FEATURE PERFORMANCE COMPARISON FEATURE PERFORMANCE COMPARISON y SC is a training set of k-dimensional observations with labels S and C b C is a parameter.

Slides:



Advertisements
Similar presentations
Lectureship Early Career Fellowship School of Technology, Oxford Brookes University 19/6/2008 Fabio Cuzzolin INRIA Rhone-Alpes.
Advertisements

Machine learning and imprecise probabilities for computer vision
Learning Riemannian metrics for motion classification Fabio Cuzzolin INRIA Rhone-Alpes Computational Imaging Group, Pompeu Fabra University, Barcellona.
Coherent Laplacian 3D protrusion segmentation Oxford Brookes Vision Group Queen Mary, University of London, 11/12/2009 Fabio Cuzzolin.
Gestures Recognition. Image acquisition Image acquisition at BBC R&D studios in London using eight different viewpoints. Sequence frame-by-frame segmentation.
1 Gesture recognition Using HMMs and size functions.
We consider situations in which the object is unknown the only way of doing pose estimation is then building a map between image measurements (features)
Bilinear models for action and identity recognition Oxford Brookes Vision Group 26/01/2009 Fabio Cuzzolin.
Machine Learning for Vision-Based Motion Analysis Learning pullback metrics for linear models Oxford Brookes Vision Group Oxford Brookes University 17/10/2008.
Evidential modeling for pose estimation Fabio Cuzzolin, Ruggero Frezza Computer Science Department UCLA.
Lectureship A proposal for advancing computer graphics, imaging and multimedia design at RGU Robert Gordon University Aberdeen, 20/6/2008 Fabio Cuzzolin.
Bilinear models and Riemannian metrics for motion classification Fabio Cuzzolin Microsoft Research, Cambridge, UK 11/7/2006.
Pattern Finding and Pattern Discovery in Time Series
Face Recognition: A Convolutional Neural Network Approach
Angelo Dalli Department of Intelligent Computing Systems
On the Dimensionality of Face Space Marsha Meytlis and Lawrence Sirovich IEEE Transactions on PAMI, JULY 2007.
AUTOMATIC SPEECH CLASSIFICATION TO FIVE EMOTIONAL STATES BASED ON GENDER INFORMATION ABSTRACT We report on the statistics of global prosodic features of.
2004/11/161 A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition LAWRENCE R. RABINER, FELLOW, IEEE Presented by: Chi-Chun.
 CpG is a pair of nucleotides C and G, appearing successively, in this order, along one DNA strand.  CpG islands are particular short subsequences in.
Statistical NLP: Lecture 11
Profiles for Sequences
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
Chapter 2: Pattern Recognition
Recognition of Human Gait From Video Rong Zhang, C. Vogler, and D. Metaxas Computational Biomedicine Imaging and Modeling Center Rutgers University.
KNN, LVQ, SOM. Instance Based Learning K-Nearest Neighbor Algorithm (LVQ) Learning Vector Quantization (SOM) Self Organizing Maps.
Computer Vision I Instructor: Prof. Ko Nishino. Today How do we recognize objects in images?
Human Identification using Silhouette Gait Data Rutgers University Chan-Su Lee.
Learning to Identify Overlapping and Hidden Cognitive Processes from fMRI Data Rebecca Hutchinson, Tom Mitchell, Indra Rustandi Carnegie Mellon University.
Handwritten Character Recognition using Hidden Markov Models Quantifying the marginal benefit of exploiting correlations between adjacent characters and.
Radial-Basis Function Networks
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION.
3D Motion Capture Assisted Video human motion recognition based on the Layered HMM Myunghoon Suk & Ashok Ramadass Advisor : Dr. B. Prabhakaran Multimedia.
Segmental Hidden Markov Models with Random Effects for Waveform Modeling Author: Seyoung Kim & Padhraic Smyth Presentor: Lu Ren.
International Conference on Intelligent and Advanced Systems 2007 Chee-Ming Ting Sh-Hussain Salleh Tian-Swee Tan A. K. Ariff. Jain-De,Lee.
ENT 273 Object Recognition and Feature Detection Hema C.R.
Representations for object class recognition David Lowe Department of Computer Science University of British Columbia Vancouver, Canada Sept. 21, 2006.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: ML and Simple Regression Bias of the ML Estimate Variance of the ML Estimate.
A survey of different shape analysis techniques 1 A Survey of Different Shape Analysis Techniques -- Huang Nan.
MUSTAFA OZAN ÖZEN PINAR SAĞLAM LEVENT ÜNVER MEHMET YILMAZ.
Lecture 27: Recognition Basics CS4670/5670: Computer Vision Kavita Bala Slides from Andrej Karpathy and Fei-Fei Li
CSE 185 Introduction to Computer Vision Face Recognition.
Optimal Component Analysis Optimal Linear Representations of Images for Object Recognition X. Liu, A. Srivastava, and Kyle Gallivan, “Optimal linear representations.
1 CONTEXT DEPENDENT CLASSIFICATION  Remember: Bayes rule  Here: The class to which a feature vector belongs depends on:  Its own value  The values.
Project by: Cirill Aizenberg, Dima Altshuler Supervisor: Erez Berkovich.
Separating Style and Content with Bilinear Models Joshua B. Tenenbaum, William T. Freeman Computer Examples Barun Singh 25 Feb, 2002.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
Speech Communication Lab, State University of New York at Binghamton Dimensionality Reduction Methods for HMM Phonetic Recognition Hongbing Hu, Stephen.
Ch 5b: Discriminative Training (temporal model) Ilkka Aho.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Chapter 13 (Prototype Methods and Nearest-Neighbors )
Discriminative Training and Machine Learning Approaches Machine Learning Lab, Dept. of CSIE, NCKU Chih-Pin Liao.
CS Statistical Machine learning Lecture 25 Yuan (Alan) Qi Purdue CS Nov
9.913 Pattern Recognition for Vision Class9 - Object Detection and Recognition Bernd Heisele.
Classification of melody by composer using hidden Markov models Greg Eustace MUMT 614: Music Information Acquisition, Preservation, and Retrieval.
Next, this study employed SVM to classify the emotion label for each EEG segment. The basic idea is to project input data onto a higher dimensional feature.
Part 3: Estimation of Parameters. Estimation of Parameters Most of the time, we have random samples but not the densities given. If the parametric form.
1 Bilinear Classifiers for Visual Recognition Computational Vision Lab. University of California Irvine To be presented in NIPS 2009 Hamed Pirsiavash Deva.
Learning pullback action manifolds Heriot Watt University, 26/5/2010 Fabio Cuzzolin Oxford Brookes Vision Group.
Video-based human motion recognition using 3D mocap data
Outline Multilinear Analysis
Decoding Neuronal Ensembles in the Human Hippocampus
CONTEXT DEPENDENT CLASSIFICATION
Separating Style and Content with Bilinear Models Joshua B
Separating Style and Content with Bilinear Models Joshua B
Face Recognition: A Convolutional Neural Network Approach
Introduction.
Pattern Recognition and Training
The “Margaret Thatcher Illusion”, by Peter Thompson
Presentation transcript:

FEATURE PERFORMANCE COMPARISON FEATURE PERFORMANCE COMPARISON y SC is a training set of k-dimensional observations with labels S and C b C is a parameter vector representing content, while A S is a style-specific linear map mapping the content space onto the observation space EXPERIMENTS WITH THE MOBO DATABASE EXPERIMENTS WITH THE MOBO DATABASE ASYMMETRIC BILINEAR MODELS ASYMMETRIC BILINEAR MODELS USING BILINEAR MODELS FOR VIEW-INVARIANT ACTION AND IDENTITY RECOGNITION Fabio Cuzzolin, UCLA Vision Lab, University of California at Los Angeles USING BILINEAR MODELS FOR VIEW-INVARIANT ACTION AND IDENTITY RECOGNITION Fabio Cuzzolin, UCLA Vision Lab, University of California at Los Angeles INTERNATIONAL CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2006 New York University, NY, June the training set of sequences is used to learn a three-layer model the model can be used thereafter to estimate the content of new image sequences with known content but unknown style we want to recognize the identity of a walking person, no we want to recognize the identity of a walking person, no matter the viewpoint or the walking gait performed matter the viewpoint or the walking gait performed bilinear models can be used to describe datasets in bilinear models can be used to describe datasets in which each sequence possesses more than a single label which each sequence possesses more than a single label a three-layer model in which HMMs represent sequences a three-layer model in which HMMs represent sequences and are fed to a bilinear model is proposed to provide an and are fed to a bilinear model is proposed to provide an effective view- and action-invariant approach to gaitID effective view- and action-invariant approach to gaitID VIEW-INVARIANCE IN IDENTITY VIEW-INVARIANCE IN IDENTITY RECOGNITION FROM GAIT RECOGNITION FROM GAIT the problem: recognizing the identity of a person from the way he/she walks in a realistic setup, the person to identify would walk into the surveyed area from an arbitrary direction -> view-invariance view-invariance is a particular case of the style-invariance issue 3 view-invariant gaitID. Left: score as a function of the nuisance (action), test view 1. Right: score for the dataset of sequences of action ``slow", different test views. performance of the bilinear classifier in the ID vs action experiment as a function of the nuisance (view=1:5), averaged over all the possible choices of the test action. The average best-match performance of the bilinear classifier is shown in solid red, (minimum and maximum in magenta). The best-3 matches ratio is in dotted red. The average performance of the KL-nearest neighbor classifier is shown in solid black, minimum and maximum in blue. Pure chance is in dashed black. FEATURE EXTRACTION FROM SILHOUETTES FEATURE EXTRACTION FROM SILHOUETTES VIEW- AND ACTION-INVARIANT GAIT ID VIEW- AND ACTION-INVARIANT GAIT ID in the first layer features are extracted from the available silhouettes, by simply projecting their contour onto a family of lines passing through their center; in the second layer each feature sequence is fed to an HMM with a fixed number of states, yielding a dataset of Markov models; as the dynamics is the same for all sequences, they can be represented by the stacked C matrix of the HMM HIDDEN MARKOV MODELS HIDDEN MARKOV MODELS Left: ID-invariant action recognition using the bilinear classifier. The entire dataset is considered, regardless the viewpoint. The correct classification percentage is shown as a function of the test identity in black (for models using Lee's features) and red (contour projections). Related mean levels are drawn as dotted lines. Right: View- invariant action recognition. THREE-LAYER MODEL THREE-LAYER MODEL we chose the CMU Mobo database, in which 25 different people perform four different walking- related actions: walking slow, walking fast, walking along a slope, walking while carrying a ball. Cameras are more or less equally spaced around the treadmill. sequences in the Mobo database have three different labels: identity, action, and viewpoint; four series of tests in which we built bilinear models for different content and style labels: view-invariant gaitID, action-invariant gaitID, view-invariant action recognition, style-invariant action classification. comparison with two other approaches: baseline algorithm, and direct application of a nearest-neighbor NN classifier on the dataset of HMMs, using Kullback-Leibler. 2 consider a training set of sequences in which each sequence is associated with more than a single label; each motion can in fact be classified according to the person who performed it, the category of action performed (i.e. walking, reaching out, pointing, etc.), or (if the number of cameras is finite) the viewpoint from which the sequence is shot; multilinear and bilinear models can be seen as tools for separating ``style" and ``content" of the objects to classify. 1 an asymmetric bilinear model can learned from an observation sequence through the SVD of a stacked observation matrix y SC when new motions are acquired in which a known person is being seen walking from a different viewpoint (unknown style) an iterative EM procedure can be set up to classify the content (identity): E step: estimation of p(c|s), the prob. of the content given the current estimate of s; M step: estimation of the linear map for s. FROM VIEW-INVARIANCE TO STYLE-INVARIANCE FROM VIEW-INVARIANCE TO STYLE-INVARIANCE