Specific-to-General Learning for Temporal Events with Application to Learning Event Definitions from Video

We develop, analyze, and evaluate a novel, supervised, specific-to-general learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions from video sequences. First, we introduce a simple, propositional, temporal, event-description language called AMA that is sufficiently expressive to represent many events yet sufficiently restrictive to support learning. We then give algorithms, along with lower and upper complexity bounds, for the subsumption and generalization problems for AMA formulas. We present a positive-examples-only specific-to-general learning method based on these algorithms. We also present a polynomial-time-computable "syntactic" subsumption test that implies semantic subsumption without being equivalent to it. A generalization algorithm based on syntactic subsumption can be used in place of semantic generalization to improve the asymptotic complexity of the resulting learning algorithm. Finally, we apply this algorithm to the task of learning relational event definitions from video and show that it yields definitions that are competitive with hand-coded ones.

[1]  William W. Cohen.  Grammatically Biased Learning: Learning Logic Programs Using an Explicit Antecedent Description Language , 1994, Artif. Intell..

[2]  Ada Wai-Chee Fu,et al.  Discovering Temporal Patterns for Interval-Based Events , 2000, DaWaK.

[3]  William W. Cohen,et al.  Learning the Classic Description Logic: Theoretical and Experimental Results , 1994, KR.

[4]  Frank Höppner.  Discovery of Temporal Patterns. Learning Rules about the Qualitative Behaviour of Time Series , 2001, PKDD.

[5]  Aaron F. Bobick,et al.  Action recognition using probabilistic parsing , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[6]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Paul R. Cohen,et al.  Fluent Learning: Elucidating the Structure of Episodes , 2001, IDA.

[8]  Matthew Brand,et al.  The "Inverse Hollywood Problem": From Video to Scripts and Storyboards via Causal Analysis , 1997, AAAI/IAAI.

[9]  Allan D. Jepson,et al.  Towards the computational perception of action , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[10]  Jeffrey Mark Siskind,et al.  Visual Event Classification via Force Dynamics , 2000, AAAI/IAAI.

[11]  Dan Roth,et al.  Relational Learning via Propositional Algorithms: An Information Extraction Case Study , 2001, IJCAI.

[12]  G. Plotkin.  Automatic Methods of Inductive Inference , 1972 .

[13]  Stephen Muggleton,et al.  Efficient Induction of Logic Programs , 1990, ALT.

[14]  Heikki Mannila,et al.  Discovering Frequent Episodes in Sequences , 1995, KDD.

[15]  Yoav Shoham,et al.  Temporal Logics in AI: Semantical and Ontological Considerations , 1987, Artif. Intell..

[16]  Jeffrey Mark Siskind,et al.  A Maximum-Likelihood Approach to Visual Event Classification , 1996, ECCV.

[17]  Katharina Morik,et al.  Learning Concepts from Sensor Data of a Mobile Robot , 2005, Machine Learning.

[18]  Gary C. Borchardt,et al.  Event Calculus , 1985, IJCAI.

[19]  Matthew Brand,et al.  Physics-Based Visual Understanding , 1997, Comput. Vis. Image Underst..

[20]  A. U.S..  Causal Analysis for Visual Gesture Understanding , 1995 .

[21]  Luc De Raedt,et al.  Clausal Discovery , 1997, Machine Learning.

[22]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[23]  Terrance Philip Regier,et al.  The acquisition of lexical semantics for spatial terms: a connectionist model of perceptual categorization , 1992 .

[24]  Eduardo F. Morales,et al.  PAL: A Pattern-Based First-Order Inductive System , 1997, Machine Learning.

[25]  Barak A. Pearlmutter,et al.  Results of the Abbadingo One DFA Learning Competition and a New Evidence-Driven State Merging Algorithm , 1998, ICGI.

[26]  Jeffrey Mark Siskind,et al.  Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic , 1999, J. Artif. Intell. Res..

[27]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[28]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[29]  Ramakrishnan Srikant,et al.  Mining sequential patterns , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[30]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[31]  Stephen Muggleton.  Inverting Entailment and Progol , 1993, Machine Intelligence 14.

[32]  Saso Dzeroski,et al.  Learning Nonrecursive Definitions of Relations with LINUS , 1991, EWSL.

[33]  Luc De Raedt,et al.  DLAB: A Declarative Language Bias Formalism , 1996, ISMIS.

[34]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[35]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[36]  Volker Klingspor,et al.  Learning concepts from sensor data of a mobile robot , 1996, Machine Learning.

[37]  Fahiem Bacchus,et al.  Using temporal logics to express search control knowledge for planning , 2000, Artif. Intell..

[38]  Leonard Talmy,et al.  Force Dynamics in Language and Cognition , 1987, Cogn. Sci..