Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/10/91)
VISION-LIST Digest Thu May 09 14:41:01 PDT 91 Volume 10 : Issue 21 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM - Access Vision List Archives via anonymous ftp to ADS.COM Today's Topics: Range image archive status Share a room during "Geometric Methods in Computer Vision of SPIE" pgmtxtur - statistical approach to texture Re: matching sets of points in 2 space Hough transform code Looking for implemented chainning algorithms in C Edge tracer literature search Stereo vision and sensor fusion Performance Evaluation (long) IJCAI-91 Programme Schedule (long) ---------------------------------------------------------------------- Date: Sun, 5 May 91 12:51:52 EST From: Patrick J. Flynn <flynn@shillelagh.cse.nd.edu> Subject: Range image archive status The range image archive on shillelagh.cse.nd.edu (129.74.9.7) will be removed and anonymous ftp disabled on or before May 30, 1991. When I get settled in at Washington State University, I'll re-install the archive on a machine there. This might take a few months, so anyone interested in retrieving the images before the end of the summer should do it now. Please restrict anonymous ftp traffic to non-business hours. I have logged several hundred ftp sessions since I made the archive available last year, and I hope people are finding the data useful. As always, e-mailed questions and suggestions regarding the archive are welcome. Patrick J. Flynn Now: Dept. of Comp. Sci. & Engineering, Univ. of Notre Dame (flynn@cse.nd.edu) Soon: School of EE & CS, Washington State University (flynn@eecs.wsu.edu) ------------------------------ Date: Tue, 7 May 91 17:02:04 EDT From: gong@division.cs.columbia.edu (Yitao Gong) Subject: share a room during "Geometric Methods in Computer Vision of SPIE" Hi, I am a PhD student of Computer Science of Columbia. I'd like to share a room with someone during "Geometric Methods in Computer Vision of SPIE", July 21-26 in San Diego. If interested, send email to: gong@cs.columbia.edu Yitao ------------------------------ Date: Mon, 29 Apr 91 20:35:11 CDT From: jdm5548@diamond.tamu.edu (James Darrell McCauley) Subject: pgmtxtur - statistical approach to texture I've posted source to the USENET newsgroup alt.sources that calculates textural features using the statistical approach. You must have PBMPLUS to compile. If you don't get that newsgroup or don't have a news feed and you would like to receive these, send me e-mail and I'll send you a copy. Thanks to those who tried to find texture images with ground truth. I finally calculated everything by hand for a small image to do my debugging. James Darrell McCauley, Grad Res Asst, Spatial Analysis Lab Dept of Ag Engr, Texas A&M Univ, College Station, TX 77843-2117, USA (jdm5548@diamond.tamu.edu, jdm5548@tamagen.bitnet) ------------------------------ Date: 3 May 91 00:26:46 GMT From: tmb@ai.mit.edu (Thomas M. Breuel) Organization: MIT Artificial Intelligence Lab Subject: Re: matching sets of points in 2 space > Point Set Matching > ------------------ > (Barrodale Computing Services Ltd, May 1991). > > Problem Definition: > We are given two sets of points in the plane. These points could represent > two `simplified' images or output from some sensors. The first set > contains M points. The second set is similar to the first set, except > that some of the points from the first set are missing and some new > points, not in the first set, are present. The second set contains N > points. The positions of the points in the second set are, within a > given tolerance, the same as common points in the first set. However, > within this tolerance fairly large local distortions can occur. > > The problem has three parts: > 1. Find all the points in the first set which do not have a match in > the second set. > 2. Find all points in the second set which do not have a match in > the first set. > 3. For all points in the first set which have a common point in the > second set find the correct match. > Questions: > We are interested in hearing from anyone who has worked on the above > problem or has worked on related problems. We are also interested in > looking at the possibility of using artificial intelligence > techniques, like neural networks, for solving the problem. [since this question seems to come up from time-to-time, I'm posting this response] The following papers will give you a good start at the literature (Eric Grimson's book has an extensive bibliography of the pre-1990 work on the subject; you should look there for other references): Alt H., Mehlhorn K., Wagener H., Welzl E., 1988, Congruence, Similarity, and Symmetries of Geometric Objects., Discrete and Computational Geometry. Baird H. S., 1985, Model-Based Image Matching Using Location, MIT Press, Cambridge, MA. Breuel T. M., 1991, An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition, In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition. Cass T. A., 1990, Feature Matching for Object Localization in the Presence of Uncertainty, In Proceedings of the International Conference on Computer Vision, Osaka, Japan, IEEE, Washington, DC. Grimson E., 1990, Object Recognition by Computer, MIT Press, Cambridge, MA. State-of-the-art algorithms running on a SparcStation can find optimal solutions (either maximal size of match at given error or minimum error at given size of match) to this kind of bounded error recognition problem on the average in under a minute, for models consisting of hundreds points of and images consisting of 1000-2000 unlabeled, oriented features. ------------------------------ Date: Sun, 5 May 91 14:21:30 EDT From: Zhengbin Wang <math4811@nexus.yorku.ca> Subject: Hough transform code Does anyone has the Hough transform code for me to share? Thanks in advance. Richard ------------------------------ Date: Tue, 07 May 91 00:59:00 +0100 From: A.Etemadi@ee.surrey.ac.uk Subject: Looking for implemented chainning algorithms in C G'day, I am looking for any C programs for chainning edge data. I would be most grateful if anyone could send me either programs, or a pointer as to where to get them. I would implement the ones mentioned in Rosenfeld & Kak, 1982, Chapter 10.3 and Ballard & Brown, 1982, Chapters 4 & 8, but I'm tired of reinventing the wheel. Thanks in advance Dr. A. Etemadi, | Phone: (0483) 571-281 Ext. 2311 V.S.S.P. Group, | Fax : (0483) 300-803 Dept. of Electronic and Electrical Eng., | Email: University of Surrey, | Janet: a.etemadi@ee.surrey.ac.uk Guildford, | ata@c.mssl.ucl.ac.uk Surrey GU2 5XH | SPAN : ata@mssl United Kingdom | ata@msslc ------------------------------ Date: 1 May 91 19:57:01 GMT From: bedros@agnes.cs.umn.edu Organization: University of Minnesota, Minneapolis Subject: Edge tracer Keywords: edge detection, edge tracing I am working on postprocessing a low bitrate coded image, thus trying to enhance the edges in the image. I am looking for some references on edge tracing for an edge detected image. Also, any code would be greatly appreciated. Thanks, Saad J Bedros please reply to bedros@ee.umn.edu ------------------------------ Date: Thu, 9 May 91 17:16:31 +0100 From: sjd@computing-maths.cardiff.ac.uk (Molly) Organization: University of Wales College of Cardiff, Cardiff, WALES, UK. Subject: literature search I am looking for a referance entitled : INTEGRATING VISION MODULES WITH COUPLED MRF'S by T.POGGIO . TECHNICAL REPORT WORKING PAPER 285, ARTIFICIAL INTELLIGENCE LABORATORY, MASSACHUSETTS INSTITUTE OF TECHNOLOGY, 1985. Can anybody help me aquire this paper by sending me the address of the author or literature in which i might find it. My e-mail address is sjd@uk.ac.cf.cm Thanks in advance. ------------------------------ Date: Tue, 30 Apr 91 06:03:39 PDT From: 30-Apr-1991 1502 <pau@yippee.enet.dec.com> Subject: Stereo vision and sensor fusion Further to the request for information on stereo vision,but with a slant towards sensor diversity and multi-sensor inputs,many knowledge representation architectures and fusion algorithms are given in : L.F.Pau,Sensor and data fusion,Academic Press,NY,1991 ------------------------------ Date: Wed, 1 May 91 13:03:01 PDT From: tapas@george.ee.washington.edu Subject: Performance Evaluation (long) I have appended all the responses I received for a request I had sent out sometime back. The request was for papers on "Performance Evaluation" in the context of image processing/vision algorithms. Also, I have appended a list of papers we came across and the abstract of our paper on performance evaluation of algorithms which can be posed as performing a detection task. Thanks to every one who responded and a million apologies for the delay on my part in submitting the responses to the list. Also, if you have come across anymore references in the meantime, I will appreciate it if you could post them to the list. Thanks in advance. Tapas Kanungo tapas@george.ee.washington.edu Intelligent Systems Laboratory Department of Electrical Engineering, FT-10 University of Washington Seattle, WA 98195 ================================ Note: 1) The paper by Raudys and Jain has many references which you might want to look at. 2) The January issue of CVGIP:Image Understanding has few papers that discuss the need for performance evaluation. 3) Our paper, Kanungo, Jasimha, Haralick, Palmer, talks about how to characterize the performance of ANY system that does a detection task. That is, input to the system is an image with or without a target and the output of the system is just a YES or NO. ================================ ingemar@robata.nec.com Tapas, I recently submitted a paper entitled ``Optimum and Practical Filters for edge Detection'' to IEEE PAMI. This paper derives optimum filters and then presents a methodology for quantitatively comparing practical filters with the optimum ones. I'd be happy to send you a copy if you let me know your mailing address. Ingemar J. Cox,NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 phone: 609 951 2722 fax: 609 951 2482 email: ingemar@research.nec.com (Inet) uucp: princeton!nec!ingemar Note email will change to ingemar@research.nj.nec.com soon ================================== munnari!wacsvax.cs.uwa.oz.au!wang@uunet.UU.NET In response to your request of Oct 11, I recommend P.K. Sahoo's paper "A Survey of Thresholding Techniques", published in CVGIP 41, 1988, to you. He used some measures for evaluating different thresholding methods which you may be interested in, and have learned as well. C.Y. Wang =================== ace@ecn.purdue.edu I saw your note on the net. We did some evalaution of edge operators. You may want to look at: 1) Delp and Chu, "Detecting Edge Segments", IEEE Trans. Systems, Man, and Cybernetics, Jan. 1985, pp. 144-152. 2)Eichel and Delp, "Quantitative Analysis of a Moment Based Edge Operator", IEEE Trans. Systems, Man, and Cybernetics, Jan. 1990, pp.59-66. We also did some evaluation in: Tan, Gelfannd, and Delp, "A Comparative Cost Function Approach to Edge Detection", IEEE Trans. Systems, Man, and Cybernetics, Dec. 1989, pp. 1337-1349 Prof. E.J. Delp, Purdue University, School of Electrical Engineering =========================== pkahn@ads.com Please take a look at a paper by Kahn, Kitchen, & Riseman, to appear in this Nov's PAMI entitled "A Fast Line Finder for Vision-Guided Robot Navigation." It discusses performance design for fast low-level vision computations. ...note Kitchen and Malin's paper in the bibliobgraphy of this paper: they do some very good performance assessments there. Please note there is the issue of performance from the standpoint of "how well does x perform at doing y?" and there is performance from the standpoint of complexity of computation. Our paper primarily addresses complexity of computation and executional performance. You might also want to look at "The Complexity of Perceptual Search Tasks," J.K. Tsotsos, IJCAI89, pp. 1571-1577. regards, phil... =========================== vistnes@prl.dec.com See "Texture models and image measures for texture discrimination," IJCV 3(4), 1989, 311-336. in which I discuss a method for evaluating texture discrimination algorithms. Richard Vistnes ======================== laine@wave.cis.ufl.edu I response to your request, may I suggest a paper on the performance of stereo matching algorithms executing on the gerneral class of SIMD machines. Laine, Andrew F., "A Parrallel Algorithm for Incremental Stereo Matching on SIMD Machines". To appear IEEE Transactions on Robotics and Automation, 1990. I will gladly provide preprints upon request. The section on Performance Evaluation, contains a general formulation and methodology for the performance evaluation of stereo matching algorithms over the class of SIMD machines. I believe the methodogy may be appealing to reformulate other computer vision alogithms as well. ** An abridged version of this paper was presented at the IEEE 10th International Conference on Pattern Recognition, Atlantic City, NJ, June 16-21, 1990. ================= Following papers are also into performance evaluationi: @article{ DeF:eval, author = "Deutsch, E. S. and J. R. Fram", title = "A quantitative study of the Orientational Bias of some Edge Detector Schemes", journal = "IEEE Transactions on Computers", month = "March", year = 1978} @article{FrD:human, author = "Fram, J.R. and E.S. Deutsch", title = "On the quantitative evaluation of edge detection schemes and their comparisions with human performance", journal = "IEEE Transaction on Computers", volume = "C-24", number = "6", pages = "616-627" year = 1975} @article{AbP:eval, author = "Abdou, I.E. and W. K. Pratt", title = "Qualitative design and evaluation of enhancement/thresholding edge detector", journal = "Proc. IEEE", volume = "67", number = "5", pages = "753-763", year = 1979} @article{PeM:eval, author = "Peli, T. and D. Malah", title = "A study of edge detection algorithms", journal = "Computer Graphics and Image Processing", volume = "20", pages ="1-21", year = 1982} @article{KiR:eval, author = "Kitchen, L. and A. Rosenfeld", title = "Edge Evaluation using local edge coherence", journal = "IEEE Transactions on Systems, Man and Cybernetics", volume = "SMC-11", number = "9", pages = "597-605", year = 1981} @article{HaL:eval, author = "Haralick, R.M. and J. S. J. Lee", title = "Context dependent edge detection and evaluation", journal = "Pattern Recognition", volume = "23", number = "1/2", pages = "1-19", year = 1990} @article{Har:performance, author = "Haralick, R.M.", title = "Performance assessment of near perfect machines", journal = "Machine Vision and Applications", volume = "2", number = "1", pages = "1-16", year = 1989} @inproceedings{KJHP:performance, author = "Kanungo, T. and M.Y. Jaisimha and R.M. Haralick and J. Palmer", booktitle = "Proc. SPIE vol. 1385 Optics, Illumination, and Image Sensing for Machine Vision V", pages = "104-112", month = "November", year = 1990} @article{HNR:hough, author = "Hunt, D.J. and L.W. Nolte and A.R. Reibman and W.H. Ruedger", title = "Hough Transform and Signal Detection Theory Performance for Images with Additive Noise", journal = cvgip, volume = 52, pages = "386-401", year = 1990} @article{RJ:smallsample, author = " Raudys, J.S. and A.K. Jain", title = "Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners", journal = pami, volume = 13, number = 3, pages = "252-263", year = 1990} =================== Abstract of our paper follows: \title{An Experimental Methodology for Performance Characterization of a Line Detection Algorithm } % \author{\dag T. Kanungo, \dag M. Y. Jaisimha, \dag R. M. Haralick and \ddag J. Palmer \\ \\ \dag Department of Electrical Engineering, FT-10 \\ \ddag Department of Psychology, NI-25 \\ University of Washington \\ Seattle WA 98195 \\ U.S.A.} % \date{ \today \\ \presenttime } \maketitle \begin{abstract} With the burgeoning of computer vision algorithms, it has become increasingly necessary to characterize and evaluate their performance in a quantitative fashion. In the vast majority of the existing literature, the assessment of an algorithm is usually done by analyzing its results on just two to three images. There is no mention of the population of images the algorithm is supposed to work on. No effort is made to address the concerns of whether or not the sample set used is representative of the population. In addition, the analysis of the accuracy and level of confidence in the results is often not specified. In this paper, we present a methodology for designing experiments to characterize low level computer vision algorithms which addresses these issues. The methodology is illustrated by applying it to the specific case where a line detection algorithm is used to detect the presence or absence of a vertical edge in the presence of a masking grating. The line detection algorithm consists of edge detection using the second directional derivative edge detector followed by a mapping to Hough space. The performance of the algorithm is studied with respect to the edge contrast, the image noise, orientation, and phase. The eventual objective of the experiment is to study the orientation sensitivity of the line detection algorithm. A set of experiments were performed to obtain the operating curves relating the probability of misdetection and the probability of false alarm of the algorithm. The contrast threshold which is the measure of the sensitivity a representative set of the control parameter values. Thresholds representing meaningful measures of the performance levels are then extracted from the operating curves. These thresholds are statistically consolidated to get a combined performance versus grating orientation curve, and a measure of the overall performance level. The line detection algorithm is thus characterized by the operating curves, the combined performance curve and the overall performance level. The results also show that the performance of the line detection algorithm is not affected by the orientation of the masking grating. \end{abstract} ------------------------------ Date: Thu, 9 May 1991 10:44:51 -0400 From: Kimberlee Pietrzak-Smith <kim@cs.toronto.edu> Subject: IJCAI-91 Programme Schedule ***INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 1991*** IJCAI-91 Programme Schedule Monday, August 26, 1991 9-10am: Invited Speaker 1 - Ross Quinlan 10-10:30am: Coffee 10:30-12:30pm: ML: Explanation Based Learning Christer Samuelsson Quantitative Evaluation of Explanation-Based Learning as an Optimization Tool for a Large-Scale Natural Language System Prasad Tadepalli A Formalization of Explanation-Based Macro-Operator Learning Masayuki Yamamura An Augmented EBL and its Application to Utility Problem Jungsoon Yoo Concept Formation over Explanations and Problem-Solving Experience NL: NL Processing Dan Moldovan High Performance Natural Language Processing on Semantic Network Array Processor Hiroaki Kitano Massively Parallel Memory-Based Parsing Esther Konig Using Parallel Processing for Semantic Analysis Karl Gregor Erbach An environment for experimentation with parsing strategies KR: Nonmonotonic Reasoning - Modal Logics Vladimir Lifschitz Nonmonotonic Databases and Epistemic Queries: Preliminary Report Nicholas Asher Commonsense Entailment: A Modal Theory of Nonmonotonic Reasoning Mirek Truszczynski Modal Interpretations of Default Logic Ilkka Niemela Constructive Tightly Grounded Autoepistemic Reasoning AR: Theorem Proving I Michael Fisher Yet Another Resolution Method for Temporal Logic Thomas Guckenbiehl Formalizing and Using Persistency Fausto Giunchiglia Reflective reasoning with and between a declarative metatheory and the implementation code Nachum Dershowitz Ordering-Based Strategies for Horn Clauses Arch: Knowledge Base Management G. Ravi Prakash A Methodology for Systematic Verification of OPS5-based AI Applications Loren Terveen Intelligent Assistance through Collaborative Manipulation Keith Decker Effects of Parallelism on Blackboard System Scheduling Rick Evertsz The Automated Analysis of Rule-based Systems, Based on their Procedural Semantics 12:30-2pm: Lunch 2-3:30pm: Panel 1: AI in Telecommunications ML: Classifiers/Genetic Algorithms Wray Buntine Classifiers: A Theoretical and Empirical Study James Kelly A Hybrid Genetic Algorithm for Classification Kenneth A. De Jong Learning Concept Classification Rules Using Genetic Algorithms KR: Belief Sukhamay Kundu A New Logic of Beliefs: Monotonic Beliefs and Nonmonotonic Beliefs - Part 1 Gerhard Lakemeyer A Model of Decidable Introspective Reasoning with Qualitifying-In Anand S. Rao Asymmetry Thesis and Side-effect Problems in Linear Time and Branching Time Intention Logics LP: Logic Programming I Sieger van Denneheuvel Weak equivalence for constraint sets Chilukuri K. Mohan Fitting Semantics for Conditional Term Rewriting Luis Moniz Pereira A Derivation Procedure for Extended Stable Models (Draft) Phil: Philosophical Foundations I Francis Jeffry Pelletier The Philosophy of Automated Theorem Proving Raymond Earl Jennings Generalised Inference and Inferential Modelling John Slaney The Implications of Paraconsistency 3:30-4pm: Coffee 4-5:30pm: AI On Line ML: Inductive Learning I Sholom M. Weiss Reduced Complexity Rule Induction Alen Varsek Qualitative Model Evolution Celine Rouveirol Semantic Model for Induction of First Order Theories AR: Search I G.M.A. Provan An Expected-Cost Analysis of Backtracking and Non-Backtracking Algorithms Amitava Bagchi Admissible Search Methods for Minimum Penalty Sequencing of Jobs with Setup Times on One and Two Machines Anna Bramanti-Gregor Learning Admissible Heuristics while Solving Problems LP: Logic Programming II Mike Brayshaw An Architecture for Visualising the Execution of Parallel Logic Programs Kang Zhang A Non-shared Binding Scheme for Parallel Prolog Implementation KR: Reasoning with Inconsistency Mamede Lima Marques Contextual Negations and Reasoning with Contradictions Gerd Wagner Ex contradictione nihil sequitir Rob: Architectures Luc Steels Emergent Frame Recognition And Its Use In Artificial Creatures R. Peter Bonasso Integrating Reaction Plans and Layered Competences through Synchronous Control 7:30pm: Computers & Thought Award: Martha Pollack and Rodney Brooks Announcement of IJCAI Best Paper Award Tuesday, August 27, 1991 9-10am: Invited Speaker 2- Shigeru Sato 10-10:30am: Coffee 10:30-12:30pm: ML: Inductive Learning II Robin Hanson Bayesian Classification with Correlation and Inheritance Der-Shung Yang A Scheme for Feature Construction and a Comparison of Empirical Methods Steven Salzberg Learning with a Helpful Teacher Stefan Wrobel Towards a Model of Grounded Concept Formation AR: Planning I Stuart J. Russell Composing Real-Time Systems Eric Biefeld Bottleneck Identification Using Process Chronologies Jeffrey S. Rosenschein Incomplete Information and Deception in Multi-Agent Negotiation Marta Franova Solving "How to Clear a Block" with Constructive Matching Methodology NL: Pragmatics Peter van Beck Resolving Plan Ambiguity for Cooperative Response Generation Yorick Wilks Your metaphor or mine: Belief ascription and metaphor interpretation Philip R. Cohen Confirmations and Joint Action QR: Diagnosis Philippe Dague When Oscillators Stop Oscillating Gerhard Friedrich Diagnosing Temporal Misbehavior Franz Lackinger Integrating Model-Based Monitoring and Diagnosis of Complex Dynamic Systems David Poole Representing diagnostic knowledge for probabilistic Horn abduction Vis: Object Recognition Yerucham Shapira A Pictorial Approach to Object Classification Thomas M. Strat Natural Object Recognition: A Theoretical Framework and Its Implementation John R. Kender On Seeing Spaghetti: A Novel Self-Adjusting Seven Parameter Hough Space for Analyzing Flexible Extruded Objects Tomaso Poggio HyperBF Networks for real object recognition 12:30-2pm: Lunch 2-3:30pm: Panel 2: AI and Design ML: Inductive Logic Programming J.R. Quinlan Determinate Literals as an Aid in Inductive Logic Programming Charles X. Ling Inductive Learning from Good Examples Marc Kirschenbaum Refinement Strategies for Inductive Learning of Simple Prolog Programs KR: Nonmonotonic Reasoning - Conditional Logics Hirofumi Katsuno A Unified View of Consequence Relation, Belief Revision and Conditional Logic Craig Boutilier Inaccessible Worlds and Irrelevance: Preliminary Report Didier Dubois Possibilistic logic, preference models, non-monotonicity and related issues AR: Search II Hermann Kaindl Using Aspiration Windows for Minimax Algorithms Stephen V. Chenoweth High Performance A* Search Using Rapidly Growing Heuristics Toru Ishida Moving Target Search CM: Cognitive Modelling 1 Jacobijn Sandberg How situated is cognition? Katia P. Sycara Index Transformation Techniques for Facilitating Creative Use of Multiple Cases Gregg Collins Plan debugging in an Intentional System 3:30-4pm: Coffee 4-5:30pm: AI On Line ML: Concept Formation Jason Catlett Overpruning Large Decision Trees Larry Watanabe Learning Structural Decision Trees From Examples David Heath Learning Nested Concept Classes with Limited Storage Sunil Thakar Acquiring Knowledge by Efficient Query Learning KR: Concept Languages Franz Baader Augmenting Concept Languages by Transitive Closure of Roles: An Alternative to Terminological Cycles Franz Baader A Scheme for Integrating Concrete Domains into Concept Languages Maurizio Lenzerini Tractable Concept Languages AR: Theorem Proving II Toni Bollinger A Model Elimination Calculus for Generalized Clauses Inside the LILOG Inference Machine Elmar Eder Consolution and its Relation with Resolution Manfred Kerber How to Prove Higher Order Theorems in First Order Logic Hitoshi Iba Reasoning of Geometric Concepts based on Algebraic Constraint-directed Method Phil: Philosophical Foundations II David Israel Actions and Movements Selmer Bringsjord In Defense of Hyper-Logicist AI Francesco Bergadano The Problem of Induction and Machine Learning QR: Qualitative Modelling Erling A. Woods The Hybrid Phenomena Theory Feng Zhao Extracting and Representing Qualitative Behaviors of Complex Systems in Phase Spaces Toyoaki Nishida A Geometric Approach to Total Envisioning Wednesday, August 28, 1991 9-10am: Distinguished Scientist Award & Lecture: Marvin Minsky 10-10:30am: Coffee 10:30-12:30pm: KR: Topics in Knowledge Representation Periklis Belegrinos A Model for Actions and Processes Hans Juergen Ohlbach Parameter Structures for Parametrized Modal Operators Russell Greiner Measuring and Improving the Effectiveness of Representations Gadi Pinkas Propositional Non-Monotonic Reasoning and Inconsistency in Symmetric Neural Networks AR: Planning II Edwin P.D. Pednault Generalizing Nonlinear Planning to Handle Complex Goals and Actions with Context-Dependent Effects Jens Christensen A Formal Model for Classical Planning Amy L. Lansky Localized Search for Multiagent Planning Steven Minton Commitment Strategies in Planning: A Comparative Analysis NL: NL Systems Marie Meteer POST: Using Probabilities in Language Processing John A. Bateman The rapid prototyping of natural language generation components: an application of functional typology Oliviero Stock Natural Language and Exploration of an Information Space: the ALFRESCO Interactive System C. Rullent Efficient Representation of Linguistic Knowledge for Continuous Speech Understanding QR: Qualitative Modelling, Temporal Reasoning Ulf Soderman Combining Qualitative and Quantitative Knowledge to Generate Models fo Physical Systems Judea Pearl Directed Constraint Networks: A Relational Framework for Causal Modeling Jan Top Computational and Physical Causality Antony Galton Reified Temporal Theories And How To Unreify Them Vis: Interpretation Paul Cohen Shading-Based Two-View Matching Pascal Fua Combining Stereo and Monocular Information: Computing Robust Dense Depth Maps and Preserving Depth Discontinuities R. Mike Cameron-Jones Visual Interpretation of Lambertian Surface Deformation Terry Regier Line Labeling and Junction Labeling: A Coupled System for Image Interpretation 12:30-2pm: Lunch 2-5:30pm: Computer & Chess Afternoon Panel and Chess Match Thursday, August 29, 1991 9-10am: Invited Speaker 3 - Robert Kowalski 10-10:30am: Coffee 10:30-12:30pm: ML: Inductive Learning III Armand E. Prieditis Machine Discovery of Effective Admissible Heuristics by Means-Ends Analysis David Chapman Learning from Delayed Reinforcement In a Complex Domain Wayne Iba Learning to Classify Observed Motor Behavior Peter C-H. Cheng Modelling Experiments in Scientific Discovery AR: Reason Maintenance Jean Christophe Madre A Logically Complete Reasoning Maintenance System Based on a Logical Constraint Solver Jerome Euzenat Contexts for Nonmonotonic RMSes Wang Xianchang On Semantics of TMS Ulrich Junker Prioritized Defaults: Implementation by TMS and Application to Diagnosis NL: Representation and Semantics Padraig Cunningham Organizational Issues Arising from the Integration of Lexicon and Concept Network in a Text Understanding System Mark Johnson Logic and Feature Structures Leonardo Lesmo Representation and Interpretation of Definite Noun Phrases Stephen Busemann Using Pattern-Action Rules for the Generation of GPSG Structures From MT-Oriented Semantics LP: Logic Programming III Kienchung Kuo Programming in Autoepistemic Logic L. Thorne McCarty Indefinite Reasoning with Definite Rules Karen L. Kwast The Incomplete Database Mark Wallace Compiling Integrity Checking into Update Procedures Dinesh Gadwal UMRAO: A Chess Endgame Tutor Luigia Carlucci-Aiello Reasoning about Student Knowledge and Reasoning Tak-Wai Chan Integration-Kid: A Learning Companion System William R. Murray An Endorsement-based Approach to Student Modeling for Planner-controlled Tutors 12:30-2pm: Lunch 2-3:30pm: Panel 3: Multiple Approaches tp Mulitple Agent Problem Solving ML: Case Based Learning Diane J. Cook The Base Selection Task in Analogical Planning Scott Fertig FGP: A Software Architecture for Acquiring Knowledge from Cases James P. Callan Adaptive Case-Based Reasoning KR: Nonmonotonic Reasoning - Circumscription Nicolas Helft Query Answering in Circumscription Yves Moinard Circumscription and Definability Zhaogang Qian Circumscribing Defaults AR: Theorem Proving III Robert Demolombe An Inference Rule for Hypothesis Generation Katsumi Inoue Consequence-Finding Based on Ordered Linear Resolution Christoph Lingenfelder Proof Transformation with Built-in Equality Predicate Arch: Distributed AI I Sarit Kraus Negotiations over Time in A Multi Agent Environment: Preliminary Report Piotr J. Gmytrasiewicz A Decision-Theoretic Approach to Coordination Multiagent Interactions Munindar P. Singh Towards a Formal Theory of Communication for Multiagent Systems 3:30-4pm: Coffee 4-5:30pm: AI On Line ML: Classification & Generalization Floriana Esposito Flexible Matching for Noisy Structural Descriptions Haym Hirsch Theoretical Underpinnings of Version Spaces Jacques Nicolas Empirical Bias for Version Space KR: Concept Languages, Inheritance Reasoning Klaus Schild A Correspondence Theory for Terminological Logics: Preliminary Report John Yen Generalizing Term Subsumption Languages to Fuzzy Logic David S. Touretzky A Skeptic's Menagerie: Conflictors, Preemptors, Reinstators, and Zombies in Nonmonotonic Inheritance AR: Constraint Satisfaction Rina Dechter On the Feasibility of Distributed Constraint Satisfaction Pascal van Hentenryck Efficient Arc Consistency Algorithm for a Class of CSP Problems Peter Cheeseman Where the Really Hard Problems Are QR: Reasoning under Uncertainty I Yen-Teh Hsia Characterizing Belief with Minimum Commitment Rudolf Kruse On a Tool for Reasoning with Mass Distribution Henry E. Kyburg Evidential Probability Rob: Navigation Stephen F. Peters Planning Robot Control Parameter Values with Qualitative Reasoning Patrick Stelmasyk Mobile Robot Navigation by an Active Control of the Vision System Matthew Barth Determining Robot Egomotion from Motion Parallax Observed by an Active Camera 5:30pm: General Meeting Friday, August 30, 1991 9-10am: Invited Speaker 4- Takeo Kanade 10-10:30am: Coffee 10:30-12:30pm: AR: Planning III Christer Backstrom Parallel Non-Binary Planning in Polynomial Time Tom Bylander Complexity Results for Planning Dekang Lin A Message Passing Algorithm for Plan Recognition Fahiem Bacchus The Downward Refinement Property NL: Parsing and Morphology Tsunenori Mine Coordinative Parallel Morphological and Syntactical Analysis Method in Japanese Liang-Jyh Wang A Parsing Method for Identifying Words in Mandarin Chinese Sentences Harald Trost X2MORF: A Morphological Component Based on Augmented Two-Level Morphology Venu Dasigi Parsing = Parsimonious Covering (Abduction in Logical Form Generation) Arch: Connectionist & Parallel Rule Systems Tony Plate Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations Andrew Sohn A Macro Actor/Token Implemetation of Production Systems on Data-Flow Multiprocessor Dan Moldovan Performance Comparison of Models for Multiple Rule Firing Ian Nevill Robinson On Supporting Associative Access and Processing over Dynamic Knowledge Bases Summary Session: IJCAI-91, Learning and Knowledge Acquisition Summary Session: KR'91, International Conference on Principles of Knowledge Representation and Reasoning 12:30-2pm: Lunch 2-3:30pm: Panel 4: Massively Parallel Computing in Artificial Intelligence: Bridging Gaps Between Hardware and Applications ML: Knowledge Acquisition Kathleen McKusick Constraints on Tree Structure in Concept Formation Brian R. Gaines An Interactive Visual Language for Term Subsumption Languages Matthias Gutknecht Cooperative Hybrid Systems CM: Cognitive Modelling 2 N. Hari Narayanan Reasoning Visually about Spatial Interactions Akira Shimaya A Cognitive Model for Figure Segregation W.K. Yeap An MFIS for Computing a Raw Cognitive Map Summary Session: IJCAI-91, Automated Reasoning Summary Session: International Symposium on AI and Mathematics 3:30-4pm: Coffee 4-5:30pm: ML: Connectionist Models Warren R. Becraft Integration of Neural Networks and Expert Systems for Process Fault Diagnosis Chilukuri Krishna Mohan Analyzing Images Containing Multiple Sparse Patterns with Neural Networks Selwyn Piramuthu The Utility of Feature Construction for Back-Propagation Arch: Distributed AI II Hideyuki Nakashima Communication and Inference through Situations David N. Kinny Commitment and Effectiveness of Situated Agents Takashi Nishiyama Generating Integrated Interpretation of Partial Information Based on Distributed Qualitative Reasoning QR: Reasoning under Uncertainty II S.K.M. Wong Propagation of Preference Relations in Qualitative Inference Networks Wilson Xun Wen Parallel Distributed Belief Networks That Learn Summary Session: IJCAI-91, Natural Language Summary Session: International Conference on Automated Deduction LEGEND: AR: Automated Reasoning Arch: Architectures & Languages CM: Cognitive Modelling KR: Knowledge Representation LP: Logic Programming ML: Machine Learning NL: Natural Language Phil: Philosophical Foundations QR: Qualitative Reasoning Rob: Robotics Vis: Vision ------------------------------ End of VISION-LIST digest 10.21 ************************