DOCSLIB.ORG

Non-Linear Dynamical System Approach to Behavior Modeling

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Non-Linear Dynamical System Approach to Behavior Modeling 1 Introduction The importance of game and simulation applications grows everyday, as does the need for animated agents Non-linear dynamical that operate autonomously in these environments. These agents must be able to exhibit certain low- and system approach to high-level behaviors and interact with the environ- behavior modeling ment. Various approaches for modeling behavior and movement decisions have been investigated, among them the pioneering work of Reynolds (Reynolds 1987) and that of others (Haumann and Parent 1988; Wilhelms 1990; Renault et al. 1990; Bates et al. Siome Goldenstein, 1992; Noser and Thalmann 1993; Reynolds 1993; Edward Large, Ko et al. 1994; Tu and Terzopoulos 1994; Noser et al. Dimitris Metaxas 1995). These include, kinematic, dynamic, learning, and artificial intelligence-based approaches. AI techniques for behavior generation, such as (Hau- VAST Lab., Center for Human Modeling and mann and Parent 1988; Lethebridge and Ware 1989), Simulation, Computer and Information Science Department, University of Pennsylvania, 200 South generally require complex inferencing mechanisms. 33rd Street, Philadelphia, PA, USA 19104-6389 This may require considerable computational re- e-mail: {siome,large,dnm}@graphics.cis.upenn.edu sources, raising the question of scalability of such systems, as the number of independent agents and behaviors grows, and each agent has a different set of goals and behavioral directives. In addition, agents We present a dynamic systems approach to must be able to interact with real-time moving ob- modeling and generating low-level behav- jects that might either contribute to or compromise iors for autonomous agents. Such behaviors the final goal. Other approaches to this problem em- include real-time target tracking and obsta- ploy learning, perception, and dynamic techniques cle avoidance in time-varying environments. (Ridsdale 1990; Tu and Terzopouluos 1994; Noser The novelty of the method lies on the inte- et al. 1995; Grzeszczuk and Terzopouluos 1995), gration of distinct non-linear dynamic sys- while computational geometry techniques have been tems to model the agent’s interaction with employed in rather restricted environments (Wilfong the environment. An angular velocity con- 1988). trol dynamic system guides the agent’s di- Dynamic system approaches to this problem have rection angle, while another dynamic system mostly been explored at the level of control the- selects the environmental input that will be ory (Cohen 1992; Liu et al. 1994; Kokkevis et al. used in the control system. The agent inter- 1995). This methodology restricts the type of be- acts with the environment through its knowl- haviors that can be simulated since it does not cope edge of the position of stationary and mov- well with dynamically changing environments and ing objects. In our system agents automati- its computational complexity prohibits its use in cally avoid stationary and moving obstacles real-time simulations. Others discuss the useful- to reach the desired target(s). This approach ness of different layers of control and behaviors to allows us to prove the stability conditions achieve better results (Kurlander and Ling 1995; that result in a principled methodology for Magnenat-Thalmann and Thalman 1995; Blumberg the computation of the system’s dynamic pa- and Galyean 1995; Perlin and Goldberg 1996) rameters. We present a variety of real-time In this paper, we investigate and develop an alterna- simulations that illustrate the power of our tive methodology that has its roots in behavior-based approach. robotics (e.g., (Braitenberg 1989; Brooks 1991)) and is based on a novel way of combining differential Key words: Digital agents – Game anima- equations exhibiting particular behaviors (Steinhage tions – Low-level behaviors – Motion plan- and Schöner 1997; Large et al. 1999). Using this ning – Dynamical systems type of approach, Schöner and colleagues (Schöner and Dose 1992; Schöner et al. 1996) have devel- The Visual Computer (1999) 15:349–364 c Springer-Verlag 1999 350 S. Goldenstein: Non-linear dynamical system approach to behavior modeling oped a dynamical system for robot path planning and porarily disregard a target if there is an unsurpassable control. In this system a set of behavioral variables, moving or stationary obstacle immediately between namely heading direction and velocity, define a state it and the target. Like a human, it will first focus on space in which the dynamics of robot behavior is avoiding the obstacle, and then refocus on the target. described. Path planning is governed by a nonlinear In this paper we also prove an important result on dynamical system that generates a time course of the properties of the parameters of the task constraint the behavioral variables. The system dynamics are system which determine the number of behaviors specified as a nonlinear vector field, while the task modeled. These properties are associated with the that the agent will execute depends upon the task stability2 of the task constraint system. We also pro- constraints. Task constraints, such as obstacle avoid- vide an inductive proof that extends the above result ance and target tracking, are modeled as component to any number of dimensions in the task constraint forces which define attractors and repellers for the system. This result allows the principled design of dynamical system. The individual constraint contri- complex systems with large number of behaviors. butions are weighted and then added together into Our system allows single and multiple target track- a single vector field, which determines the observed ing in the presence of multiple static and moving behavior. Next, a second dynamical system is used obstacles, and scales well with the number of behav- to compute these weights. This dynamical system, iors. Obstacles are processed in a local fashion based the task level system, operates at a faster time scale on their relative location to the agent and the tar- than the movement level (Large et al. 1999). Qualita- get. In our current implementation and without loss tively different behaviors are modeled as fixed points of generality the agents are memoryless and reactive of this dynamical system, and the environment deter- in nature. Depending on the situation (emergence of mines the values of the parameters. As the perceptual new obstacles and/or targets) their movement can be information changes, parameters change, causing bi- discontinuous. furcations in the task-level system. During the course This paper is organized as follows. In Sects. 2 and of the simulation, one fixed point loses stability and 3 we present the dynamic formulation of the sys- another becomes stable, modeling the decision to tem. Section 4 describes the task constraint system cease executing one behavior and to execute another responsible for the generation of the behaviors. We instead. devise an inductive proof for the restrictions on this Here, we adapt the above methodology to model and system’s parameters (stability analysis) that will re- simulate autonomous low-level dynamic behaviors sult in the desired behaviors. Finally, we present which can be used in applications ranging from vir- a series of real-time simulations involving complex tual environments to games. We use (see also our interactions between the agents, the environment and preliminary results, in (Goldenstein et al. 1998)) a set the targets. of time-varying differential equations that control the heading angle and forward speed of a given dig- ital autonomous agent. Based on a principled com- 2 Movement dynamics and low-level bination of these equations we create a whole set of relatively complex low-level behaviors such as ob- behavior stacle avoidance and target tracking. To avoid unsta- ble fixed points in the differential equations1 we add Our methodology consists of the combination of two a Gaussian noise term in each equation. Using this distinct dynamic systems to model the movement system, decisions are made online and do not require and behavior of each autonomous agent. The first any previous memory, training, or global planning. system controls the movement of the agent. The state The set of targets and obstacles can change during space of this system is two-dimensional, the first pa- the course of the simulation, since the agent is able rameter represents the heading direction, while the to make smart local decisions based on its current other specifies its velocity (In a three-dimensional global knowledge of the dynamic environment in space there would be two heading angles and one which it is situated. For example, an agent will tem- forward velocity). The second system controls the 1 In differential equation terminology a fixed point is a point 2 The stability is related to the local convergence properties of where the derivative of the vector field is zero the system around a fixed point S. Goldenstein: Non-linear dynamical system approach to behavior modeling 351 agent’s movement decision-making, i.e., its behav- from the sum of contributions from all obstacles. We ior. The state space of this system is the space of the then extend the formulations to account for multiple agent’s behaviors. The parameter values of the state groups. vector components determine which elements of the Using (1) an attractor is defined as environment (e.g., obstacles, targets) will be used in φ˙ = =− (φ − ψ) , the calculation of the agent’s movement and there- ftar a sin (2) fore behavior. ψ Each autonomous agent’s movement is described in where is the angle of the target’s location relative a polar coordinates. It consists of a heading direction φ to the agent’s location and is a constant parame- v ter. Figure 1 shows a plot of (2), assuming that the and a forward velocity . The heading angle is con- ψ = trolled by a one-dimensional non-linear dynamical target is in front of the agent ( 0). The negative slope around the fixed point (in this case, the origin) system, which consists of repellers placed in the sub- φ˙ tended angle of the obstacles, and attractors in the is what gives the attractor property, forcing to be subtended angles of targets (see Sect.
Load more

Recommended publications
  • Outlier Rejection in High-Dimensional Deformable Models
    Image and Vision Computing 25 (2007) 274–284 www.elsevier.com/locate/imavis Outlier rejection in high-dimensional deformable models Christian Vogler a,*, Siome Goldenstein b, Jorge Stolfi b, Vladimir Pavlovic c, Dimitris Metaxas c a Gallaudet Research Institute, Gallaudet University, 800 Florida Avenue NE, HMB S-433 Washington, DC 20002-3695, USA b Instituto de Computac¸a˜o, Universidade Estadual de Campinas, Caixa Postal 6176, Campinas, SP 13084-971, Brazil c Department of Computer Science, Rutgers University, 110 Frelinghuysen Road, Piscataway, NJ 08854-8019, USA Received 16 October 2004; received in revised form 11 August 2005; accepted 11 October 2005 Abstract Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The core of the approach consists of using low-level vision algorithms, such as edge trackers or optical flow, to collect a large number of 2D displacements, or motion measurements, at selected model points and mapping them into 3D space with the model Jacobians. However, the low-level algorithms are prone to errors and outliers, which can skew the entire tracking procedure if left unchecked. There are several known techniques in the literature, such as RANSAC, that can find and reject outliers. Unfortunately, these approaches are not easily mapped into the deformable model tracking framework, where there is no closed-form algebraic mapping from samples to the underlying parameter space. In this paper, we present three simple, yet effective ways to find the outliers. We validate and compare these approaches in an 11- parameter deformable face tracking application against ground truth data.
    [Show full text]
  • Texture Resampling While Ray-Tracing: Approximating the Convolution Region Using Caching
    University of Pennsylvania ScholarlyCommons Technical Reports (CIS) Department of Computer & Information Science February 1994 Texture Resampling While Ray-Tracing: Approximating the Convolution Region Using Caching Jeffry S. Nimeroff University of Pennsylvania Norman I. Badler University of Pennsylvania Dimitris Metaxas University of Pennsylvania Follow this and additional works at: https://repository.upenn.edu/cis_reports Recommended Citation Jeffry S. Nimeroff, Norman I. Badler, and Dimitris Metaxas, "Texture Resampling While Ray-Tracing: Approximating the Convolution Region Using Caching", . February 1994. University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-94-03. This paper is posted at ScholarlyCommons. https://repository.upenn.edu/cis_reports/243 For more information, please contact [email protected]. Texture Resampling While Ray-Tracing: Approximating the Convolution Region Using Caching Abstract We present a cache-based approach to handling the difficult oblempr of performing visually acceptable texture resampling/filtering while ar y-tracing. While many good methods have been proposed to handle the error introduced by the ray-tracing algorithm when sampling in screen space, handling this error in texture space has been less adequately addressed. Our solution is to introduce the Convolution Mask Approximation Module (CMAM). The CMAM locally approximates the convolution region in texture space as a set of overlapping texture triangles by using a texture sample caching system and ray tagging. Since the caching mechanism is hidden within the CMAM, the ray-tracing algorithm itself is unchanged while achieving an adequate level of texture filtering (area sampling as opposed to point sampling/interpolation in texture space). The CMAM is easily adapted to incorporate prefiltering methods such as MIP mapping and summed-area tables as well as direct convolution methods such as elliptical weighted average filtering.
    [Show full text]
  • 2015 HRP Annual Report
    National Aeronautics and Space Administration HUMAN RESEARCH PROGRAM SEEKING KNOWLEDGE FY2015 ANNUAL REPORT TABLE OF CONTENTS Human Research Program Overview ................................................................... 01 }}Background }}Goal and Objectives }}Program Organization }}Partnerships and Collaborations Major Program-Wide Accomplishments ...............................................................07 International Space Station Medical Projects Element .......................................... 13 Space Radiation Element ...................................................................................... 25 Human Health Countermeasures Element ........................................................... 31 }}Vision and Cardiovascular Portfolio }}Exercise and Performance Portfolio }}Multisystem Portfolio }}Bone and Occupant Protection Portfolio }}Technology and Infrastructure Portfolio Exploration Medical Capability Element .............................................................. 45 Space Human Factors and Habitability Element .................................................. 53 }}Advanced Environmental Health Portfolio }}Advanced Food Technology Portfolio }}Space Human Factors Engineering Portfolio Behavioral Health and Performance Element ....................................................... 63 }}Sleep/Fatigue Portfolio }}Behavioral Medicine Portfolio }}Team Risk Portfolio Engagement and Communications ....................................................................... 71 Publications ..........................................................................................................77
    [Show full text]
  • Towards Efficient U-Nets: a Coupled and Quantized Approach
    This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TPAMI.2019.2907634, IEEE Transactions on Pattern Analysis and Machine Intelligence TOWARDS EFFICIENT U-NET: A COUPLED AND QUANTIZED APPROACH 1 Towards Efficient U-Nets: A Coupled and Quantized Approach Zhiqiang Tang, Xi Peng, Kang Li and Dimitris N. Metaxas, Fellow, IEEE Abstract—In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Specially, we propose an order-K coupling design to trim off long-distance shortcuts, together with an iterative refinement and memory sharing mechanism. To further improve the efficiency, we quantize the parameters, intermediate features, and gradients of the coupled U-Nets to low bit-width numbers. We validate our approach in two tasks: human pose estimation and facial landmark localization. The results show that our approach achieves state-of-the-art localization accuracy but using ∼70% fewer parameters, ∼30% less inference time, ∼98% less model size, and saving ∼75% training memory compared with benchmark localizers. Index Terms—Stacked U-Nets, Dense Connectivity, Network Quantization, Efficient AI, Human Pose Estimation, Face Alignment. F 1 INTRODUCTION the stacked U-Nets, generating the coupled U-Nets (CU- The U-Net architecture [1] is a basic category of Convolution Net). The key idea is to directly connect blocks of the same Neural Network (CNN).
    [Show full text]
  • Mingchen, Gao CV
    Mingchen Gao 347 Davis Hall Phone: (716)-645-2834 University at Buffalo Email: [email protected] Buffalo NY 14260 https://cse.buffalo.edu/~mgao8/ RESEARCH INTERESTS Big Healthcare Data, Biomedical Imaging Informatics, Machine Learning, Computer Vision EDUCATION 09/2007 { 06/2014 Rutgers University, New Brunswick, NJ Ph.D. in Computer Science Thesis: Cardiac Reconstruction and Analysis from High Resolution CT Images Advisor: Prof. Dimitris Metaxas 09/2003 { 06/2007 Southeast University, Nanjing, China Chien-Shiung Wu College (Gifted Young Class) B.E. in Computer Science and Engineering EMPLOYMENTS 08/2017 { present Assistant Professor, Department of Computer Science and Engineering University at Buffalo, SUNY 09/2014 { 08/2017 Postdoctoral Fellow, Center for Infectious Disease Imaging Department of Radiology and Imaging Sciences, Clinical Center National Institutes of Health (NIH), Bethesda, MD 07/2009 { 06/2014 Research Assistant, Rutgers University, Computer Science Department New Brunswick, NJ 03/2013 { 08/2013 Research Intern, Siemens Medical Solution, Malvern, PA 05/2012 { 08/2012 Software Engineer Intern, Google Inc., Image Search Group, Mountain View, CA 09/2007 { 06/2009 Teaching Assistant, Rutgers University, Computer Science Department, New Brunswick, NJ FUNDING Artificial Intelligence Germination Space Program, University at Buffalo, SUNY 09/01/18-08/31/19 AI Drug Discovery to Characterise and Treat Every Disease $25,000 Role: Co-PI Mingchen Gao 2 STUDENT ADVISING PhD Students Yan Shen 01/2018 - present Chunwei Ma 08/2018 - present
    [Show full text]
  • Curriculum Vitae—Doug Decarlo
    Curriculum Vitae—Doug DeCarlo Department of Computer Science [email protected] 110 Frelinghuysen Road http://www.cs.rutgers.edu/˜decarlo Piscataway, NJ 08854-8019 TEL: 732 445 2001 x1495 EDUCATION • Ph.D., University of Pennsylvania, Department of Computer and Information Science, July 1998. Dissertation: Generation, Estimation and Tracking of Faces Advisor: Dimitris Metaxas • B.S. in Computer Science/Mathematics, Carnegie Mellon University, 1991. • B.S. in Computer Engineering, Carnegie Mellon University, 1991. APPOINTMENTS • Associate Chair, Department of Computer Science Rutgers University, Fall 2006–present. • Associate Professor, Department of Computer Science with a joint appointment in the Rutgers Center for Cognitive Science (RuCCS) Rutgers University, 2005–present • Visiting Fellow, Department of Computer Science Princeton University, Fall 2002 • Assistant Professor, Department of Computer Science with a joint appointment in the Rutgers Center for Cognitive Science (RuCCS) Rutgers University, 1999–2005 • Postdoctoral researcher, Rutgers Center for Cognitive Science (RuCCS) Rutgers University, 1998–1999. REFEREED JOURNAL PUBLICATIONS • Exaggerated Shading for Depicting Shape and Detail. Szymon Rusinkiewicz, Mike Burns, Doug DeCarlo, In ACM Transactions on Graphics (Special Issue for ACM SIGGRAPH 2006), July 2006, 25(3), pages 1199–1205. • Line Drawings from Volume Data. Mike Burns, Janek Klawe, Adam Finkelstein, Szymon Rusinkiewicz, Doug DeCarlo, In ACM Transactions on Graphics (Special Issue for ACM SIGGRAPH 2005), July 2005, 24(3), pages 512–518. • Speaking with Hands: Creating Animated Conversational Characters from Recordings of Human Perfor- mance. Matthew Stone, Doug DeCarlo, Insuk Oh, Christian Rodriguez, Adrian Stere, Alyssa Lees and Chris Bregler, In ACM Transactions on Graphics (Special Issue for ACM SIGGRAPH 2004), July 2004, 23(3), pages 506–513.
    [Show full text]
  • Athens October 17-21 2016 INTERCONTINENTAL ATHENAEUM ATHENS / GREECE
    MICCAITH 2016 19 INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & GREECE COMPUTER ASSISTED INTERVENTION Athens October 17-21 2016 INTERCONTINENTAL ATHENAEUM ATHENS / GREECE www.miccai2016.org PROGRAM 2016 Images are courtesy of: A. Leemans, PROVIDI Lab, UMC Utrecht, The Netherlands; E. Keeve, Charite Berlin; CASMIP Lab, The Hebrew U. of Jerusalem, Israel; ©CISTIB, Univ. of Sheffield, UK; CAMMA, ICube., Univ. of Strasbourg, France; Medical Image Analysis, ISTB, Univ. Bern, Switzerland 19TH INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION October 17-21 2016 INTERCONTINENTAL ATHENAEUM CONTENT Page WELCOME 2 PROGRAM OVERVIEW 4 GENERAL INFORMATION 5 FLOOR PLANS 8 SPONSORS 11 SPECIAL AND SOCIAL EVENTS 12 GALA DINNER 14 KEYNOTES 15 CONFERENCE PROGRAM 18 POSTER SESSIONS 24 17 OCTOBER SATELLITE EVENTS 48 21 OCTOBER SATELLITE EVENTS 78 MICCAI BOARD 104 MICCAI 2016 ORGANIZATION COMMITEE 105 MICCAI 2016 PROGRAM COMMITEE 106 19TH INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION October 17-21 2016 INTERCONTINENTAL ATHENAEUM WELCOME Welcome to MICCAI 2016 in Athens! It is a privilege and honour for the organisation team to be your host this year at the Intercontinental Athenaeum Hotel in Athens. MICCAI is an outstanding platform to promote, foster and disseminate our research in a very collegial and friendly atmosphere, which we all enjoy so much. We very much hope that we will provide you yet another memorable MICCAI this year as well. MICCAI 2016 received 756 submissions, from which we selected 228 papers for publication. We are very grateful to our Program Committee members and our reviewers who are at the core of the stringent selection process.
    [Show full text]
  • Curriculum Vitae Junzhou Huang
    Curriculum Vitae Junzhou Huang Scalable Modeling & Imaging & Learning Lab Mobile: (732)853-4673 Dept. Computer Science & Engineering Office: (817)272-9596 The University of Texas at Arlington Email: [email protected] 500 UTA Boulevard, Arlington, TX 76019 http://ranger.uta.edu/~huang Research Interest • Machine Learning, Data Mining, Computer Vision, Medical Imaging Informatics Education • Rutgers, the State University of New Jersey, New Brunswick, NJ, USA Ph.D. in Computer Science, June 2011 Thesis: Structured Sparsity: Theorems, Algorithms and Applications Advisor: Dr. Dimitris Metaxas and Dr. Tong Zhang • University of Notre Dame, Notre Dame, IN, USA Ph.D. Candidate in Computer Science and Engineering, 2004 - 2005 • Institute of Automation, Chinese Academy of Sciences, Beijing, China M.S. in Pattern Recognition and Intelligent Systems, June 2003 Thesis: Super Resolution Based Iris Image Enhancement Advisor: Dr. Tieniu Tan • Huazhong University of Science and Technology, Wuhan, China B.E. in Control Science and Engineering, June 1996 Professional Experience • The University of Texas at Arlington 2021 - now, Professor in Computer Science and Engineering 2016 - 2021, Associate Professor in Computer Science and Engineering 2011 - 2016, Assistant Professor in Computer Science and Engineering • Rutgers University 2005 - 2011, Research Assistant in Computer Science • Chinese Academy of Science 2000 - 2004, Research Assistant in the National Lab of Pattern Recognition • Industrial and Commercial Bank of China 1996 - 2000, Software Engineer Award and Honor • 6th Place Winner, the 3D Structure Prediction Challenge in the 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), December 2020. (AlphaFold2 from Deepmind won the 1st place), • 1st Place Winner, the Contact and Distance Prediction Challenge in the 14th Com- munity Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), December 2020.
    [Show full text]
  • Sparse Methods for Computer Vision, Graphics and Medical Imaging
    Sparse methods for computer vision, graphics and medical imaging A Special Track of the 9th International Symposium on Visual Computing (ISVC’13) http://www.isvc.net July 29-31, 2013, Crete, Greece Scope: Sparsity-based compressive sensing and sparse learning have been widely investigated and applied in machine learning, computer vision, computer graphics and medical imaging. The goal of this special track is to publish novel theory, algorithms and applications on sparse methods for applications in these areas. It will foster dialogue and debate in this relatively new field, which includes Compressive Sensing (CS), Sparse Learning (SL) and their applications to these areas. Therefore, the proposed Special Track will gather researchers representing the various fields of machine learning, computer Vision, computer graphics, medical image analysis, mathematics and statistics. This track attempts to establish a bridge between researchers from these diverse fields. The track issue will consist of previously unpublished papers according to ISVC guidelines. Topics: The topics of interest include but are not limited to the following areas: • Compressive sensing MR and other medical imaging • Sparse representation and its applications • Dictionary learning techniques and their applications • Structured and group sparsity • Statistical analysis • Convex optimization based on sparsity priors • General applications in computer vision, such as face recognition, emotion recognition, sign language recognition, super-resolution, tracking • General applications in graphics, such as geometry processing, modeling and simulation • General applications in medical image analysis, such as segmentation, registration, modeling, detection, etc. Paper Submission Procedure: Papers submitted to ISVC 2013 Special Track must not have been previously published and must not be currently under consideration for publication elsewhere.
    [Show full text]
  • Shaoting Zhang Computer Science [email protected] UNC Charlotte Assistant Professor Charlotte, NC, 28223
    Shaoting Zhang Computer Science [email protected] UNC Charlotte http://webpages.uncc.edu/~szhang16/ Assistant Professor Charlotte, NC, 28223 RESEARCH INTERESTS Large-scale and robust data analytics, medical informatics, computer vision and machine learning EDUCATION Rutgers University, Piscataway, NJ 2007/09 – 2012/01 Ph.D. in Computer Science Advisor: Dr. Dimitris N. Metaxas Shanghai Jiao Tong University, Shanghai, China 2005 – 2007 M.S. in Computer Software and Theory Advisor: Dr. Lixu Gu. Thesis co-advisor: Matthias Harders (ETH) Zhejiang University, Hangzhou, China 2001 – 2005 B.S. in Software Engineering EMPLOYMENT University of North Carolina at Charlotte, NC 2013/08 – present Assistant Professor Department of Computer Science Rutgers University, Piscataway, NJ 2012/02 – 2013/08 Research Assistant Professor Department of Computer Science Center for Computational Biomedicine Imaging and Modeling (CBIM) Center for Dynamic Data Analytics (CDDA) Rutgers University, Piscataway, NJ 2007/09 – 2012/01 Research and Teaching Assistant Department of Computer Science, CBIM NEC Laboratories America, Cupertino, CA 2011/06 – 2011/09 Research Intern Siemens Healthcare, Malvern, PA 2010/05 – 2010/08 Research Intern Shanghai Jiao Tong University, Shanghai, China 2005/01 – 2007/07 Research Assistant Lab of Image Guided Surgery and Therapy AWARDS 1. The 3rd Most Cited Paper in Medical Image Analysis since 2011 (the first author) 2016 http://www.journals.elsevier.com/medical-image-analysis/most-cited-articles 2. MICCAI Young Scientist Award in MICCAI’15 (the corresponding author) The 18th Conference on Medical Image Computing and Computer Assisted Intervention Received by my co-advised PhD student Menglin Jiang, 4 awardees out of 810 submissions 2015 3. Finalist of Best Student Paper Awards in IEEE ISBI’15 (the corresponding author) Received by my PhD student Xiaofan Zhang.
    [Show full text]
  • Agenda Final IMG10 V2
    What Can Computer Vision Do for Neuroscience and Vice Versa? Sunday November 14th 3:00 pm Check-in 6:00 pm Reception (Lobby) 7:00 pm Dinner 8:00 pm Session 1: Computer Vision at JFRC I Chair: Eugene Myers 8:00 pm Eugene Myers, Janelia Farm Research Campus/HHMI Introductory remarks 8:10 pm Dmitri Chklovskii, Janelia Farm Research Campus/HHMI Super-resolution reconstruction of brain structure using sparse redundant representations 8:40 pm Hanchuan Peng, Janelia Farm Research Campus/HHMI Seeing more is knowing more 9:10 pm Refreshments available at Bob’s Pub 11/7/2010 1 What Can Computer Vision Do for Neuroscience and Vice Versa? Monday November 15th 7:30 am Breakfast 9:00 am Session 2: Feature Learning Chair: Dmitri Chklovskii 9:00 am Jean Ponce, Ecole Normale Supérieure Sparse coding and dictionary learning for image analysis 9:30 am Yann LeCun, New York University Should artificial vision use the same building blocks as natural vision? 10:00 am Break 10:30 am Session 3: Brain Image Segmentation and Analysis Chair: Hanchuan Peng 10:30 am Demetri Terzopoulos, University of California, Los Angeles Linear and multilinear PCA for automatic brain image segmentation 11:00 am Sebastian Seung, HHMI/Massachusetts Institute of Technology Learning to segment images by optimizing error metrics that are sensitive to topological disagreements 11:30 am Tolga Tasdizen, University of Utah Cell membrane detection in electron microscopy 12:00 pm Rene Vidal, Johns Hopkins University Processing high angular resolution diffusion images of the brain 12:30 pm
    [Show full text]
  • Curriculum Vitae
    CURRICULUM VITAE Vassilis Athitsos Computer Science and Engineering Department Phone: 817-272-0155 University of Texas at Arlington Fax: 817-272-3784 500 UTA Boulevard, Room 623 E-mail: [email protected] Arlington, Texas 76019 Web: http://vlm1.uta.edu/~athitsos RESEARCH INTERESTS Computer Vision, Data Mining, Machine Learning, Gesture and Sign Language Recognition. EDUCATION Boston University, Ph.D. in Computer Science, 2006. University of Chicago, M.S. in Computer Science, 1997. University of Chicago, B.S. in Mathematics, 1995. PROFESSIONAL APPOINTMENTS Sep. 2018 – present: Professor, Computer Science and Engineering Department, University of Texas at Arlington. Sep. 2012 – Aug. 2018: Associate Professor, Computer Science and Engineering Department, University of Texas at Arlington. Aug. 2007 – Aug. 2012. Assistant Professor, Computer Science and Engineering Department, University of Texas at Arlington. Oct. 2006 – Jul. 2007. Postdoctoral Researcher, Computer Science Department, Boston University. Aug 2005 – Sep. 2006. Member of Technical Staff, Siemens Corporate Research. Princeton, New Jersey. Apr. 1998 – Jul. 2005. Research Assistant, Computer Science Department, Boston University. Oct. 1995 – Mar. 1998. Research and Teaching Assistant, Computer Science Department, University of Chicago. HONORS AND AWARDS • Best Student Paper Award, in International Conference on Intelligent User Interfaces (IUI), March 2017. The conference had 272 submissions, and 63 accepted papers. • Outstanding Early Career Award, College of Engineering, University of Texas at Arlington, February 2013. • NSF CAREER Award, 2010. • Outstanding Reviewer Award, CVPR 2010. • Best Paper Award, in IEEE Workshop on Computer Vision and Pattern Recognition for Human Communicative Behavior Analysis (CVPR4HB), June 2008. The workshop had 29 submitted papers. • Best Paper Award, in International Conference on Document Analysis and Retrieval (ICDAR), August 2005.
    [Show full text]