MotionVis Donovan Parks. Outline  Project motivation and goal  Details of projects  Video showing results  Future work and conclusions.

Slides:

Advertisements

Similar presentations

RANDOM PROJECTIONS IN DIMENSIONALITY REDUCTION APPLICATIONS TO IMAGE AND TEXT DATA Ella Bingham and Heikki Mannila Ângelo Cardoso IST/UTL November 2009.

Advertisements

Multimedia Database Systems

Effective Keyword Based Selection of Relational Databases Bei Yu, Guoliang Li, Karen Sollins, Anthony K.H Tung.

Proposed concepts illustrated well on sets of face images extracted from video: Face texture and surface are smooth, constraining them to a manifold Recognition.

Generation of Virtual Image from Multiple View Point Image Database Haruki Kawanaka, Nobuaki Sado and Yuji Iwahori Nagoya Institute of Technology, Japan.

Automating Graph-Based Motion Synthesis Lucas Kovar Michael Gleicher University of Wisconsin-Madison.

ARNOLD SMEULDERS MARCEL WORRING SIMONE SANTINI AMARNATH GUPTA RAMESH JAIN PRESENTERS FATIH CAKIR MELIHCAN TURK Content-Based Image Retrieval at the End.

Implicit Probabilistic Models of Human Motion for Synthesis and Tracking Hedvig Sidenbladh, KTH, Sweden (now FOI, Sweden) Michael J. Black, Brown University,

A Novel Scheme for Video Similarity Detection Chu-Hong Hoi, Steven March 5, 2003.

Summary & Homework Jinxiang Chai. Outline Motion data process paper summary Presentation tips Homework Paper assignment.

Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.

DIMENSIONALITY REDUCTION BY RANDOM PROJECTION AND LATENT SEMANTIC INDEXING Jessica Lin and Dimitrios Gunopulos Ângelo Cardoso IST/UTL December

International Conference on Image Analysis and Recognition (ICIAR’09). Halifax, Canada, 6-8 July Video Compression and Retrieval of Moving Object.

Automated Extraction and Parameterization of Motions in Large Data Sets SIGGRAPH’ 2004 Lucas Kovar, Michael Gleicher University of Wisconsin-Madison.

Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,

“Exploring High-D Spaces with Multiform Matrices and Small Multiples” Mudit Agrawal Nathaniel Ayewah MacEachren, A., Dai, X., Hardisty, F., Guo, D., and.

Marrying Spatialization and Traditional Cartography Geography 200B March 12, 2003 Presented by Kirk Goldsberry.

Image-Based Rendering using Hardware Accelerated Dynamic Textures Keith Yerex Dana Cobzas Martin Jagersand.

1 An Empirical Study on Large-Scale Content-Based Image Retrieval Group Meeting Presented by Wyman

10-603/15-826A: Multimedia Databases and Data Mining SVD - part I (definitions) C. Faloutsos.

MotionVis Donovan Parks. Introduction  Large motion capture DB’s widely used in the film and video game industries  This has created a desire to be.

A Global Geometric Framework for Nonlinear Dimensionality Reduction Joshua B. Tenenbaum, Vin de Silva, John C. Langford Presented by Napat Triroj.

Dimensionality Reduction

Methodology Conceptual Database Design

Geometry Videos Symposium on Computer Animation 2003 Hector M. Briceño Collaborators: Pedro V. Sander, Leonard McMillan, Steven Gortler, and Hugues Hoppe.

Jan SedmidubskySeptember 23, 2014Motion Retrieval for Security Applications Jan Sedmidubsky Jakub Valcik Pavel Zezula Motion Retrieval for Security Applications.

Large-Scale Content-Based Image Retrieval Project Presentation CMPT 880: Large Scale Multimedia Systems and Cloud Computing Under supervision of Dr. Mohamed.

Bag of Video-Words Video Representation

AdvisorStudent Dr. Jia Li Shaojun Liu Dept. of Computer Science and Engineering, Oakland University 3D Shape Classification Using Conformal Mapping In.

The Tutorial of Principal Component Analysis, Hierarchical Clustering, and Multidimensional Scaling Wenshan Wang.

Multimedia Databases (MMDB)

Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology On multidimensional scaling and the embedding of self-organizing.

Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology Adaptive nonlinear manifolds and their applications to pattern.

FODAVA-Lead Education, Community Building, and Research: Dimension Reduction and Data Reduction: Foundations for Interactive Visualization Haesun Park.

Automated Construction of Parameterized Motions Lucas Kovar Michael Gleicher University of Wisconsin-Madison.

PMLAB Finding Similar Image Quickly Using Object Shapes Heng Tao Shen Dept. of Computer Science National University of Singapore Presented by Chin-Yi Tsai.

IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.

Efficient Instant-Fuzzy Search with Proximity Ranking Authors: Inci Centidil, Jamshid Esmaelnezhad, Taewoo Kim, and Chen Li IDCE Conference 2014 Presented.

Mingyang Zhu, Huaijiang Sun, Zhigang Deng Quaternion Space Sparse Decomposition for Motion Compression and Retrieval SCA 2012.

ISOMAP TRACKING WITH PARTICLE FILTER Presented by Nikhil Rane.

Event retrieval in large video collections with circulant temporal encoding CVPR 2013 Oral.

Query Sensitive Embeddings Vassilis Athitsos, Marios Hadjieleftheriou, George Kollios, Stan Sclaroff.

Manifold learning: MDS and Isomap

CSC2535: Computation in Neural Networks Lecture 12: Non-linear dimensionality reduction Geoffrey Hinton.

Non-Linear Dimensionality Reduction

1 Applications of video-content analysis and retrieval IEEE Multimedia Magazine 2002 JUL-SEP Reporter: 林浩棟.

Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality Piotr Indyk, Rajeev Motwani The 30 th annual ACM symposium on theory of computing.

Chapter 8. Learning of Gestures by Imitation in a Humanoid Robot in Imitation and Social Learning in Robots, Calinon and Billard. Course: Robots Learning.

Unsupervised Learning

A Patent Document Retrieval System Addressing Both Semantic and Syntactic Properties Liang Chen*,Naoyuki Tokuda+, Hisahiro Adachi+ *University of Northern.

Math 285 Project Diffusion Maps Xiaoyan Chong Department of Mathematics and Statistics San Jose State University.

Query by Image and Video Content: The QBIC System M. Flickner et al. IEEE Computer Special Issue on Content-Based Retrieval Vol. 28, No. 9, September 1995.

3D Motion Data Mining Multimedia Project Multimedia and Network Lab, Department of Computer Science.

ViSOM － A Novel Method for Multivariate Data Projection and Structure Visualization Advisor : Dr. Hsu Graduate : Sheng-Hsuan Wang Author : Hujun Yin.

Planning Tracking Motions for an Intelligent Virtual Camera Tsai-Yen Li & Tzong-Hann Yu Presented by Chris Varma May 22, 2002.

Intelligent Database Systems Lab Presenter: YU-TING LU Authors: Junping Zhang, Hua Huang and Jue Wang IEEE INTELLIGENT SYSTEMS Manifold Learning.

Constrained Synthesis of Textural Motion for Animation Shmuel Moradoff Dani Lischinski The Hebrew University of Jerusalem.

Similarity Measurement and Detection of Video Sequences Chu-Hong HOI Supervisor: Prof. Michael R. LYU Marker: Prof. Yiu Sang MOON 25 April, 2003 Dept.

Out of sample extension of PCA, Kernel PCA, and MDS WILSON A. FLORERO-SALINAS DAN LI MATH 285, FALL

MOTION PATTERN PRESERVING IK OPERATING IN THE MOTION PRINCIPAL COEFFICIENTS SPACE Motion Pattern Preserving IK Operating in the Motion Principal Coefficients.

Naifan Zhuang, Jun Ye, Kien A. Hua

Experience Report: System Log Analysis for Anomaly Detection

Fig. 2 Two-dimensional embedding result obtained using nMDS.

Progress Report Meeting

Segmentation of Dynamic Scenes

Video-based human motion recognition using 3D mocap data

Applying Key Phrase Extraction to aid Invalidity Search

Video Analysis via Nonlinear Dimensionality Reduction Technique

Li Li, Zhu Li, Vladyslav Zakharchenko, Jianle Chen, Houqiang Li

Presentation transcript:

MotionVis Donovan Parks

Outline  Project motivation and goal  Details of projects  Video showing results  Future work and conclusions

Motivation  Large motion capture DB’s widely used in the film and video game industries  This has created a desire to be able to search these databases for logically similar motions

Project Goal  Numerous similarity metrics have been proposed: Which of these should be preferred? What are their respective strengths and weaknesses? How can a given metric be improved?  Develop an environment for analyzing the structure of a motion capture DB under a given similarity metric

Project Overview  InfoVis environment for visualizing MoCap DB under a given similarity metric

CMU MoCap Database  Publicly available database of MoCap data (mocap.cs.cmu.edu)  Project considers a subset of the CMU database 110 walking sequences 45 running sequences 18 jumping sequences 5 boxing sequences 3 cartwheel sequences

Li’s Similarity Metric  Treat each frame as a point in high-d space  Hypothesis: Similar motions will have a similar principal axis as determined by PCA  Angle between principal axes is used as the similarity measure Li and Prabhakaran (2006)

Dimensionality Reduction  Three dimensionality techniques considered: PCA / Classic MDS (linear, fast) Metric MDS (nonlinear, slow) Non-metric MDS (rank order, slow)  With 2 dimensions: Classic MDS has a stress of ~0.08 Metric MDS has a stress of ~0.05 Non-metric MDS has a stress of ~0.03

Visual encodings

Future Work  Fix various short-comings of current implementation  Consider other MoCap similarity metrics  Dealing with data that has an intrinsic dimensionality > 2

Conclusions  Environment for aiding understanding of a MoCap-based similarity metrics  Provides information about a similarity metric that is hard to obtain from: analyzing numerical results existing visualization environments

Literature  Implemented similarity metric: Chuanjun Li and B. Prabhakaran. Indexing of motion capture data for efficient and fast similarity search,  Other similarity metrics: Lucas Kovar and Michael Gleicher. Automated extraction and parameterization of motions in large data sets. ACM Trans. Graph., 23(3):559568, Meinard Müller, Tido Röder, and Michael Clausen. Efficient content-based retrieval of motion capture data. ACM Trans. Graph., 24(3):677685,  Related InfoVis papers: Chris Roussin Rich DeJordy, Stephen P. Borgatti and Daniel S. Halgin. Visualizing proximity data, Jonathan C. Roberts. State of the art: coordinated and multiple views in exploratory visualization. Proc. Conference on Coordinated and Multiple Views in Exploratory Visualization, 2007.