This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
This paper presents a plan-based model of dialogue that combines world, linguistic, and contextual knowledge in order to recognize complex communicative actions such as expressing...
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
Contextual information is important for sequence modeling. Hidden Markov Models (HMMs) and extensions, which have been widely used for sequence modeling, make simplifying, often u...
IAPR Workshop on Machine Vision and Applications, pp. 455-458, 2000, Tokyo, Japan In this paper, we integrate the model-based tracking and local contexture (temporal and spatial) ...