of both the object and the scene, nonrigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher-level applications that require the location and/or shape of the object in every frame. Typically, assumptions are made

, which includes level of description, transitions among expression, eliciting conditions, reliability and validity of training and test data, individual differences in subjects, head orientation and scene complexity, image characteristics, and relation to non-verbal behavior. We then present the CMU

This paper presents an automatic method of creating surface models at several levels of detail from an original polygonal description of a given object. Representing models at various levels of detail is important for achieving high frame rates in interactive graphics applications and also

to generate scene-level descriptions. Finally, we investigate how tag quality can be characterized and potential methods to improve it.

-based Kalman filtering algorithm. We compare the performance of the two approaches by analyzing their theoretical convergence rates, by conducting quantitative experiments with images of a flat poster, and by conducting qualitative experiments with images of a realistic outdoor-scene model. The results show

could be resolved to a large extent. The video is segmented to meaningful entities or scenes, using the scene level descriptions provided by the commentary. These segments can then be automatically annotated with the respective descriptions. This allows for a semantic access and retrieval of video

Boundary detection is a fundamental problem in computer vision. However, bound-ary detection is difficult as it involves integrating multiple cues (intensity, color, texture) as well as trying to incorporate object class or scene level descriptions to mitigate the am-biguity of the local signal

Boundary detection is a fundamental problem in computer vision. However, bound-ary detection is difficult as it involves integrating multiple cues (intensity, color, texture) as well as trying to incorporate object class or scene level descriptions to mitigate the am-biguity of the local signal

We present a new method for representating the state spaces of hierarchical level of detail descriptions, or scene descriptions with multiple hierarchical levels of detail. This representation, called a level of detail graph, permits the investigation and exploration of the state spaces of non

We examine the possible use of Description Logics as a knowledge representation and reasoning system for high-level scene interpretation. It is shown that aggregates composed of multiple parts and constrained primarily by temporal and spatial relations can be used to represent high-level concepts