view org/ai-journal-review.org @ 446:3e91585b2a1c

save.
author Robert McIntyre <rlm@mit.edu>
date Tue, 25 Mar 2014 03:24:28 -0400
parents ff0d8955711e
children ebdedb039cbb
line wrap: on
line source
1 #+title:Interesting Papers in Artificial Intelligence
3 I decided to read all of the /titles/ in the Artificial Intelligence
4 journal, and found these interesting papers. The entire title-reading
5 process took about 2 hours.
7 * Interesting Concept
9 - (2002) Jordi Delgado - Emergence of social conventions in complex networks
11 Here, "social conventions" means a very specific property of graphs
12 in the context of game theory. Their social networks are groups of
13 mindless automotaons which each have a single opinion that can take
14 the values "A" or "B". They use the "coordination game" payoff
15 matrix that engourages each pair of agents to agree with each other,
16 and study various ways the graph can come to 90% of the agents all
17 believe either "A" or "B". It's probably not useful for actual
18 social worlds, and there's no simulation of any interesting
19 environment, but it might be useful for designing protocols, or as a
20 problem solving method.
22 References:
23 + L.A. Nunes Amaral, A. Scala, M. Barthélémy, H.E. Stanley, Classes
24 of small-world networks, Proc. Nat. Acad. Sci. 97 (2000)
25 11149–11152.
26 + D.J Watts, S.H. Strogatz, Collective dynamics of small-world
27 networks, Nature 393 (1998) 440–442.
28 + Y. Shoham, M. Tennenholtz, On the emergence of social conventions:
29 Modeling, analysis and simulations, Artificial Intelligence 94
30 (1997) 139–166.
32 - (1997) Yoav Shoham, Moshe Tennenholtz - On the emergence of social
33 conventions: modeling, analysis, and simulations
36 Marcelo A. Falappa, Gabriele Kern-Isberner, Guillermo R. Simari -
37 Explanations, belief revision and defeasible reasoning
39 Claudio Bettini, X.Sean Wang, Sushil Jajodia - Solving
40 multi-granularity temporal constraint networks
42 Alberto Maria Segre, Sean Forman, Giovanni Resta, Andrew Wildenberg -
43 Nagging: A scalable fault-tolerant paradigm for distributed search
45 Fahiem Bacchus, Xinguang Chen, Peter van Beek, Toby Walsh - Binary
46 vs. non-binary constraints
48 Jie Cheng, Russell Greiner, Jonathan Kelly, David Bell, Weiru Liu -
49 Learning Bayesian networks from data: An information-theory based
50 approach
52 Kurt Engesser, Dov M. Gabbay - Quantum logic, Hilbert space, revision
53 theory
55 J.-D. Fouks, L. Signac - The problem of survival from an algorithmic
56 point of view
58 Catherine Carr - The MIT Encyclopedia of the Cognitive Sciences,
59 edited by Robert Wilson and Frank Keil
61 - Tim Taylor - Christoph Adami, Introduction to Artificial Life
62 References:
63 + M.A. Boden (Ed.), The Philosophy of Artificial Life, Oxford
64 University Press, Oxford, 1996.
65 + C.G. Langton (Ed.), Artificial Life: An Introduction, MIT Press,
66 Cambridge, MA, 1995.
68 A.S d'Avila Garcez, K Broda, D.M Gabbay - Symbolic knowledge
69 extraction from trained neural networks: A sound approach
71 José Hernández-Orallo - Truth from Trash. How Learning Makes Sense by
72 Chris Thornton
74 Fabio G. Cozman - Credal networks
76 Aaron N. Kaplan, Lenhart K. Schubert - A computational model of belief
78 Mike Perkowitz, Oren Etzioni - Towards adaptive Web sites: Conceptual
79 framework and case study
81 Wilhelm Rödder - Conditional logic and the Principle of Entropy
83 Christian Vilhelm, Pierre Ravaux, Daniel Calvelo, Alexandre Jaborska,
84 Marie-Christine Chambrin, Michel Boniface - Think!: A unified
85 numerical–symbolic knowledge representation scheme and reasoning
86 system
88 Charles L. Ortiz Jr. - A commonsense language for reasoning about
89 causation and rational action
91 Raúl E. Valdés-Pérez - Principles of human—computer collaboration for
92 knowledge discovery in science
94 Paul Snow - The vulnerability of the transferable belief model to
95 Dutch books
97 Simon Kasif, Steven Salzberg, David Waltz, John Rachlin, David
98 W. Aha - A probabilistic framework for memory-based reasoning
100 Geoffrey LaForte, Patrick J. Hayes, Kenneth M. Ford - Why Gödel's
101 theorem cannot refute computationalism
103 Hiroshi Motoda, Kenichi Yoshida - Machine learning techniques to make
104 computers easier to use
106 Aravind K. Joshi - Role of constrained computational systems in
107 natural language processing
109 Moshe Tennenholtz - On stable social laws and qualitative equilibria
111 Michael Arbib - The metaphorical brains
113 Andrew Gelsey, Mark Schwabacher, Don Smith - Using modeling knowledge
114 to guide design space search
116 Márk Jelasity, József Dombi - GAS, a concept on modeling species in
117 genetic algorithms
119 Randall H. Wilson - Geometric reasoning about assembly tools
121 Kurt Ammon - An automatic proof of Gödel's incompleteness theorem
123 Shmuel Onn, Moshe Tennenholtz - Determination of social laws for
124 multi-agent mobilization
126 Stuart J. Russell - Rationality and intelligence
128 Hidde de Jong, Arie Rip - The computer revolution in science: steps
129 towards the realization of computer-supported discovery environments
131 Adnan Darwiche, Judea Pearl - On the logic of iterated belief revision
133 R.C. Holte, T. Mkadmi, R.M. Zimmer, A.J. MacDonald - Speeding up
134 problem solving by abstraction: a graph oriented approach
136 R. Holte, T. Mkadmi, R.M. Zimmer, A.J. McDonald - Speeding up problem
137 solving by abstraction: a graph oriented approach
139 Raúl E. Valdés-Pérez - A new theorem in particle physics enabled by
140 machine discovery
142 Dan Roth - On the hardness of approximate reasoning
144 Bart Selman, David G. Mitchell, Hector J. Levesque - Generating hard
145 satisfiability problems
147 Herbert A. Simon - Artificial intelligence: an empirical science
149 John K. Tsotsos - Behaviorist intelligence and the scaling problem
151 Shigeki Goto, Hisao Nojima - Equilibrium analysis of the distribution
152 of information in human society
154 Raúl E. Valdés-Pérez - Machine discovery in chemistry: new results
156 Stephen W. Smoliar - Artificial life: Christopher G. Langton, ed.
158 Yoav Shoham, Moshe Tennenholtz - On social laws for artificial agent
159 societies: off-line design
161 Barbara Hayes-Roth - An architecture for adaptive intelligent systems
163 Bruce Randall Donald - On information invariants in robotics
165 Ian P. Gent, Toby Walsh - Easy problems are sometimes hard
167 Tad Hogg, Colin P. Williams - The hardest constraint problems: A
168 double phase transition
170 Yoram Moses, Yoav Shoham - Belief as defeasible knowledge
172 Donald Michie - Turing's test and conscious thought
174 John McDermott - R1 (“XCON”) at age 12: lessons from an elementary
175 school achiever
177 Takeo Kanade - From a real chair to a negative chair
179 Harry G. Barrow, J.M. Tenenbaum - Retrospective on “Interpreting line
180 drawings as three-dimensional surfaces”
182 Judea Pearl - Belief networks revisited
184 Glenn A. Kramer - A geometric constraint engine
186 Fausto Giunchiglia, Toby Walsh - A theory of abstraction
188 John L. Pollock - How to reason defeasibly
190 Aaron Sloman - The emperor's real mind: Review of Roger Penrose's the
191 emperor's new mind: Concerning computers, minds and the laws of
192 physics
194 Olivier Dordan - Mathematical problems arising in qualitative
195 simulation of a differential equation
197 Eric Saund - Putting knowledge into a visual shape representation
199 Michael Freund, Daniel Lehmann, Paul Morris - Rationality,
200 transitivity, and contraposition
202 Anthony S. Maida - Maintaining mental models of agents who have
203 existential misconceptions
205 Henry A. Kautz, Bart Selman - Hard problems for simple default logics
207 Mark J. Stefik, Stephen Smoliar - Four reviews of The Society of Mind
208 and a response
210 Michael G. Dyer - A society of ideas on cognition: Review of Marvin
211 Minsky's The Society of Mind
213 Matthew Ginsberg - The society of mind: Marvin Minsky
215 George N. Reeke Jr - The society of mind: Marvin Minsky
217 Stephen W. Smoliar - The society of mind: Marvin Minsky
219 Marvin Minsky - Society of mind: A response to four reviews
221 Stephen W. Smoliar - How to build a person: A prolegomenon: John
222 Pollock
224 David Makinson, Karl Schlechta - Floating conclusions and zombie
225 paths: Two deep difficulties in the “directly skeptical” approach to
226 defeasible inheritance nets
228 Donald A. Norman - Approaches to the study of intelligence
230 Rodney A. Brooks - Intelligence without representation
232 David Kirsh - Today the earwig, tomorrow man?
234 Douglas B. Lenat, Edward A. Feigenbaum - On the thresholds of
235 knowledge
237 Jordan B. Pollack - Recursive distributed representations
239 R. Bhaskar, Anil Nigam - Qualitative physics using dimensional
240 analysis
242 Don F. Beal - A generalised quiescence search algorithm
244 Kai-Fu Lee, Sanjoy Mahajan - The development of a world class Othello
245 program
247 Helmut Horacek - Reasoning with uncertainty in computer chess
249 Jeff Shrager - Induction: Process of inference, learning and
250 discovery: John H. Holland, Keith J. Holyoak, Richard E. Nisbett, and
251 Paul R. Thagard (MIT Press, Cambridge, MA, 1986); 355 pages
253 Daniel S. Weld - The psychology of everyday things: Donald A. Norman,
254 (Basic Books, New York, 1988); 257 pages, $19.95
256 John R. Anderson - A theory of the origins of human knowledge
258 G. Tesauro, T.J. Sejnowski - A parallel network that learns to play
259 backgammon
261 G. Priest - Reasoning about truth
263 Donald Perlis - Truth and meaning
265 Daniel S. Weld - Women, fire, and dangerous things: George Lakoff,
266 (University of Chicago Press, Chicago, IL, 1987); 614 pages, $29.95
268 Mark J. Stefik - On book reviews policy and process
270 Robert K. Lindsay - The science of the mind: Owen J. Flanagan, Jr.,
271 (MIT Press, Cambridge, MA, 1984); 290 pages
273 Sheila Rock - On machine intelligence: Donald Michie, 2nd ed. (Ellis
274 Horwood, Chichester, United Kingdom, 1986); 265 pages, £29.95
276 Stephen W. Smoliar - Epistemology and cognition: A.I. Goldman,
277 (Harvard University Press, Cambridge, MA, 1986); ix + 437 pages,
278 $27.50
280 David Elliot Shaw - On the range of applicability of an artificial
281 intelligence machine
283 Michael Gordon - Machine intelligence and related topics: An
284 information scientist's weekend book: Donald Michie, (Gordon and
285 Breach, New York, 1982); 328 pages, $57.75
287 Ryszard S. Michalski, Patrick H. Winston - Variable precision logic
289 Martin Herman, Takeo Kanade - Incremental reconstruction of 3D scenes
290 from multiple, complex images
292 vision : June 8–11, 1987, London, United Kingdom
294 André Vellino - Artificial intelligence: The very idea: J. Haugeland,
295 (MIT Press, Cambridge, MA, 1985); 287 pp.
297 Judea Pearl - Fusion, propagation, and structuring in belief networks
299 Daniel G. Bobrow - Scientific debate
301 Mark Stefik - The AI business: Commercial uses of artificial
302 intelligence: P.H. Winston and K.A. Prendergast, (MIT Press,
303 Cambridge, MA 1984); 324 pages, $15.95
305 Hans Berliner, Carl Ebeling - The SUPREM architecture: A new
306 intelligent paradigm
308 Donna Reese - Artificial intelligence: P.H. Winston, (Addison-Wesley,
309 Reading, MA, 2nd ed., 1984); 527 pages
311 Kenneth D. Forbus - Structure and interpretation of computer programs:
312 H. Abelson and G.J. Sussman with J. Sussman, (MIT, Cambridge, 1985);
313 503 pages
315 Chia-Hoang Lee, Azriel Rosenfeld - Improved methods of estimating
316 shape from shading using the light source coordinate system
318 Daniel G. Bobrow, Patrick J. Hayes - Artificial intelligence — Where
319 are we?
321 Barbara J. Grosz - Natural-language processing
323 Johan De Kleer - How circuits work
325 G.D. Ritchie, F.K. Hanna - am: A case study in AI methodology
327 Douglas B. Lenat, John Seely Brown - Why am and eurisko appear to work
329 Elaine Kant - On the efficient synthesis of efficient programs
331 Randall Davis, Reid G. Smith - Negotiation as a metaphor for
332 distributed problem solving
334 Patrick H. Winston - Learning new principles from precedents and
335 exercises
337 Paul S. Rosenbloom - A world-championship-level Othello program
339 Tomas Lozano-Perez - Robotics
341 Tom M. Mitchell - Generalization as search
343 Dana S. Nau - The last player theorem
345 Hans J. Berliner - Backgammon computer program beats world champion
347 Gerald Jay Sussman, Guy Lewis Steele Jr. - Constraints—A language for
348 expressing almost-hierarchical descriptions
350 Takeo Kanade - A theory of Origami world
352 Ria Follett - Synthesising recursive functions with side effects
354 John McCarthy - Circumscription—A form of non-monotonic reasoning
356 Michael A. Bauer - Programming by examples
358 Patrick H. Winston - Learning by creatifying transfer frames
360 Alan Bundy - Will it reach the top? Prediction in the mechanics world
362 Richard M. Stallman, Gerald J. Sussman - Forward reasoning and
363 dependency-directed backtracking in a system for computer-aided
364 circuit analysis
366 D. Marr - Artificial intelligence—A personal view
368 Berthold K.P. Horn - Understanding image intensities
370 F. Malloy Brown - Doing arithmetic without diagrams
372 Azriel Rosenfeld - The psychology of computer vision: Patrick Henry
373 Winston (ed.) McGraw-Hill, New York, 1975, vi+282 pages, $19.50
375 R.C.T. Lee - On machine intelligence: D. Michie. Halstead Press, a
376 division of John Wiley & Sons, 1974.
378 W.W. Bledsoe, Peter Bruell - A man-machine theorem-proving system
380 Gary G. Hendrix - Modeling simultaneous actions and continuous
381 processes
383 Yoshiaki Shirai - A context sensitive line finder for recognition of
384 polyhedra
386 Kenneth Mark Colby, Franklin Dennis Hilf, Sylvia Weber, Helena C
387 Kraemer - Turing-like indistinguishability tests for the validation of
388 a computer simulation of paranoid processes
390 Aaron Sloman - Interactions between philosophy and artificial
391 intelligence: The role of intuition and non-logical reasoning in
392 intelligence
394 * Story related
396 Charles B. Callaway, James C. Lester - Narrative prose generation
398 - Katja Markert, Udo Hahn :: Understanding metonymies in discourse
399 Metonymies are difficult enough to drive these people to use the
400 context of the sentences around the metonymy to interpret
401 it. They create a set of heuristics which interpret
402 metonomies. The first is obvious violations of sentence rules,
403 such as having a non-agent do something only an agent can do.
405 Another rule is that metonomyies should be more "apt", where it's
406 more likely for a T.V. Screen to refer to the T.V. than a small
407 button on the T.V., or a transistor.
409 Metonymies should be very difficult for current parsers to
410 understand, and are good examples, since they are short and
411 require context and common sense.
413 They have a dumb, ad-hoc "common sense database" that is
414 dissapointing. It contains subclasses and has-a relations.
416 References:
417 + D.A. Cruse, On the transitivity of the part-whole relation,
418 J. Linguistics 15 (1979) 29–38.
419 good quotes:
420 - We took the door off its hinges and went through it.
421 - The house has a handle.sources
424 Kathleen R. McKeown, Steven K. Feiner, Mukesh Dalal, Shih-Fu Chang -
425 Generating multimedia briefings: coordinating language and
426 illustration
428 Varol Akman - Formalizing common sense: Papers by John McCarthy:
429 V. Lifschitz, ed., (Ablex Publishing Corporation, Norwood, NJ, 1990);
430 vi+256 pages, hardback, ISBN 0-89391-535-1 (Library of Congress:
431 Q335.M38 1989)
433 Akira Shimaya - Interpreting non-3-D line drawings
435 Adam J. Grove - Naming and identity in epistemic logic part II: a
436 first-order logic for naming
438 Luc Lismont, Philippe Mongin - A non-minimal but very weak
439 axiomatization of common belief
441 on integration of natural language and vision processing
443 Russell Greiner - Learning by understanding analogies
445 * Review Articles
447 H.Jaap van den Herik, Jos W.H.M. Uiterwijk, Jack van Rijswijck - Games
448 solved: Now and in the future
450 Jonathan Schaeffer, H.Jaap van den Herik - Games, computers, and
451 artificial intelligence
453 Peter A. Flach - On the state of the art in machine learning: A
454 personal review
456 A.G. Cohn, D. Perlis - “Field Reviews”: A new style of review article
457 for Artificial Intelligence
459 James Delgrande, Arvind Gupta, Tim Van Allen - A comparison of
460 point-based approaches to qualitative temporal reasoning
462 Weixiong Zhang, Rina Dechter, Richard E. Korf - Heuristic search in
463 artificial intelligence
465 Karen Sparck Jones - Information retrieval and artificial intelligence
467 Wolfram Burgard, Armin B. Cremers, Dieter Fox, Dirk Hähnel, Gerhard
468 Lakemeyer, Dirk Schulz, Walter Steiner, Sebastian Thrun - Experiences
469 with an interactive museum tour-guide robot
471 Minoru Asada, Hiroaki Kitano, Itsuki Noda, Manuela Veloso - RoboCup:
472 Today and tomorrow—What we have learned
474 Margaret A. Boden - Creativity and artificial intelligence
476 Daniel G. Bobrow, J.Michael Brady - Artificial Intelligence 40 years
477 later
479 Fangzhen Lin, Hector J. Levesque - What robots can do: robot programs
480 and effective achievability
482 Melanie Mitchell - L.D. Davis, handbook of genetic algorithms
484 Russell Greiner, Adam J. Grove, Alexander Kogan - Knowing what doesn't
485 matter: exploiting the omission of irrelevant data
487 W. Whitney, S. Rana, J. Dzubera, K.E. Mathias - Evaluating
488 evolutionary algorithms
490 David S. Touretzky - Neural networks in artificial intelligence:
491 Matthew Zeidenberg
493 Mark J. Stefik, Stephen W. Smoliar - The commonsense reviews
495 Peter Szolovits, Stephen G. Pauker - Categorical and probabilistic
496 reasoning in medicine revisited
498 Daniel G. Bobrow - Artificial intelligence in perspective: a
499 retrospective on fifty volumes of the Artificial Intelligence Journal
501 David Kirsh - Foundations of AI: The big issues
503 Hector J. Levesque - All I know: A study in autoepistemic logic
505 J.T. Schwartz, M. Sharir - A survey of motion planning and related
506 geometric algorithms
508 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level
509 vision: A survey
511 Hans J. Berliner - A chronology of computer chess and its literature
513 John McCarthy - Artificial intelligence: a paper symposium: Professor
514 Sir James Lighthill, FRS. Artificial Intelligence: A General
515 Survey. In: Science Research Council, 1973
516 * Cortex related (sensory fusion / simulated worlds)
518 Alfonso Gerevini, Jochen Renz - Combining topological and size
519 information for spatial reasoning
521 John Slaney, Sylvie Thiébaux - Blocks World revisited
523 Wai K. Yeap, Margaret E. Jefferies - Computing a representation of the
524 local environment
526 R.P. Loui - On the origin of objects: B.C. Smith's MIT Press,
527 Cambridge, MA, 1996. $37.50 (cloth). $17.50 (paper). 440 pages. ISBN
528 0-262-69209-0
530 Tze Yun Leong - Multiple perspective dynamic decision making
532 Cristiano Castelfranchi - Modelling social action for AI agents
534 Luc Steels - The origins of syntax in visually grounded robotic agents
536 Sebastian Thrun - Learning metric-topological maps for indoor mobile
537 robot navigation
539 John Haugeland - Body and world: a review of What Computers Still
540 Can't Do: A critique of artificial reason (Hubert L. Dreyfus): (MIT
541 Press, Cambridge, MA, 1992); liii + 354 pages, $13.95
543 David J. Musliner, Edmund H. Durfee, Kang G. Shin - World modeling for
544 the dynamic construction of real-time control plans
546 Jozsef A. Toth - Reasoning agents in a dynamic world: The frame
547 problem: Kenneth M. Ford and Patrick J. Hayes, eds., (JAI Press,
548 Greenwich, CT, 1991); 290+xiv pages
550 Michael A. Arbib, Jim-Shih Liaw - Sensorimotor transformations in the
551 worlds of frogs and robots
553 Ingemar J. Cox, John J. Leonard - Modeling a dynamic environment using
554 a Bayesian multiple hypothesis approach
556 on integration of natural language and vision processing
558 Demetri Terzopoulos, Andrew Witkin, Michael Kass - Constraints on
559 deformable models:Recovering 3D shape and nonrigid motion
561 Bruce R. Donald - A search algorithm for motion planning with six
562 degrees of freedom
564 Yorick Wilks - Making preferences more active
566 * Vision Related
568 Azriel Rosenfeld - B. Jähne, H. Haussecker, and P. Geissler, eds.,
569 Handbook of Computer Vision and Applications. 1. Sensors and
570 Imaging. 2. Signal Processing and Pattern Recognition. 3. Systems and
571 Applications
573 Thomas F. Stahovich, Randall Davis, Howard Shrobe - Qualitative
574 rigid-body mechanics
576 Tzachi Dar, Leo Joskowicz, Ehud Rivlin - Understanding mechanical
577 motion: From images to behaviors
579 Minoru Asada, Eiji Uchibe, Koh Hosoda - Cooperative behavior
580 acquisition for mobile robots in dynamically changing real worlds via
581 vision-based reinforcement learning and development
583 Thomas F. Stahovich, Randall Davis, Howard Shrobe - Generating
584 multiple new designs from a sketch
586 Ernst D. Dickmanns - Vehicles capable of dynamic vision: a new breed
587 of technical beings?
589 Thomas G. Dietterich, Richard H. Lathrop, Tomás Lozano-Pérez - Solving
590 the multiple instance problem with axis-parallel rectangles
592 Rajesh P.N. Rao, Dana H. Ballard - An active vision architecture based
593 on iconic representations
595 John K. Tsotsos, Scan M. Culhane, Winky Yan Kei Wai, Yuzhong Lai, Neal
596 Davis, Fernando Nuflo - Modeling visual attention via selective tuning
598 Roger Mohr, Boubakeur Boufama, Pascal Brand - Understanding
599 positioning from multiple images
601 Andrew Zisserman, David Forsyth, Joseph Mundy, Charlie Rothwell, Jane
602 Liu, Nic Pillow - 3D object recognition using invariance
604 Naresh C. Gupta, Laveen N. Kanal - 3-D motion estimation from motion
605 field
607 Damian M. Lyons - Vision, instruction, and action: David Chapman, (MIT
608 Press Cambridge, MA, 1991); 295 pages, $35.00, (paperback)
610 Yoshinori Suganuma - Learning structures of visual patterns from
611 single instances
613 Dana H. Ballard - Animate vision
615 Raymond Reiter, Alan K. Mackworth - A logical framework for depiction
616 and image interpretation
618 Ellen Lowenfeld Walker, Martin Herman - Geometric reasoning for
619 constructing 3D scene descriptions from images
621 Michele Barry, David Cyrluk, Deepak Kapur, Joseph Mundy, Van-Duc
622 Nguyen - A multi-level geometric reasoning system for vision
624 Alex P. Pentland - Shading into texture
626 Brady - Parallelism in Vision
628 Jon A. Webb, J.K. Aggarwal - Structure from motion of rigid and
629 jointed objects
631 Michael Brady - Computer vision
633 Takeo Kanade - Recovery of the three-dimensional shape of an object
634 from a single view
636 Rodney A. Brooks - Symbolic reasoning among 3-D models and 2-D images
638 H.K. Nishihara - Intensity, visible-surface, and volumetric
639 representations
641 Thomas O. Binford - Inferring surfaces from images
643 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level
644 vision: A survey
646 - (1980) Berthold K.P. Horn, Brian G. Schunck - Determining optical
647 flow
649 Optical flow is an estimation of the movement of brightness
650 patterns. If the image is "smooth" then optical flow is also an
651 estimate of the movement of objects in the image (projected onto the
652 plane of the image). They get some fairly good results on some very
653 contrived examples. Important point is that calculating optical flow
654 involves a relaxation process where the velocities of regions of
655 constant brightness are inferred from the velocities of the edges of
656 those regions.
658 This paper is a lead up to Horn's book, Robot Vision.
660 Hexagonal sampling may be a good alternative to rectangular
661 sampling.
663 A reduced version of this algorithm is implemented in hardware in
664 optical mice to great effect.
666 + Hamming, R.W., Numerical Methods for Scientists and Engineers
667 (McGraw-Hill, New York, 1962).
668 + Limb, J.O. and Murphy, J.A., Estimating the velocity of moving
669 images in television signals, Computer Graphics and Image
670 Processing 4 (4) (1975) 311-327.
671 + Mersereau, R.M., The processing of hexagonally sampled
672 two-dimensional signals, Proc. of the IEEE 67 (6) (1979) 930-949.
675 - (1993) Berthold K.P. Horn, B.G. Schunck - “Determining optical flow”: a
676 retrospective
678 Very useful read where Horn criticies his previous paper.
680 - Whishes that he distinguished "optical flow" form "motion
681 field". "Optical flow" is an image property, whilc the "motion
682 field" is the movement of objects in 3D space. "Optical flow" is a
683 2D vector field; the "motion field" is 3D.
684 - Wished he made the limitations of his algorithm more clear.
685 - His original paper didn't concern itself with flow segmentation,
686 which is required to interpret real world images with objects and
687 a background.
688 - Thinks that the best thing about the original paper is that it
689 introduced variational calculus methods into computer vision.
691 References:
693 + R. Courant and D. Hilbert, Methods of Mathematical Physics
694 (Interscience, New York, 1937/1953).
695 + D. Mart, Vision (Freeman, San Francisco, CA, 1982).
696 + C.M. Thompson, Robust photo-topography by fusing
697 shape-from-shading and stereo,Ph.D. Thesis, Mechanical Engineering
698 Department, MIT, Cambridge, MA (1993).
699 + K. Ikeuchi and B.K.P. Horn, Numerical shape from shading and
700 occluding boundaries, Artif lntell. 17 (1981) 141-184.
702 Katsushi Ikeuchi, Berthold K.P. Horn - Numerical shape from shading
703 and occluding boundaries
705 Andrew P. Witkin - Recovering surface shape and orientation from
706 texture
708 Irwin Sobel - On calibrating computer controlled cameras for
709 perceiving 3-D scenes
711 P.M. Will, K.S. Pennington - Grid coding: A preprocessing technique
712 for robot and machine vision
714 M.B. Clowes - On seeing things
716 Claude R. Brice, Claude L. Fennema - Scene analysis using regions
718 * Cryo!
720 - (1999) Kenneth D. Forbus, Peter B. Whalley, John O. Everett, Leo
721 Ureel, Mike Brokowski, Julie Baher, Sven E. Kuehne - CyclePad: An
722 articulate virtual laboratory for engineering thermodynamics
724 Should learn about thermodynamics, and about "thermal cycles."
725 http://www.qrg.northwestern.edu/projects/NSF/cyclepad/cyclepad.htm
727 This system is more about expressing models and assumtions than
728 automatically generating them, and as such is similiar to our "math
729 language" idea.
731 It's like a simple circuit modeller, and similar to Dylan's idea of
732 an online circuit modeler.
734 #+begin_quote
735 We found that if CyclePad did not do the “obvious” propagation in
736 preference to interpolation, students trusted it less.
737 #+end_quote
739 It's too bad that the paper doesn't mention the shortcommings of the
740 system.
742 + J.O. Everett, Topological inference of teleology: Deriving
743 function from structure via evidential reasoning, Artificial
744 Intelligence 113 (1999) 149–202.
745 + P. Hayes, Naive physics 1: Ontology for liquids, in: J. Hobbs,
746 R. Moore (Eds.), Formal Theories of the Commonsense World, Ablex,
747 Norwood, NJ, 1985.
748 + P. Nayak, Automated modeling of physical systems, Ph.D. Thesis,
749 Computer Science Department, Stanford University, 1992.
750 + R.W. Haywood, Analysis of Engineering Cycles: Power, Refrigerating
751 and Gas Liquefaction Plant, Pergamon Press, 1985.
752 + R.M. Stallman, G.J. Sussman, Forward reasoning and
753 dependency-directed backtracking in a system for computer-aided
754 circuit analysis, Artificial Intelligence 9 (1977) 135–196.
755 + Dylan should read this, since it concerns his online circuit
756 analysis idea.