Jeffrey Mark Siskind

Learn More
This paper presents an implemented system for recognizing the occurrence of events described by simple spatial-motion verbs in short image sequences. The semantics of these verbs is specified with event-logic expressions that describe changes in the state of force-dynamic relations between the participants of the event. An efficient finite representation is(More)
This paper proposes a new cost function, cut ratio, for segmenting images using graph-based methods. The cut ratio is defined as the ratio of the corresponding sums of two different weights of edges along the cut boundary and models the mean affinity between the segments separated by the boundary per unit boundary length. This new cost function allows the(More)
We present ratio contour, a novel graph-based method for extracting salient closed boundaries from noisy images. This method operates on a set of boundary fragments that are produced by edge detection. Boundary extraction identifies a subset of these fragments and connects them sequentially to form a closed boundary with the largest saliency. We encode the(More)
Recognizing human activities in partially observed videos is a challenging problem and has many practical applications. When the unobserved subsequence is at the end of the video, the problem is reduced to activity prediction from unfinished activity streaming, which has been studied by many researchers. However, in the general case, an unobserved(More)
We present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it. Action class is rendered as a verb, participant objects as noun phrases, properties of those objects as adjectival modifiers in those noun phrases, spatial relations between those participants as prepositional phrases, and characteristics(More)
We have implemented a comprehensive constraint-based programming language as an extension to Common Lisp. This constraint package provides a uniied framework for solving both numeric and non-numeric systems of constraints using a combination of local propagation techniques including binding propagation, Boolean constraint propagation, generalized forward(More)
We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of ‘mean cut’ cost functions. Minimizing these cost functions corresponds to finding a cut with minimummean edge weight in a connected planar graph. This approach has several advantages over prior approaches to image segmentation. First, it allows cuts with(More)
Nondeterministic Lisp is a simple extension of Lisp which provides automatic backtracking Nondeterminism allows concise description of many search tasks which form the basis of much AI research This paper discusses Screamer an e cient im plementation of nondeterministic Lisp as a fully portable extension ofCommon Lisp In this paper we present the basic(More)