Lecture 5: Clustering and Segmenta4on Part 1
|
|
- Harry Robinson
- 5 years ago
- Views:
Transcription
1 Lecture 5: Clustering and Segmenta4on Part 1 Professor Fei- Fei Li Stanford Vision Lab Lecture 5 -! 1
2 What we will learn today Segmenta4on and grouping Gestalt principles Segmenta4on as clustering K- means Feature space Probabilis4c clustering (Problem Set 1 (Q3)) Mixture of Gaussians, EM Lecture 5 -! 2
3 Lecture 5 -! 3
4 Image Segmenta4on Goal: iden4fy groups of pixels that go together Slide credit: Steve Seitz, Kristen Grauman Lecture 5 -! 4
5 The Goals of Segmenta4on Separate image into coherent objects Image Human segmenta4on Slide credit: Svetlana Lazebnik Lecture 5 -! 5
6 The Goals of Segmenta4on Separate image into coherent objects Group together similar- looking pixels for efficiency of further processing superpixels X. Ren and J. Malik. Learning a classifica4on model for segmenta4on. ICCV Slide credit: Svetlana Lazebnik Lecture 5 -! 6
7 Segmenta4on Compact representa4on for image data in terms of a set of components Components share common visual proper4es Proper4es can be defined at different level of abstrac4ons Lecture 5 -! 7
8 General ideas Tokens whatever we need to group (pixels, points, surface elements, etc., etc.) Bobom up segmenta4on tokens belong together because they are locally coherent Top down segmenta4on This lecture (#5) tokens belong together because they lie on the same visual en4ty (object, scene ) > These two are not mutually exclusive Lecture 5 -! 8
9 What is Segmenta4on? Clustering image elements that belong together Par44oning Divide into regions/sequences with coherent internal proper4es Grouping Iden4fy sets of coherent tokens in image Slide credit: Christopher Rasmussen Lecture 5 -! 9
10 What is Segmenta4on? Why do these tokens belong together? Lecture 5 -! 10
11 Basic ideas of grouping in human vision Gestalt proper4es Figure- ground discrimina4on Lecture 5 -! 11
12 Examples of Grouping in Vision Grouping video frames into shots Determining image regions What things should be grouped? Figure- ground What cues indicate groups? Slide credit: Kristen Grauman Object- level grouping Lecture 5 -!12
13 Similarity Slide credit: Kristen Grauman Lecture 5 -! 13
14 Symmetry Slide credit: Kristen Grauman Lecture 5 -! 14
15 Common Fate Image credit: Arthus- Bertrand (via F. Durand) Slide credit: Kristen Grauman Lecture 5 -! 15
16 Proximity Slide credit: Kristen Grauman Lecture 5 -! 16
17 Muller- Lyer Illusion Gestalt principle: grouping is key to visual percep4on. Lecture 5 -! 17
18 The Gestalt School Grouping is key to visual percep4on Elements in a collec4on can have proper4es that result from rela4onships The whole is greater than the sum of its parts Illusory/subjec4ve contours Occlusion Familiar configura4on hbp://en.wikipedia.org/wiki/gestalt_psychology Slide credit: Svetlana Lazebnik Lecture 5 -! 18
19 Gestalt Theory Gestalt: whole or group Whole is greater than sum of its parts Rela4onships among parts can yield new proper4es/features Psychologists iden4fied series of factors that predispose set of elements to be grouped (by human visual system) I stand at the window and see a house, trees, sky. Theoretically I might say there were 327 brightnesses and nuances of colour. Do I have "327"? No. I have sky, house, and trees. Max Wertheimer ( ) Untersuchungen zur Lehre von der Gestalt, Psychologische Forschung, Vol. 4, pp , Lecture 5 -! 19
20 Gestalt Factors These factors make intui4ve sense, but are very difficult to translate into algorithms. Image source: Forsyth & Ponce Lecture 5 -! 20
21 Con4nuity through Occlusion Cues Lecture 5 -! 21
22 Con4nuity through Occlusion Cues Con4nuity, explana4on by occlusion Lecture 5 -! 22
23 Con4nuity through Occlusion Cues Image source: Forsyth & Ponce Lecture 5 -! 23
24 Con4nuity through Occlusion Cues Image source: Forsyth & Ponce Lecture 5 -! 24
25 Figure- Ground Discrimina4on Lecture 5 -! 25
26 The Ul4mate Gestalt? Lecture 5 -! 26
27 What we will learn today Segmenta4on and grouping Gestalt principles Segmenta4on as clustering K- means Feature space Probabilis4c clustering Mixture of Gaussians, EM Model- free clustering Mean- ship Lecture 5 -! 27
28 Image Segmenta4on: Toy Example black pixels gray pixels white pixels input image intensity These intensi4es define the three groups. We could label every pixel in the image according to which of these primary intensi4es it is. i.e., segment the image based on the intensity feature. What if the image isn t quite so simple? Slide credit: Kristen Grauman Lecture 5 -! 28
29 Pixel count Input image Intensity Pixel count Input image Slide credit: Kristen Grauman Intensity Lecture 5 -! 29
30 Pixel count Input image Intensity Now how to determine the three main intensi4es that define our groups? We need to cluster. Slide credit: Kristen Grauman Lecture 5 -! 30
31 Intensity Goal: choose three centers as the representa4ve intensi4es, and label every pixel according to which of these centers it is nearest to. Best cluster centers are those that minimize Sum of Square Distance (SSD) between all points and their nearest cluster center c i : SSD= clusters i p cluster i p c i 2 Slide credit: Kristen Grauman Lecture 5 -! 31
32 Clustering With this objec4ve, it is a chicken and egg problem: If we knew the cluster centers, we could allocate points to groups by assigning each to its closest center. If we knew the group memberships, we could get the centers by compu4ng the mean per group. Slide credit: Kristen Grauman Lecture 5 -! 32
33 K- Means Clustering Basic idea: randomly ini4alize the k cluster centers, and iterate between the two steps we just saw. 1. Randomly ini4alize the cluster centers, c 1,..., c K 2. Given cluster centers, determine points in each cluster For each point p, find the closest c i. Put p into cluster i 3. Given points in each cluster, solve for c i Set c i to be the mean of points in cluster i 4. If c i have changed, repeat Step 2 Proper4es Will always converge to some solu4on Can be a local minimum Does not always find the global minimum of objec4ve func4on: SSD= clusters i p cluster i p c i 2 Slide credit: Steve Seitz Lecture 5 -! 33
34 Segmenta4on as Clustering K=2 img_as_col = double(im(:)); cluster_membs = kmeans(img_as_col, K); K=3 labelim = zeros(size(im)); for i=1:k inds = find(cluster_membs==i); meanval = mean(img_as_column(inds)); labelim(inds) = meanval; end Slide credit: Kristen Grauman Lecture 5 -! 34
35 K- Means Clustering Java demo: hbp://home.dei.polimi.it/mabeucc/clustering/tutorial_html/appletkm.html Lecture 5 -! 35
36 K- Means++ Can we prevent arbitrarily bad local minima? 1. Randomly choose first center. 2. Pick new center with prob. propor4onal to (Contribu4on of p to total error) 3. Repeat un4l k centers. Expected error = O(log k) * op4mal Arthur & Vassilvitskii 2007 Slide credit: Steve Seitz Lecture 5 -! 36
37 Feature Space Depending on what we choose as the feature space, we can group pixels in different ways. Grouping pixels based on intensity similarity Feature space: intensity value (1D) Slide credit: Kristen Grauman Lecture 5 -! 37
38 Feature Space Depending on what we choose as the feature space, we can group pixels in different ways. Grouping pixels based on color similarity B G R=255 G=200 B=250 R=245 G=220 B=248 Feature space: color value (3D) Slide credit: Kristen Grauman R R=15 G=189 B=2 Lecture 5 -! 38 R=3 G=12 B=2
39 Feature Space Depending on what we choose as the feature space, we can group pixels in different ways. Grouping pixels based on texture similarity F 1 F 2 Filter bank of 24 filters F 24 Feature space: filter bank responses (e.g., 24D) Slide credit: Kristen Grauman Lecture 5 -! 39
40 Smoothing Out Cluster Assignments Assigning a cluster label per pixel may yield outliers: Original Labeled by cluster center s intensity How can we ensure they are spa4ally smooth? 1 2? 3 Slide credit: Kristen Grauman Lecture 5 -! 40
41 Segmenta4on as Clustering Depending on what we choose as the feature space, we can group pixels in different ways. Grouping pixels based on intensity+posi9on similarity Intensity Y X Way to encode both similarity and proximity. Slide credit: Kristen Grauman Lecture 5 -! 41
42 K- Means Clustering Results K- means clustering based on intensity or color is essen4ally vector quan4za4on of the image abributes Clusters don t have to be spa4ally coherent Image Intensity- based clusters Color- based clusters Image source: Forsyth & Ponce Lecture 5 -! 42
43 K- Means Clustering Results K- means clustering based on intensity or color is essen4ally vector quan4za4on of the image abributes Clusters don t have to be spa4ally coherent Clustering based on (r,g,b,x,y) values enforces more spa4al coherence Image source: Forsyth & Ponce Lecture 5 -! 43
44 Summary K- Means Pros Simple, fast to compute Converges to local minimum of within- cluster squared error Cons/issues Sewng k? Sensi4ve to ini4al centers Sensi4ve to outliers Detects spherical clusters only Assuming means can be computed Slide credit: Kristen Grauman Lecture 5 -! 44
45 What we will learn today Segmenta4on and grouping Gestalt principles Segmenta4on as clustering K- means Feature space Probabilis4c clustering (Problem Set 1 (Q3)) Mixture of Gaussians, EM Lecture 5 -! 45
46 Probabilis4c Clustering Basic ques4ons What s the probability that a point x is in cluster m? What s the shape of each cluster? K- means doesn t answer these ques4ons. Basic idea Instead of trea4ng the data as a bunch of points, assume that they are all generated by sampling a con4nuous func4on. This func4on is called a genera4ve model. Defined by a vector of parameters θ Slide credit: Steve Seitz Lecture 5 -! 46
47 Mixture of Gaussians One genera4ve model is a mixture of Gaussians (MoG) K Gaussian blobs with means μ b covariance matrices V b, dimension d Blob b defined by: Blob b is selected with probability The likelihood of observing x is a weighted mixture of Gaussians, Slide credit: Steve Seitz Lecture 5 -! 47
48 Expecta4on Maximiza4on (EM) Goal Find blob parameters θ that maximize the likelihood func4on: Approach: 1. E- step: given current guess of blobs, compute ownership of each point 2. M- step: given ownership probabili4es, update blobs to maximize likelihood func4on 3. Repeat un4l convergence Slide credit: Steve Seitz Lecture 5 -! 48
49 EM Details E- step Compute probability that point x is in blob b, given current guess of θ M- step Compute probability that blob b is selected (N data points) Mean of blob b Covariance of blob b Slide credit: Steve Seitz Lecture 5 -! 49
50 Applica4ons of EM Turns out this is useful for all sorts of problems Any clustering problem Any model es4ma4on problem Missing data problems Finding outliers Segmenta4on problems Segmenta4on based on color Segmenta4on based on mo4on Foreground/background separa4on... EM demo hbp://lcn.epfl.ch/tutorial/english/gaussian/html/index.html Slide credit: Steve Seitz Lecture 5 -! 50
51 Segmenta4on with EM Original image EM segmentation results k=2 k=3 k=4 k=5 Image source: Serge Belongie Lecture 5 -! 51
52 Summary: Mixtures of Gaussians, EM Pros Probabilis4c interpreta4on Sop assignments between data points and clusters Genera4ve model, can predict novel data points Rela4vely compact storage Cons Local minima Ini4aliza4on Open a good idea to start with some k- means itera4ons. Need to know number of components Solu4ons: model selec4on (AIC, BIC), Dirichlet process mixture Need to choose genera4ve model Numerical problems are open a nuisance Lecture 5 -! 52
53 What we have learned today Segmenta4on and grouping Gestalt principles Segmenta4on as clustering K- means Feature space Probabilis4c clustering (Problem Set 1 (Q3)) Mixture of Gaussians, EM Lecture 5 -! 53
Lecture 5: Clustering and Segmentation Part 1
Lecture 5: Clustering and Segmentation Part 1 Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today Segmentation and grouping Gestalt principles Segmentation as clustering K means Feature
More informationBBM 413 Fundamentals of Image Processing Dec. 11, Erkut Erdem Dept. of Computer Engineering Hacettepe University. Segmentation Part 1
BBM 413 Fundamentals of Image Processing Dec. 11, 2012 Erkut Erdem Dept. of Computer Engineering Hacettepe University Segmentation Part 1 Image segmentation Goal: identify groups of pixels that go together
More informationIndexing local features. Wed March 30 Prof. Kristen Grauman UT-Austin
Indexing local features Wed March 30 Prof. Kristen Grauman UT-Austin Matching local features Kristen Grauman Matching local features? Image 1 Image 2 To generate candidate matches, find patches that have
More informationIndexing local features and instance recognition
Indexing local features and instance recognition May 14 th, 2015 Yong Jae Lee UC Davis Announcements PS2 due Saturday 11:59 am 2 Approximating the Laplacian We can approximate the Laplacian with a difference
More informationCS 1674: Intro to Computer Vision. Face Detection. Prof. Adriana Kovashka University of Pittsburgh November 7, 2016
CS 1674: Intro to Computer Vision Face Detection Prof. Adriana Kovashka University of Pittsburgh November 7, 2016 Today Window-based generic object detection basic pipeline boosting classifiers face detection
More informationECS 189G: Intro to Computer Vision March 31 st, Yong Jae Lee Assistant Professor CS, UC Davis
ECS 189G: Intro to Computer Vision March 31 st, 2015 Yong Jae Lee Assistant Professor CS, UC Davis Plan for today Topic overview Introductions Course overview: Logistics and requirements 2 What is Computer
More informationInstance Recognition. Jia-Bin Huang Virginia Tech ECE 6554 Advanced Computer Vision
Instance Recognition Jia-Bin Huang Virginia Tech ECE 6554 Advanced Computer Vision Administrative stuffs Paper review submitted? Topic presentation Experiment presentation For / Against discussion lead
More informationCS 1674: Intro to Computer Vision. Intro to Recognition. Prof. Adriana Kovashka University of Pittsburgh October 24, 2016
CS 1674: Intro to Computer Vision Intro to Recognition Prof. Adriana Kovashka University of Pittsburgh October 24, 2016 Plan for today Examples of visual recognition problems What should we recognize?
More information8. Schelling's Segrega0on Model
8. Schelling's Segrega0on Model Modelling Social Interac0on in Informa0on systems h9p://davidhales.com/msiis David Hales, University of Szeged dave@davidhales.com Schelling s segrega0on model Seminal Agent
More informationCS 2770: Computer Vision. Introduction. Prof. Adriana Kovashka University of Pittsburgh January 5, 2017
CS 2770: Computer Vision Introduction Prof. Adriana Kovashka University of Pittsburgh January 5, 2017 About the Instructor Born 1985 in Sofia, Bulgaria Got BA in 2008 at Pomona College, CA (Computer Science
More informationGraphical Perception. Graphical Perception. Graphical Perception. Which best encodes quantities? Jeffrey Heer Stanford University
CS448B :: 7 Oct 2010 Graphical Perception Graphical Perception Jeffrey Heer Stanford University Graphical Perception The ability of viewers to interpret visual (graphical) encodings of information and
More informationGraphical Perception. Graphical Perception. Which best encodes quantities?
CS448B :: 11 Oct 2012 Graphical Perception Graphical Perception The ability of viewers to interpret visual (graphical) encodings of information and thereby decode information in graphs. Jeffrey Heer Stanford
More informationAutomatic LP Digitalization Spring Group 6: Michael Sibley, Alexander Su, Daphne Tsatsoulis {msibley, ahs1,
Automatic LP Digitalization 18-551 Spring 2011 Group 6: Michael Sibley, Alexander Su, Daphne Tsatsoulis {msibley, ahs1, ptsatsou}@andrew.cmu.edu Introduction This project was originated from our interest
More informationCSE Data Visualization. Graphical Perception. Jeffrey Heer University of Washington
CSE 512 - Data Visualization Graphical Perception Jeffrey Heer University of Washington Design Principles [Mackinlay 86] Expressiveness A set of facts is expressible in a visual language if the sentences
More informationGeneric object recognition
Generic object recognition May 19 th, 2015 Yong Jae Lee UC Davis Announcements PS3 out; due 6/3, 11:59 pm Sign attendance sheet (3 rd one) 2 Indexing local features 3 Kristen Grauman Visual words Map high-dimensional
More informationCS229 Project Report Polyphonic Piano Transcription
CS229 Project Report Polyphonic Piano Transcription Mohammad Sadegh Ebrahimi Stanford University Jean-Baptiste Boin Stanford University sadegh@stanford.edu jbboin@stanford.edu 1. Introduction In this project
More informationCS 1699: Intro to Computer Vision. Introduction. Prof. Adriana Kovashka University of Pittsburgh September 1, 2015
CS 1699: Intro to Computer Vision Introduction Prof. Adriana Kovashka University of Pittsburgh September 1, 2015 Course Info Course website: http://people.cs.pitt.edu/~kovashka/cs1699 Instructor: Adriana
More informationSupervised Learning in Genre Classification
Supervised Learning in Genre Classification Introduction & Motivation Mohit Rajani and Luke Ekkizogloy {i.mohit,luke.ekkizogloy}@gmail.com Stanford University, CS229: Machine Learning, 2009 Now that music
More informationContemporary philosophy. 12 th April
Contemporary philosophy 12 th April The problem Distance, 8me, needs, death and heritage have always made it hard to understand how human beings share world, how Nature is understandable to each of us
More informationLatin Square Design. Design of Experiments - Montgomery Section 4-2
Latin Square Design Design of Experiments - Montgomery Section 4-2 Latin Square Design Can be used when goal is to block on two nuisance factors Constructed so blocking factors orthogonal to treatment
More informationA Framework for Segmentation of Interview Videos
A Framework for Segmentation of Interview Videos Omar Javed, Sohaib Khan, Zeeshan Rasheed, Mubarak Shah Computer Vision Lab School of Electrical Engineering and Computer Science University of Central Florida
More informationVISUAL CONTENT BASED SEGMENTATION OF TALK & GAME SHOWS. O. Javed, S. Khan, Z. Rasheed, M.Shah. {ojaved, khan, zrasheed,
VISUAL CONTENT BASED SEGMENTATION OF TALK & GAME SHOWS O. Javed, S. Khan, Z. Rasheed, M.Shah {ojaved, khan, zrasheed, shah}@cs.ucf.edu Computer Vision Lab School of Electrical Engineering and Computer
More informationOSL Preprocessing Henry Luckhoo. Wednesday, 23 October 13
OSL Preprocessing OHBA s So7ware Library OSL SPM FMRIB fastica Neuromag Netlab Custom Fieldtrip OSL can be used for task and rest analyses preprocessing sensor space analysis source reconstrucaon staasacs
More informationModeling memory for melodies
Modeling memory for melodies Daniel Müllensiefen 1 and Christian Hennig 2 1 Musikwissenschaftliches Institut, Universität Hamburg, 20354 Hamburg, Germany 2 Department of Statistical Science, University
More informationReconstruction of Ca 2+ dynamics from low frame rate Ca 2+ imaging data CS229 final project. Submitted by: Limor Bursztyn
Reconstruction of Ca 2+ dynamics from low frame rate Ca 2+ imaging data CS229 final project. Submitted by: Limor Bursztyn Introduction Active neurons communicate by action potential firing (spikes), accompanied
More informationIntroduction to Psychology Prof. Braj Bhushan Department of Humanities and Social Sciences Indian Institute of Technology, Kanpur
Introduction to Psychology Prof. Braj Bhushan Department of Humanities and Social Sciences Indian Institute of Technology, Kanpur Lecture 08 Perception Gestalt Principles Till now, we have talked about
More informationData Mining. Dr. Raed Ibraheem Hamed. University of Human Development, College of Science and Technology Department of CS
Data Mining Dr. Raed Ibraheem Hamed University of Human Development, College of Science and Technology Department of CS 2016 2017 Road map Common Distance measures The Euclidean Distance between 2 variables
More informationResearch Article. ISSN (Print) *Corresponding author Shireen Fathima
Scholars Journal of Engineering and Technology (SJET) Sch. J. Eng. Tech., 2014; 2(4C):613-620 Scholars Academic and Scientific Publisher (An International Publisher for Academic and Scientific Resources)
More informationMidiFind: Fast and Effec/ve Similarity Searching in Large MIDI Databases
1 MidiFind: Fast and Effec/ve Similarity Searching in Large MIDI Databases Gus Xia Tongbo Huang Yifei Ma Roger B. Dannenberg Christos Faloutsos Schools of Computer Science Carnegie Mellon University 2
More informationTechnical Specifications
1 Contents INTRODUCTION...3 ABOUT THIS LAB...3 IMPORTANCE OF THE MODULE...3 APPLYING IMAGE ENHANCEMENTS...4 Adjusting Toolbar Enhancement...4 EDITING A LOOKUP TABLE...5 Trace-editing the LUT...6 Comparing
More informationAlgorithmic Music Composition
Algorithmic Music Composition MUS-15 Jan Dreier July 6, 2015 1 Introduction The goal of algorithmic music composition is to automate the process of creating music. One wants to create pleasant music without
More informationDigital Color Management Basics. An Introduc6on for Mo6on Pictures
Digital Color Management Basics An Introduc6on for Mo6on Pictures Reference Reading Review Hunt, Chapter 11, Objec6ves in Colour Reproduc6on 2 Defini6on of Color Management Every successful color-imaging
More informationN T I. Introduction. II. Proposed Adaptive CTI Algorithm. III. Experimental Results. IV. Conclusion. Seo Jeong-Hoon
An Adaptive Color Transient Improvement Algorithm IEEE Transactions on Consumer Electronics Vol. 49, No. 4, November 2003 Peng Lin, Yeong-Taeg Kim jhseo@dms.sejong.ac.kr 0811136 Seo Jeong-Hoon CONTENTS
More informationLossless Compression Algorithms for Direct- Write Lithography Systems
Lossless Compression Algorithms for Direct- Write Lithography Systems Hsin-I Liu Video and Image Processing Lab Department of Electrical Engineering and Computer Science University of California at Berkeley
More informationHidden Markov Model based dance recognition
Hidden Markov Model based dance recognition Dragutin Hrenek, Nenad Mikša, Robert Perica, Pavle Prentašić and Boris Trubić University of Zagreb, Faculty of Electrical Engineering and Computing Unska 3,
More informationRecap of Last (Last) Week
Recap of Last (Last) Week 1 The Beauty of Information Visualization Napoléon s Historical Retreat 2 Course Design Homepage: have you visited and registered? 3 The Value of Information Visualization Have
More informationMUSI-6201 Computational Music Analysis
MUSI-6201 Computational Music Analysis Part 9.1: Genre Classification alexander lerch November 4, 2015 temporal analysis overview text book Chapter 8: Musical Genre, Similarity, and Mood (pp. 151 155)
More informationBrowsing News and Talk Video on a Consumer Electronics Platform Using Face Detection
Browsing News and Talk Video on a Consumer Electronics Platform Using Face Detection Kadir A. Peker, Ajay Divakaran, Tom Lanning Mitsubishi Electric Research Laboratories, Cambridge, MA, USA {peker,ajayd,}@merl.com
More informationMachine Translation Part 2, and the EM Algorithm
Machine Translation Part 2, and the EM Algorithm CS 585, Fall 2015 Introduction to Natural Language Processing http://people.cs.umass.edu/~brenocon/inlp2015/ Brendan O Connor College of Information and
More informationSpa$al Programming for Musical Representa$on and Analysis
Spa$al Programming for Musical Representa$on and nalysis Louis igo & ntoine Spicher & Olivier Michel mgs.spatial-computing.org LL, University Paris st réteil LIO, University of Orléans Mai 23-24, 2011
More informationLinköping University Post Print. Packet Video Error Concealment With Gaussian Mixture Models
Linköping University Post Print Packet Video Error Concealment With Gaussian Mixture Models Daniel Persson, Thomas Eriksson and Per Hedelin N.B.: When citing this work, cite the original article. 2009
More informationModule 3: Video Sampling Lecture 16: Sampling of video in two dimensions: Progressive vs Interlaced scans. The Lecture Contains:
The Lecture Contains: Sampling of Video Signals Choice of sampling rates Sampling a Video in Two Dimensions: Progressive vs. Interlaced Scans file:///d /...e%20(ganesh%20rana)/my%20course_ganesh%20rana/prof.%20sumana%20gupta/final%20dvsp/lecture16/16_1.htm[12/31/2015
More informationTopic 10. Multi-pitch Analysis
Topic 10 Multi-pitch Analysis What is pitch? Common elements of music are pitch, rhythm, dynamics, and the sonic qualities of timbre and texture. An auditory perceptual attribute in terms of which sounds
More informationDiscrete, Bounded Reasoning in Games
Discrete, Bounded Reasoning in Games Level-k Thinking and Cognitive Hierarchies Joe Corliss Graduate Group in Applied Mathematics Department of Mathematics University of California, Davis June 12, 2015
More informationTime Series Models for Semantic Music Annotation Emanuele Coviello, Antoni B. Chan, and Gert Lanckriet
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 19, NO. 5, JULY 2011 1343 Time Series Models for Semantic Music Annotation Emanuele Coviello, Antoni B. Chan, and Gert Lanckriet Abstract
More informationVBM683 Machine Learning
VBM683 Machine Learning Pinar Duygulu Slides are adapted from Dhruv Batra, David Sontag, Aykut Erdem Quotes If you were a current computer science student what area would you start studying heavily? Answer:
More informationAudio Structure Analysis
Lecture Music Processing Audio Structure Analysis Meinard Müller International Audio Laboratories Erlangen meinard.mueller@audiolabs-erlangen.de Music Structure Analysis Music segmentation pitch content
More informationAUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION
AUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION Halfdan Rump, Shigeki Miyabe, Emiru Tsunoo, Nobukata Ono, Shigeki Sagama The University of Tokyo, Graduate
More informationDisplays and framebuffers. CSE 457 Winter 2015
Displays and framebuffers CSE 457 Winter 2015 Reading! Angel, sec*ons 1.2, 2.1-2.7, 2.11.5! OpenGL Programming Guide (the red book available online): First four sec*ons of chapter 2 First sec*on of chapter
More informationDAY 1. Intelligent Audio Systems: A review of the foundations and applications of semantic audio analysis and music information retrieval
DAY 1 Intelligent Audio Systems: A review of the foundations and applications of semantic audio analysis and music information retrieval Jay LeBoeuf Imagine Research jay{at}imagine-research.com Rebecca
More informationMusic Recommendation from Song Sets
Music Recommendation from Song Sets Beth Logan Cambridge Research Laboratory HP Laboratories Cambridge HPL-2004-148 August 30, 2004* E-mail: Beth.Logan@hp.com music analysis, information retrieval, multimedia
More informationMurdoch redux. Colorimetry as Linear Algebra. Math of additive mixing. Approaching color mathematically. RGB colors add as vectors
Murdoch redux Colorimetry as Linear Algebra CS 465 Lecture 23 RGB colors add as vectors so do primary spectra in additive display (CRT, LCD, etc.) Chromaticity: color ratios (r = R/(R+G+B), etc.) color
More informationAudio-over-IP Technology Pavilion
Introduc)on Professional media networking is becoming increasingly important throughout this industry The advantages that IP technology can provide are now clearly recognized Audio networking has become
More informationPart II Video. General Concepts MPEG1 encoding MPEG2 encoding MPEG4 encoding
Part II Video General Concepts MPEG1 encoding MPEG2 encoding MPEG4 encoding Video General Concepts Video generali:es Video is a sequence of frames consecu:vely transmiaed and displayed so to provide a
More informationBeyond Worst Case Analysis in Approxima4on Uriel Feige The Weizmann Ins2tute
Beyond Worst Case Analysis in Approxima4on Uriel Feige The Weizmann Ins2tute 1 Plan of talk Survey some known approxima2on algorithms and open ques2ons for worst case and random instances of: max-3sat
More informationAP Statistics Sampling. Sampling Exercise (adapted from a document from the NCSSM Leadership Institute, July 2000).
AP Statistics Sampling Name Sampling Exercise (adapted from a document from the NCSSM Leadership Institute, July 2000). Problem: A farmer has just cleared a field for corn that can be divided into 100
More informationInverse Filtering by Signal Reconstruction from Phase. Megan M. Fuller
Inverse Filtering by Signal Reconstruction from Phase by Megan M. Fuller B.S. Electrical Engineering Brigham Young University, 2012 Submitted to the Department of Electrical Engineering and Computer Science
More informationProbabilistic Grammars for Music
Probabilistic Grammars for Music Rens Bod ILLC, University of Amsterdam Nieuwe Achtergracht 166, 1018 WV Amsterdam rens@science.uva.nl Abstract We investigate whether probabilistic parsing techniques from
More informationDART Tutorial Sec'on 18: Lost in Phase Space: The Challenge of Not Knowing the Truth.
DART Tutorial Sec'on 18: Lost in Phase Space: The Challenge of Not Knowing the Truth. UCAR 214 The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings
More informationMUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES
MUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES Jun Wu, Yu Kitano, Stanislaw Andrzej Raczynski, Shigeki Miyabe, Takuya Nishimoto, Nobutaka Ono and Shigeki Sagayama The Graduate
More informationMODELS of music begin with a representation of the
602 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 3, MARCH 2010 Modeling Music as a Dynamic Texture Luke Barrington, Student Member, IEEE, Antoni B. Chan, Member, IEEE, and
More informationSoftware Engineering 2DA4. Slides 3: Optimized Implementation of Logic Functions
Software Engineering 2DA4 Slides 3: Optimized Implementation of Logic Functions Dr. Ryan Leduc Department of Computing and Software McMaster University Material based on S. Brown and Z. Vranesic, Fundamentals
More informationDATA COMPRESSION USING THE FFT
EEE 407/591 PROJECT DUE: NOVEMBER 21, 2001 DATA COMPRESSION USING THE FFT INSTRUCTOR: DR. ANDREAS SPANIAS TEAM MEMBERS: IMTIAZ NIZAMI - 993 21 6600 HASSAN MANSOOR - 993 69 3137 Contents TECHNICAL BACKGROUND...
More informationLOCOCODE versus PCA and ICA. Jurgen Schmidhuber. IDSIA, Corso Elvezia 36. CH-6900-Lugano, Switzerland. Abstract
LOCOCODE versus PCA and ICA Sepp Hochreiter Technische Universitat Munchen 80290 Munchen, Germany Jurgen Schmidhuber IDSIA, Corso Elvezia 36 CH-6900-Lugano, Switzerland Abstract We compare the performance
More informationSubject-specific observed profiles of change from baseline vs week trt=10000u
Mean of age 1 The MEANS Procedure Analysis Variable : age N Mean Std Dev Minimum Maximum ƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒƒ 109 55.5321101 12.1255537 26.0000000 83.0000000
More informationTDECQ update noise treatment and equalizer optimization (revision of king_3bs_01_0117) 14th February 2017 P802.3bs SMF ad hoc Jonathan King, Finisar
TDECQ update noise treatment and equalizer optimization (revision of king_3bs_01_0117) 14th February 2017 P802.3bs SMF ad hoc Jonathan King, Finisar 1 Preamble TDECQ calculates the db ratio of how much
More informationMelody Extraction from Generic Audio Clips Thaminda Edirisooriya, Hansohl Kim, Connie Zeng
Melody Extraction from Generic Audio Clips Thaminda Edirisooriya, Hansohl Kim, Connie Zeng Introduction In this project we were interested in extracting the melody from generic audio files. Due to the
More informationA repetition-based framework for lyric alignment in popular songs
A repetition-based framework for lyric alignment in popular songs ABSTRACT LUONG Minh Thang and KAN Min Yen Department of Computer Science, School of Computing, National University of Singapore We examine
More informationLecture 18: Exam Review
Lecture 18: Exam Review The Digital World of Multimedia Prof. Mari Ostendorf Announcements HW5 due today, Lab5 due next week Lab4: Printer should be working soon. Exam: Friday, Feb 22 Review in class today
More information19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007
19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007 AN HMM BASED INVESTIGATION OF DIFFERENCES BETWEEN MUSICAL INSTRUMENTS OF THE SAME TYPE PACS: 43.75.-z Eichner, Matthias; Wolff, Matthias;
More informationINTER GENRE SIMILARITY MODELLING FOR AUTOMATIC MUSIC GENRE CLASSIFICATION
INTER GENRE SIMILARITY MODELLING FOR AUTOMATIC MUSIC GENRE CLASSIFICATION ULAŞ BAĞCI AND ENGIN ERZIN arxiv:0907.3220v1 [cs.sd] 18 Jul 2009 ABSTRACT. Music genre classification is an essential tool for
More informationDecision-Maker Preference Modeling in Interactive Multiobjective Optimization
Decision-Maker Preference Modeling in Interactive Multiobjective Optimization 7th International Conference on Evolutionary Multi-Criterion Optimization Introduction This work presents the results of the
More informationMusic Composition with RNN
Music Composition with RNN Jason Wang Department of Statistics Stanford University zwang01@stanford.edu Abstract Music composition is an interesting problem that tests the creativity capacities of artificial
More informationGender and Age Estimation from Synthetic Face Images with Hierarchical Slow Feature Analysis
Gender and Age Estimation from Synthetic Face Images with Hierarchical Slow Feature Analysis Alberto N. Escalante B. and Laurenz Wiskott Institut für Neuroinformatik, Ruhr-University of Bochum, Germany,
More informationInstrument Recognition in Polyphonic Mixtures Using Spectral Envelopes
Instrument Recognition in Polyphonic Mixtures Using Spectral Envelopes hello Jay Biernat Third author University of Rochester University of Rochester Affiliation3 words jbiernat@ur.rochester.edu author3@ismir.edu
More informationExample: compressing black and white images 2 Say we are trying to compress an image of black and white pixels: CSC310 Information Theory.
CSC310 Information Theory Lecture 1: Basics of Information Theory September 11, 2006 Sam Roweis Example: compressing black and white images 2 Say we are trying to compress an image of black and white pixels:
More informationComputer Vision for HCI. Image Pyramids. Image Pyramids. Multi-resolution image representations Useful for image coding/compression
Computer Vision for HCI Image Pyramids Image Pyramids Multi-resolution image representations Useful for image coding/compression 2 1 Image Pyramids Operations: General Theory Two fundamental operations
More informationTechNote: MuraTool CA: 1 2/9/00. Figure 1: High contrast fringe ring mura on a microdisplay
Mura: The Japanese word for blemish has been widely adopted by the display industry to describe almost all irregular luminosity variation defects in liquid crystal displays. Mura defects are caused by
More informationChapter 5. Describing Distributions Numerically. Finding the Center: The Median. Spread: Home on the Range. Finding the Center: The Median (cont.
Chapter 5 Describing Distributions Numerically Copyright 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Copyright 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Slide
More informationVideo coding standards
Video coding standards Video signals represent sequences of images or frames which can be transmitted with a rate from 5 to 60 frames per second (fps), that provides the illusion of motion in the displayed
More informationSELSE ASAR: Applica+on-Specific Approximate Recovery to Mi+gate Hardware Variability. Presenter: Manish Gupta
SELSE 2017 ASAR: Applica+on-Specific Approximate Recovery to Mi+gate Hardware Variability Presenter: Manish Gupta Collaborators: Abbas Rahimi, Daniel Lowell, John Kalama9anos, Advisors: Dean Tullsen, Rajesh
More informationUser Interface Design: Simplicity & Elegance
User Interface Design: Simplicity & Elegance Goals: Understand elegance and simplicity in design Outline principles to achieve "understatement Show examples of bad design (inelegant, busy, etc.) Elegance
More informationRe-Cinematography: Improving the Camera Dynamics of Casual Video
Re-Cinematography: Improving the Camera Dynamics of Casual Video Michael Gleicher Feng Liu Department of Computer Sciences University of Wisconsin- Madison Motivation: More video doesn t mean better video
More informationPackage spotsegmentation
Version 1.53.0 Package spotsegmentation February 1, 2018 Author Qunhua Li, Chris Fraley, Adrian Raftery Department of Statistics, University of Washington Title Microarray Spot Segmentation and Gridding
More informationLinear mixed models and when implied assumptions not appropriate
Mixed Models Lecture Notes By Dr. Hanford page 94 Generalized Linear Mixed Models (GLMM) GLMMs are based on GLM, extended to include random effects, random coefficients and covariance patterns. GLMMs are
More informationNote: Please use the actual date you accessed this material in your citation.
MIT OpenCourseWare http://ocw.mit.edu 18.06 Linear Algebra, Spring 2005 Please use the following citation format: Gilbert Strang, 18.06 Linear Algebra, Spring 2005. (Massachusetts Institute of Technology:
More informationStuart Hall: Encoding Decoding
Stuart Hall: Encoding Decoding Though we know the television programme is not a behavioural input, like a tap on the knee cap, it seems almost impossible for tradi@onal researchers to conceptualize the
More informationPredicting the immediate future with Recurrent Neural Networks: Pre-training and Applications
Predicting the immediate future with Recurrent Neural Networks: Pre-training and Applications Introduction Brandon Richardson December 16, 2011 Research preformed from the last 5 years has shown that the
More informationDiscriminative and Generative Models for Image-Language Understanding. Svetlana Lazebnik
Discriminative and Generative Models for Image-Language Understanding Svetlana Lazebnik Image-language understanding Robot, take the pan off the stove! Discriminative image-language tasks Image-sentence
More informationAutomatic Labelling of tabla signals
ISMIR 2003 Oct. 27th 30th 2003 Baltimore (USA) Automatic Labelling of tabla signals Olivier K. GILLET, Gaël RICHARD Introduction Exponential growth of available digital information need for Indexing and
More informationUNIVERSITY OF CALICUT INTRODUCTION TO VISUAL LANGUAGE QUESTION BANK
UNIVERSITY OF CALICUT SCHOOL OF DISTANCE EDUCATION BGDA (UG SDE) I SEMESTER CORE COURSE INTRODUCTION TO VISUAL LANGUAGE QUESTION BANK BMMC-COMPUTER GRAPHICS Page 1 1...is the measure of the degree of sharpness
More informationIEEE TRANSACTIONS ON MULTIMEDIA, VOL. 12, NO. 7, NOVEMBER
IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 12, NO. 7, NOVEMBER 2010 717 Multi-View Video Summarization Yanwei Fu, Yanwen Guo, Yanshu Zhu, Feng Liu, Chuanming Song, and Zhi-Hua Zhou, Senior Member, IEEE Abstract
More informationHarmonic Generation based on Harmonicity Weightings
Harmonic Generation based on Harmonicity Weightings Mauricio Rodriguez CCRMA & CCARH, Stanford University A model for automatic generation of harmonic sequences is presented according to the theoretical
More informationCharacterization and improvement of unpatterned wafer defect review on SEMs
Characterization and improvement of unpatterned wafer defect review on SEMs Alan S. Parkes *, Zane Marek ** JEOL USA, Inc. 11 Dearborn Road, Peabody, MA 01960 ABSTRACT Defect Scatter Analysis (DSA) provides
More informationName That Song! : A Probabilistic Approach to Querying on Music and Text
Name That Song! : A Probabilistic Approach to Querying on Music and Text Eric Brochu Department of Computer Science University of British Columbia Vancouver, BC, Canada ebrochu@csubcca Nando de Freitas
More informationClassification of Timbre Similarity
Classification of Timbre Similarity Corey Kereliuk McGill University March 15, 2007 1 / 16 1 Definition of Timbre What Timbre is Not What Timbre is A 2-dimensional Timbre Space 2 3 Considerations Common
More informationAUDIOVISUAL COMMUNICATION
AUDIOVISUAL COMMUNICATION Laboratory Session: Recommendation ITU-T H.261 Fernando Pereira The objective of this lab session about Recommendation ITU-T H.261 is to get the students familiar with many aspects
More informationChapter 10 Basic Video Compression Techniques
Chapter 10 Basic Video Compression Techniques 10.1 Introduction to Video compression 10.2 Video Compression with Motion Compensation 10.3 Video compression standard H.261 10.4 Video compression standard
More informationObstacle Warning for Texting
Distributed Computing Obstacle Warning for Texting Bachelor Thesis Christian Hagedorn hagedoch@student.ethz.ch Distributed Computing Group Computer Engineering and Networks Laboratory ETH Zürich Supervisors:
More informationPut your sound where it belongs: Numerical optimization of sound systems. Stefan Feistel, Bruce C. Olson, Ana M. Jaramillo AFMG Technologies GmbH
Put your sound where it belongs: Stefan Feistel, Bruce C. Olson, Ana M. Jaramillo Technologies GmbH 166th ASA, San Francisco, 2013 Sound System Design Typical Goals: Complete Coverage High Level and Signal/Noise-Ratio
More information