Some recent papers by Matthew Brand

Coupled hidden Markov models for modeling interacting processes

Under review.

The ``Inverse Hollywood Problem'': From video to scripts and storyboards via causal analysis

Proceedings, AAAI 1997.

Coupled hidden Markov models for complex action recognition

with Nuria Oliver, Sandy Pentland. Proceedings, CVPR 1997.

Discovering and visualizing narrative themes

To appear, Proceedings, Visual 1997.

A fast greedy pairwise clustering algorithm and its use in finding thematic structure in large datasets

Draft under review.

Convergence properties of generalized Fibonacci sequences

Under review -- email me for a copy

Extracting Action Content from Image Streams

Draft under review (workshop paper summarizing some other papers).

Understanding Manipulation in Video

Proceedings, 2nd International Conference on Face and Gesture Recognition, Killington, VT, 1996.

Physics-based visual understanding

Computer Vision and Image Understanding, special issue on "Physics-based modelling and reasoning in computer vision", Vol. 65, No. 2, February 1997.

Transforming problems into imagery and solving them via visual computations

Proceedings, Conference of the Cognitive Science Society, San Diego, 1996.

Causal analysis for visual gesture understanding

(with I. Essa)Proceedings, AAAI Fall Symposium on Vision and Language, Cambridge, 1995.

Seeing physics, or: Physics is for prediction

(with P. Cooper, L. Birnbaum) Proceedings, Workshop on Physics-based Vision, International Conference on Computer Vision, Cambridge, 1995.

A knowledge framework for seeing and learning

(with P. Cooper). Invited submission, Visual Learning, Volume 2: Symbolic Visual Learning, Katsushi Ikeuchi and Manuela Veloso, eds. Oxford University Press, 1995.

Causal scene understanding

(with P. Cooper, L. Birnbaum) CVGIP-Image Understanding, special issue on "Functionality in object recognition", 1995.

Explanation-mediated vision: Making sense of the world with causal analysis

PhD dissertation, The Institute for the Learning Sciences, Northwestern University, 1994.

Divided we fall: Resolving occlusions using causal reasoning

(with P. Cooper, L. Birnbaum, D. Halabe, P. Prokopowicz) Proceedings, Third European Conference on Computer Vision, ECCV94 and J. Eklundh (ed.) Lecture Notes in Computer Science, Springer-Verlag, 1994.

On the hypothesis that automata could be animals: A review of From animals to animats

(with P. Prokopowicz, C. Elliott) Artificial Intelligence, 73, 2, 1995.

Sensible scenes: Visual understanding of complex structures through causal analysis

(with L. Birnbaum, P. Cooper) Proceedings, National Conference on Artificial Intelligence, Washington D.C., 1993.

A short note on local region growing by pseudophysical simulation

Proceedings, IEEE-CS National Conference on Computer Vision and Pattern Recognition, New York, 1993.

Looking for trouble: Using causal semantics to direct focus of attention

(with L. Birnbaum and P. Cooper) Proceedings, International Conference on Computer Vision, Berlin, 1993. (A slightly extended version appeared in proceedings of the IEEE Workshop on Qualitative Vision, 1993).