bytes, dim=8, nc=16) distance is just 1-way dmin 1.*wt Forcing a weighted sum on SCFV (512 bytes) hamming distances without 2D decision fitting, i.e, count hamming distance between common active clusters, and sum up their distances Z. Li, Image Analysis & Retrv p.37

38 GD Only TPR-FPR: AKULA vs SCFV Data set 2, 3: AKULA distance is just 1-way dmin 1.*wt AKULA=128bytes, SCFV = 512 bytes. Z. Li, Image Analysis & Retrv p.38

39 3D object set: 4, 5 Data set4, 5: Z. Li, Image Analysis & Retrv p.39

40 FPR performance: AKULA in PM AKULA rates: pm rates m akula rates K K K_4K K_4K K K K Z. Li, Image Analysis & Retrv p.40

41 TPR (%) FPR TPR (%) 120 bitrate: bitrate: 1k TM7 AKULA TM7 AKULA a 1b 1c a 1b 1c Z. Li, Image Analysis & Retrv p.41

42 TPR (%) TPR (%) bitrate: 2k bitrate: 1k-4k TM7 60 TM7 40 AKULA 40 AKULA a 1b 1c a 1b 1c Z. Li, Image Analysis & Retrv p.42

43 TPR (%) TPR (%) bitrate: 2k-4k bitrate: 4k TM7 60 TM7 40 AKULA 40 AKULA a 1b 1c a 1b 1c Z. Li, Image Analysis & Retrv p.43

44 TPR (%) TPR (%) bitrate: 8k bitrate: 16k TM7 AKULA TM7 AKULA a 1b 1c a 1b 1c Z. Li, Image Analysis & Retrv p.44

45 AKULA Localization Quite some improvements: 2.7% Z. Li, Image Analysis & Retrv p.45

46 AKULA Summary Benefits: Allow more DoF in aggregation optimization, o by an outer loop boosting scheme for subspace projection optimization o And an inner loop adaptive clustering without the constraint of the global GMM model Simple weighted distance sum metric, with no need to tune a multi-dimensional decision boundary The overall pair wise matching matched up with TM7 SCFV with 2-dimensional decision boundary In GD only matching outperforms the TM7 GD Good improvements to the localization accuracy Light in extraction, but still heavy in pair wise matching, and need binarization scheme and/or indexing scheme to work for retrieval Future Improvements: Supervector AKULA? Z. Li, Image Analysis & Retrv p.46

47 Lec 08 Summary Fisher Vector Aggregate features {Xk} in R D against GMM Super Vector Aggregate GMM against a global GMM (UBM) AKULA Direct Aggregation Z. Li, Image Analysis & Retrv p.47

Image Analysis & Retrieval Lec 12 - Mid-Term Review

Image Analysis & Retrieval Lec 12 - Mid-Term Review CS/EE 5590 / ENG 401 Special Topics, Spring 2018 Image Analysis & Retrieval Lec 12 - Mid-Term Review Zhu Li Dept of CSEE, UMKC http://l.web.umkc.edu/lizhu Office Hour: Tue/Thr 2:30-4pm@FH560E, Contact:

More information

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 13

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 13 Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 13 Dimension Reduction: SVD and PCA Zhu Li Dept of CSEE, UMKC Office: FH560E, Email:

More information

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 18.

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 18. Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 18 Image Hashing Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph:

More information

Mixtures of Gaussians and Advanced Feature Encoding

Mixtures of Gaussians and Advanced Feature Encoding Mixtures of Gaussians and Advanced Feature Encoding Computer Vision Ali Borji UWM Many slides from James Hayes, Derek Hoiem, Florent Perronnin, and Hervé Why do good recognition systems go bad? E.g. Why

More information

AKULA Adaptive Cluster Aggregation for Visual Search

AKULA Adaptive Cluster Aggregation for Visual Search AKULA Adaptive Cluster Aggregation for Visual Search Abhishek Nagar *, Zhu Li *, Gaurav Srivastava *, and Kyungmo Park + * Samsung Research America 1301 E. Lookout Dr. Richardson, TX 75082, USA {a.nagar,

More information

Fisher vector image representation

Fisher vector image representation Fisher vector image representation Jakob Verbeek January 13, 2012 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.11.12.php Fisher vector representation Alternative to bag-of-words image representation

More information

Clustering Lecture 5: Mixture Model

Clustering Lecture 5: Mixture Model Clustering Lecture 5: Mixture Model Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced topics

More information

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 16

Image Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 16 Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 16 Subspace/Transform Optimization Zhu Li Dept of CSEE, UMKC Office: FH560E, Email:

More information

Computer Vision. Exercise Session 10 Image Categorization

Computer Vision. Exercise Session 10 Image Categorization Computer Vision Exercise Session 10 Image Categorization Object Categorization Task Description Given a small number of training images of a category, recognize a-priori unknown instances of that category

More information

From Pixels to Information Recent Advances in Visual Search

From Pixels to Information Recent Advances in Visual Search From Pixels to Information Recent Advances in Visual Search Bernd Girod Stanford University bgirod@stanford.edu Augmented Reality 3 Augmented Reality 2014 2012 2015 4 Future: Smart Contact Lenses Sight:

More information

ECE 5424: Introduction to Machine Learning

ECE 5424: Introduction to Machine Learning ECE 5424: Introduction to Machine Learning Topics: Unsupervised Learning: Kmeans, GMM, EM Readings: Barber 20.1-20.3 Stefan Lee Virginia Tech Tasks Supervised Learning x Classification y Discrete x Regression

More information

Image Analysis & Retrieval Lec 10 - Classification II

Image Analysis & Retrieval Lec 10 - Classification II CS/EE 5590 / ENG 401 Special Topics, Spring 2018 Image Analysis & Retrieval Lec 10 - Classification II Zhu Li Dept of CSEE, UMKC http://l.web.umkc.edu/lizhu Office Hour: Tue/Thr 2:30-4pm@FH560E, Contact:

More information

Clustering. CS294 Practical Machine Learning Junming Yin 10/09/06

Clustering. CS294 Practical Machine Learning Junming Yin 10/09/06 Clustering CS294 Practical Machine Learning Junming Yin 10/09/06 Outline Introduction Unsupervised learning What is clustering? Application Dissimilarity (similarity) of objects Clustering algorithm K-means,

More information

Metric Learning for Large Scale Image Classification:

Metric Learning for Large Scale Image Classification: Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Thomas Mensink 1,2 Jakob Verbeek 2 Florent Perronnin 1 Gabriela Csurka 1 1 TVPA - Xerox Research Centre

More information

Large scale object/scene recognition

Large scale object/scene recognition Large scale object/scene recognition Image dataset: > 1 million images query Image search system ranked image list Each image described by approximately 2000 descriptors 2 10 9 descriptors to index! Database

More information

Pattern Spotting in Historical Document Image

Pattern Spotting in Historical Document Image Pattern Spotting in historical document images Sovann EN, Caroline Petitjean, Stéphane Nicolas, Frédéric Jurie, Laurent Heutte LITIS, University of Rouen, France 1 Outline Introduction Commons Pipeline

More information

ImageCLEF 2011

ImageCLEF 2011 SZTAKI @ ImageCLEF 2011 Bálint Daróczy joint work with András Benczúr, Róbert Pethes Data Mining and Web Search Group Computer and Automation Research Institute Hungarian Academy of Sciences Training/test

More information

Machine Learning Lecture 3

Machine Learning Lecture 3 Machine Learning Lecture 3 Probability Density Estimation II 19.10.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Exam dates We re in the process

More information

Expectation Maximization: Inferring model parameters and class labels

Expectation Maximization: Inferring model parameters and class labels Expectation Maximization: Inferring model parameters and class labels Emily Fox University of Washington February 27, 2017 Mixture of Gaussian recap 1 2/26/17 Jumble of unlabeled images HISTOGRAM blue

More information

Writer Identification and Verification Using GMM Supervectors

Writer Identification and Verification Using GMM Supervectors Writer Identification and Verification Using GMM Supervectors Vincent Christlein David Bernecker Florian Hönig Elli Angelopoulou Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität

More information

on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015

on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 Vector visual representation Fixed-size image representation High-dim (100 100,000) Generic, unsupervised: BoW,

More information

CS839: Probabilistic Graphical Models. Lecture 10: Learning with Partially Observed Data. Theo Rekatsinas

CS839: Probabilistic Graphical Models. Lecture 10: Learning with Partially Observed Data. Theo Rekatsinas CS839: Probabilistic Graphical Models Lecture 10: Learning with Partially Observed Data Theo Rekatsinas 1 Partially Observed GMs Speech recognition 2 Partially Observed GMs Evolution 3 Partially Observed

More information

CS 229 Midterm Review

CS 229 Midterm Review CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask

More information

MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION. Steve Tjoa June 25, 2014

MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION. Steve Tjoa June 25, 2014 MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION Steve Tjoa kiemyang@gmail.com June 25, 2014 Review from Day 2 Supervised vs. Unsupervised Unsupervised - clustering Supervised binary classifiers (2 classes)

More information

Methods for Intelligent Systems

Methods for Intelligent Systems Methods for Intelligent Systems Lecture Notes on Clustering (II) Davide Eynard eynard@elet.polimi.it Department of Electronics and Information Politecnico di Milano Davide Eynard - Lecture Notes on Clustering

More information

Comparative Evaluation of Feature Normalization Techniques for Speaker Verification

Comparative Evaluation of Feature Normalization Techniques for Speaker Verification Comparative Evaluation of Feature Normalization Techniques for Speaker Verification Md Jahangir Alam 1,2, Pierre Ouellet 1, Patrick Kenny 1, Douglas O Shaughnessy 2, 1 CRIM, Montreal, Canada {Janagir.Alam,

More information

Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on

Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on TAN Zhili & MAK Man-Wai APSIPA 2015 Department of Electronic and Informa2on Engineering The Hong Kong Polytechnic

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

Expectation Maximization: Inferring model parameters and class labels

Expectation Maximization: Inferring model parameters and class labels Expectation Maximization: Inferring model parameters and class labels Emily Fox University of Washington February 27, 2017 Mixture of Gaussian recap 1 2/27/2017 Jumble of unlabeled images HISTOGRAM blue

More information

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213) Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding

More information

Three things everyone should know to improve object retrieval. Relja Arandjelović and Andrew Zisserman (CVPR 2012)

Three things everyone should know to improve object retrieval. Relja Arandjelović and Andrew Zisserman (CVPR 2012) Three things everyone should know to improve object retrieval Relja Arandjelović and Andrew Zisserman (CVPR 2012) University of Oxford 2 nd April 2012 Large scale object retrieval Find all instances of

More information

ILSVRC on a Smartphone

ILSVRC on a Smartphone [DOI: 10.2197/ipsjtcva.6.83] Express Paper ILSVRC on a Smartphone Yoshiyuki Kawano 1,a) Keiji Yanai 1,b) Received: March 14, 2014, Accepted: April 24, 2014, Released: July 25, 2014 Abstract: In this work,

More information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Mustafa Berkay Yilmaz, Hakan Erdogan, Mustafa Unel Sabanci University, Faculty of Engineering and Natural

More information

Clustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin

Clustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin Clustering K-means Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, 2014 Carlos Guestrin 2005-2014 1 Clustering images Set of Images [Goldberger et al.] Carlos Guestrin 2005-2014

More information

SHOT-BASED OBJECT RETRIEVAL FROM VIDEO WITH COMPRESSED FISHER VECTORS. Luca Bertinetto, Attilio Fiandrotti, Enrico Magli

SHOT-BASED OBJECT RETRIEVAL FROM VIDEO WITH COMPRESSED FISHER VECTORS. Luca Bertinetto, Attilio Fiandrotti, Enrico Magli SHOT-BASED OBJECT RETRIEVAL FROM VIDEO WITH COMPRESSED FISHER VECTORS Luca Bertinetto, Attilio Fiandrotti, Enrico Magli Dipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino (Italy) ABSTRACT

More information

Clustering: Classic Methods and Modern Views

Clustering: Classic Methods and Modern Views Clustering: Classic Methods and Modern Views Marina Meilă University of Washington mmp@stat.washington.edu June 22, 2015 Lorentz Center Workshop on Clusters, Games and Axioms Outline Paradigms for clustering

More information

Clustering. Mihaela van der Schaar. January 27, Department of Engineering Science University of Oxford

Clustering. Mihaela van der Schaar. January 27, Department of Engineering Science University of Oxford Department of Engineering Science University of Oxford January 27, 2017 Many datasets consist of multiple heterogeneous subsets. Cluster analysis: Given an unlabelled data, want algorithms that automatically

More information

Image Processing. Image Features

Image Processing. Image Features Image Processing Image Features Preliminaries 2 What are Image Features? Anything. What they are used for? Some statements about image fragments (patches) recognition Search for similar patches matching

More information

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition Pattern Recognition Kjell Elenius Speech, Music and Hearing KTH March 29, 2007 Speech recognition 2007 1 Ch 4. Pattern Recognition 1(3) Bayes Decision Theory Minimum-Error-Rate Decision Rules Discriminant

More information

TA Section: Problem Set 4

TA Section: Problem Set 4 TA Section: Problem Set 4 Outline Discriminative vs. Generative Classifiers Image representation and recognition models Bag of Words Model Part-based Model Constellation Model Pictorial Structures Model

More information

Machine Learning Lecture 3

Machine Learning Lecture 3 Many slides adapted from B. Schiele Machine Learning Lecture 3 Probability Density Estimation II 26.04.2016 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Course

More information

ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects Topics

ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects Topics ECE 484 Digital Image Processing Lec 17 - Part II Review & Final Projects opics Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346. http://l.web.umkc.edu/lizhu slides created with

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Image Segmentation Some material for these slides comes from https://www.csd.uwo.ca/courses/cs4487a/

More information

Computer vision: models, learning and inference. Chapter 13 Image preprocessing and feature extraction

Computer vision: models, learning and inference. Chapter 13 Image preprocessing and feature extraction Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction Preprocessing The goal of pre-processing is to try to reduce unwanted variation in image due to lighting,

More information

Machine Learning Lecture 3

Machine Learning Lecture 3 Course Outline Machine Learning Lecture 3 Fundamentals (2 weeks) Bayes Decision Theory Probability Density Estimation Probability Density Estimation II 26.04.206 Discriminative Approaches (5 weeks) Linear

More information

Aggregating Descriptors with Local Gaussian Metrics

Aggregating Descriptors with Local Gaussian Metrics Aggregating Descriptors with Local Gaussian Metrics Hideki Nakayama Grad. School of Information Science and Technology The University of Tokyo Tokyo, JAPAN nakayama@ci.i.u-tokyo.ac.jp Abstract Recently,

More information

10-701/15-781, Fall 2006, Final

10-701/15-781, Fall 2006, Final -7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly

More information

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013 Feature Descriptors CS 510 Lecture #21 April 29 th, 2013 Programming Assignment #4 Due two weeks from today Any questions? How is it going? Where are we? We have two umbrella schemes for object recognition

More information

Clustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin

Clustering K-means. Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, Carlos Guestrin Clustering K-means Machine Learning CSEP546 Carlos Guestrin University of Washington February 18, 2014 Carlos Guestrin 2005-2014 1 Clustering images Set of Images [Goldberger et al.] Carlos Guestrin 2005-2014

More information

Expectation-Maximization. Nuno Vasconcelos ECE Department, UCSD

Expectation-Maximization. Nuno Vasconcelos ECE Department, UCSD Expectation-Maximization Nuno Vasconcelos ECE Department, UCSD Plan for today last time we started talking about mixture models we introduced the main ideas behind EM to motivate EM, we looked at classification-maximization

More information

Aggregating local image descriptors into compact codes

Aggregating local image descriptors into compact codes Aggregating local image descriptors into compact codes Hervé Jégou, Florent Perronnin, Matthijs Douze, Jorge Sánchez, Patrick Pérez, Cordelia Schmid To cite this version: Hervé Jégou, Florent Perronnin,

More information

Sparse coding for image classification

Sparse coding for image classification Sparse coding for image classification Columbia University Electrical Engineering: Kun Rong(kr2496@columbia.edu) Yongzhou Xiang(yx2211@columbia.edu) Yin Cui(yc2776@columbia.edu) Outline Background Introduction

More information

The Approach of Mean Shift based Cosine Dissimilarity for Multi-Recording Speaker Clustering

The Approach of Mean Shift based Cosine Dissimilarity for Multi-Recording Speaker Clustering The Approach of Mean Shift based Cosine Dissimilarity for Multi-Recording Speaker Clustering 1 D. Jareena Begum, 2 K Rajendra Prasad, 3 M Suleman Basha 1 M.Tech in SE, RGMCET, Nandyal 2 Assoc Prof, Dept

More information

Large-scale visual recognition Efficient matching

Large-scale visual recognition Efficient matching Large-scale visual recognition Efficient matching Florent Perronnin, XRCE Hervé Jégou, INRIA CVPR tutorial June 16, 2012 Outline!! Preliminary!! Locality Sensitive Hashing: the two modes!! Hashing!! Embedding!!

More information

Metric Learning for Large-Scale Image Classification:

Metric Learning for Large-Scale Image Classification: Metric Learning for Large-Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Florent Perronnin 1 work published at ECCV 2012 with: Thomas Mensink 1,2 Jakob Verbeek 2 Gabriela Csurka

More information

Mixture Models and the EM Algorithm

Mixture Models and the EM Algorithm Mixture Models and the EM Algorithm Padhraic Smyth, Department of Computer Science University of California, Irvine c 2017 1 Finite Mixture Models Say we have a data set D = {x 1,..., x N } where x i is

More information

Lecture 24: Image Retrieval: Part II. Visual Computing Systems CMU , Fall 2013

Lecture 24: Image Retrieval: Part II. Visual Computing Systems CMU , Fall 2013 Lecture 24: Image Retrieval: Part II Visual Computing Systems Review: K-D tree Spatial partitioning hierarchy K = dimensionality of space (below: K = 2) 3 2 1 3 3 4 2 Counts of points in leaf nodes Nearest

More information

Generative and discriminative classification techniques

Generative and discriminative classification techniques Generative and discriminative classification techniques Machine Learning and Category Representation 013-014 Jakob Verbeek, December 13+0, 013 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.13.14

More information

Efficient Object Localization with Gaussianized Vector Representation

Efficient Object Localization with Gaussianized Vector Representation Efficient Object Localization with Gaussianized Vector Representation ABSTRACT Xiaodan Zhuang xzhuang2@uiuc.edu Mark A. Hasegawa-Johnson jhasegaw@uiuc.edu Recently, the Gaussianized vector representation

More information

Segmentation: Clustering, Graph Cut and EM

Segmentation: Clustering, Graph Cut and EM Segmentation: Clustering, Graph Cut and EM Ying Wu Electrical Engineering and Computer Science Northwestern University, Evanston, IL 60208 yingwu@northwestern.edu http://www.eecs.northwestern.edu/~yingwu

More information

Recap: Gaussian (or Normal) Distribution. Recap: Minimizing the Expected Loss. Topics of This Lecture. Recap: Maximum Likelihood Approach

Recap: Gaussian (or Normal) Distribution. Recap: Minimizing the Expected Loss. Topics of This Lecture. Recap: Maximum Likelihood Approach Truth Course Outline Machine Learning Lecture 3 Fundamentals (2 weeks) Bayes Decision Theory Probability Density Estimation Probability Density Estimation II 2.04.205 Discriminative Approaches (5 weeks)

More information

( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components

( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components Review Lecture 14 ! PRINCIPAL COMPONENT ANALYSIS Eigenvectors of the covariance matrix are the principal components 1. =cov X Top K principal components are the eigenvectors with K largest eigenvalues

More information

An Introduction to PDF Estimation and Clustering

An Introduction to PDF Estimation and Clustering Sigmedia, Electronic Engineering Dept., Trinity College, Dublin. 1 An Introduction to PDF Estimation and Clustering David Corrigan corrigad@tcd.ie Electrical and Electronic Engineering Dept., University

More information

Region-based Segmentation

Region-based Segmentation Region-based Segmentation Image Segmentation Group similar components (such as, pixels in an image, image frames in a video) to obtain a compact representation. Applications: Finding tumors, veins, etc.

More information

Scene Recognition using Bag-of-Words

Scene Recognition using Bag-of-Words Scene Recognition using Bag-of-Words Sarthak Ahuja B.Tech Computer Science Indraprastha Institute of Information Technology Okhla, Delhi 110020 Email: sarthak12088@iiitd.ac.in Anchita Goel B.Tech Computer

More information

CS Introduction to Data Mining Instructor: Abdullah Mueen

CS Introduction to Data Mining Instructor: Abdullah Mueen CS 591.03 Introduction to Data Mining Instructor: Abdullah Mueen LECTURE 8: ADVANCED CLUSTERING (FUZZY AND CO -CLUSTERING) Review: Basic Cluster Analysis Methods (Chap. 10) Cluster Analysis: Basic Concepts

More information

Data Analysis 3. Support Vector Machines. Jan Platoš October 30, 2017

Data Analysis 3. Support Vector Machines. Jan Platoš October 30, 2017 Data Analysis 3 Support Vector Machines Jan Platoš October 30, 2017 Department of Computer Science Faculty of Electrical Engineering and Computer Science VŠB - Technical University of Ostrava Table of

More information

BossaNova at ImageCLEF 2012 Flickr Photo Annotation Task

BossaNova at ImageCLEF 2012 Flickr Photo Annotation Task BossaNova at ImageCLEF 2012 Flickr Photo Annotation Task S. Avila 1,2, N. Thome 1, M. Cord 1, E. Valle 3, and A. de A. Araújo 2 1 Pierre and Marie Curie University, UPMC-Sorbonne Universities, LIP6, France

More information

Overview of the MPEG-CDVS standard

Overview of the MPEG-CDVS standard JAN 2015 1 Overview of the MPEG-CDVS standard Ling-Yu Duan, Member, IEEE, Vijay Chandrasekhar, Member, IEEE, Jie Chen, Jie Lin, Member, IEEE, Zhe Wang, Tiejun Huang, Senior Member, IEEE, Bernd Girod, Fellow,

More information

Image Analysis & Retrieval

Image Analysis & Retrieval Outline CS/EE 5590 / ENG 401 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Image Analysis & Retrieval Background Objective of the class Prerequisite Lecture Plan Course Project

More information

Unsupervised Learning

Unsupervised Learning Networks for Pattern Recognition, 2014 Networks for Single Linkage K-Means Soft DBSCAN PCA Networks for Kohonen Maps Linear Vector Quantization Networks for Problems/Approaches in Machine Learning Supervised

More information

Speech Recognition Lecture 8: Acoustic Models. Eugene Weinstein Google, NYU Courant Institute Slide Credit: Mehryar Mohri

Speech Recognition Lecture 8: Acoustic Models. Eugene Weinstein Google, NYU Courant Institute Slide Credit: Mehryar Mohri Speech Recognition Lecture 8: Acoustic Models. Eugene Weinstein Google, NYU Courant Institute eugenew@cs.nyu.edu Slide Credit: Mehryar Mohri Speech Recognition Components Acoustic and pronunciation model:

More information

Video event detection using subclass discriminant analysis and linear support vector machines

Video event detection using subclass discriminant analysis and linear support vector machines Video event detection using subclass discriminant analysis and linear support vector machines Nikolaos Gkalelis, Damianos Galanopoulos, Vasileios Mezaris / TRECVID 2014 Workshop, Orlando, FL, USA, November

More information

Normalized Texture Motifs and Their Application to Statistical Object Modeling

Normalized Texture Motifs and Their Application to Statistical Object Modeling Normalized Texture Motifs and Their Application to Statistical Obect Modeling S. D. Newsam B. S. Manunath Center for Applied Scientific Computing Electrical and Computer Engineering Lawrence Livermore

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen der Künstlichen Intelligenz Grundlagen der Künstlichen Intelligenz Unsupervised learning Daniel Hennes 29.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Supervised learning Regression (linear

More information

Inference and Representation

Inference and Representation Inference and Representation Rachel Hodos New York University Lecture 5, October 6, 2015 Rachel Hodos Lecture 5: Inference and Representation Today: Learning with hidden variables Outline: Unsupervised

More information

Multiple Kernel Learning for Emotion Recognition in the Wild

Multiple Kernel Learning for Emotion Recognition in the Wild Multiple Kernel Learning for Emotion Recognition in the Wild Karan Sikka, Karmen Dykstra, Suchitra Sathyanarayana, Gwen Littlewort and Marian S. Bartlett Machine Perception Laboratory UCSD EmotiW Challenge,

More information

Classifying Images with Visual/Textual Cues. By Steven Kappes and Yan Cao

Classifying Images with Visual/Textual Cues. By Steven Kappes and Yan Cao Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao Motivation Image search Building large sets of classified images Robotics Background Object recognition is unsolved Deformable shaped

More information

[Programming Assignment] (1)

[Programming Assignment] (1) http://crcv.ucf.edu/people/faculty/bagci/ [Programming Assignment] (1) Computer Vision Dr. Ulas Bagci (Fall) 2015 University of Central Florida (UCF) Coding Standard and General Requirements Code for all

More information

Gaussian Mixture Models For Clustering Data. Soft Clustering and the EM Algorithm

Gaussian Mixture Models For Clustering Data. Soft Clustering and the EM Algorithm Gaussian Mixture Models For Clustering Data Soft Clustering and the EM Algorithm K-Means Clustering Input: Observations: xx ii R dd ii {1,., NN} Number of Clusters: kk Output: Cluster Assignments. Cluster

More information

Clustering web search results

Clustering web search results Clustering K-means Machine Learning CSE546 Emily Fox University of Washington November 4, 2013 1 Clustering images Set of Images [Goldberger et al.] 2 1 Clustering web search results 3 Some Data 4 2 K-means

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 Clustering and EM Barnabás Póczos & Aarti Singh Contents Clustering K-means Mixture of Gaussians Expectation Maximization Variational Methods 2 Clustering 3 K-

More information

Client Dependent GMM-SVM Models for Speaker Verification

Client Dependent GMM-SVM Models for Speaker Verification Client Dependent GMM-SVM Models for Speaker Verification Quan Le, Samy Bengio IDIAP, P.O. Box 592, CH-1920 Martigny, Switzerland {quan,bengio}@idiap.ch Abstract. Generative Gaussian Mixture Models (GMMs)

More information

Adaptive Binary Quantization for Fast Nearest Neighbor Search

Adaptive Binary Quantization for Fast Nearest Neighbor Search IBM Research Adaptive Binary Quantization for Fast Nearest Neighbor Search Zhujin Li 1, Xianglong Liu 1*, Junjie Wu 1, and Hao Su 2 1 Beihang University, Beijing, China 2 Stanford University, Stanford,

More information

Mixture Models and EM

Mixture Models and EM Table of Content Chapter 9 Mixture Models and EM -means Clustering Gaussian Mixture Models (GMM) Expectation Maximiation (EM) for Mixture Parameter Estimation Introduction Mixture models allows Complex

More information

Learning Compact Visual Attributes for Large-scale Image Classification

Learning Compact Visual Attributes for Large-scale Image Classification Learning Compact Visual Attributes for Large-scale Image Classification Yu Su and Frédéric Jurie GREYC CNRS UMR 6072, University of Caen Basse-Normandie, Caen, France {yu.su,frederic.jurie}@unicaen.fr

More information

Support Vector Machines

Support Vector Machines Support Vector Machines About the Name... A Support Vector A training sample used to define classification boundaries in SVMs located near class boundaries Support Vector Machines Binary classifiers whose

More information

Feature Selection for Image Retrieval and Object Recognition

Feature Selection for Image Retrieval and Object Recognition Feature Selection for Image Retrieval and Object Recognition Nuno Vasconcelos et al. Statistical Visual Computing Lab ECE, UCSD Presented by Dashan Gao Scalable Discriminant Feature Selection for Image

More information

Image Analysis & Retrieval Lec-01: Introduction

Image Analysis & Retrieval Lec-01: Introduction CS/EE 5590 / ENG 401 Special Topics Spring 2017, M/W 5:30-6:45pm@Haag 309 Image Analysis & Retrieval Lec-01: Introduction Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph: x 2346. http://l.web.umkc.edu/lizhu

More information

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Part II: Visual Features and Representations Liangliang Cao, IBM Watson Research Center Evolvement of Visual Features

More information

Compressed local descriptors for fast image and video search in large databases

Compressed local descriptors for fast image and video search in large databases Compressed local descriptors for fast image and video search in large databases Matthijs Douze2 joint work with Hervé Jégou1, Cordelia Schmid2 and Patrick Pérez3 1: INRIA Rennes, TEXMEX team, France 2:

More information

Content-based image and video analysis. Machine learning

Content-based image and video analysis. Machine learning Content-based image and video analysis Machine learning for multimedia retrieval 04.05.2009 What is machine learning? Some problems are very hard to solve by writing a computer program by hand Almost all

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:

More information

Speed-up Multi-modal Near Duplicate Image Detection

Speed-up Multi-modal Near Duplicate Image Detection Open Journal of Applied Sciences, 2013, 3, 16-21 Published Online March 2013 (http://www.scirp.org/journal/ojapps) Speed-up Multi-modal Near Duplicate Image Detection Chunlei Yang 1,2, Jinye Peng 2, Jianping

More information

Expectation Maximization (EM) and Gaussian Mixture Models

Expectation Maximization (EM) and Gaussian Mixture Models Expectation Maximization (EM) and Gaussian Mixture Models Reference: The Elements of Statistical Learning, by T. Hastie, R. Tibshirani, J. Friedman, Springer 1 2 3 4 5 6 7 8 Unsupervised Learning Motivation

More information

Object Classification Problem

Object Classification Problem HIERARCHICAL OBJECT CATEGORIZATION" Gregory Griffin and Pietro Perona. Learning and Using Taxonomies For Fast Visual Categorization. CVPR 2008 Marcin Marszalek and Cordelia Schmid. Constructing Category

More information

Computer Vision II Lecture 14

Computer Vision II Lecture 14 Computer Vision II Lecture 14 Articulated Tracking I 08.07.2014 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Outline of This Lecture Single-Object Tracking Bayesian

More information

Homework #4 Programming Assignment Due: 11:59 pm, November 4, 2018

Homework #4 Programming Assignment Due: 11:59 pm, November 4, 2018 CSCI 567, Fall 18 Haipeng Luo Homework #4 Programming Assignment Due: 11:59 pm, ovember 4, 2018 General instructions Your repository will have now a directory P4/. Please do not change the name of this

More information

SUT Submission for NIST 2016 Speaker Recognition Evaluation: Description and Analysis

SUT Submission for NIST 2016 Speaker Recognition Evaluation: Description and Analysis The 2017 Conference on Computational Linguistics and Speech Processing ROCLING 2017, pp. 276-286 The Association for Computational Linguistics and Chinese Language Processing SUT Submission for NIST 2016

More information

Computer Vision for HCI. Topics of This Lecture

Computer Vision for HCI. Topics of This Lecture Computer Vision for HCI Interest Points Topics of This Lecture Local Invariant Features Motivation Requirements, Invariances Keypoint Localization Features from Accelerated Segment Test (FAST) Harris Shi-Tomasi

More information