Object class segmentation (OCS) is a key issue in semantic scene labeling and understanding. Its general principle consists of naming object entities into scenes according to thei...
Supervised learners can be used to automatically classify many types of spatially distributed data. For example, land cover classification by hyperspectral image data analysis is ...
The paper describes a new approach using a Conditional Random Fields (CRFs) to extract physical and logical layouts in unconstrained handwritten letters such as those sent by indi...
This paper presents a header compression algorithm that unlike previous protocols is capable of compressing MAC headers in a multiple-access (shared) channel. Previous schemes coul...
We consider a semi-supervised regression setting where we have temporal sequences of partially labeled data, under the assumption that the labels should vary slowly along a sequen...
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
Prior use of machine learning in genre classification used a list of labels as classification categories. However, genre classes are often organised into hierarchies, e.g., coveri...
— In the last decade, graph-cut optimization has been popular for a variety of labeling problems. Typically graph-cut methods are used to incorporate smoothness constraints on a ...
—Networks based on Ethernet bridging scale poorly as bridges flood the entire network repeatedly, and several schemes have been proposed to mitigate this flooding problem; howe...
Dhananjay Sampath, Suchit Agarwal, J. J. Garcia-Lu...
In this work, we investigate how to propagate annotated labels for a given single image from the image-level to their corresponding semantic regions, namely Label-toRegion (L2R), ...