This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
We present metrics to evaluate the performance of video object segmentation and tracking methods quantitatively when groundtruth segmentation maps are not available. The proposed ...
We describe a technique for video summarization that uses motion descriptors computed in the compressed domain to speed up conventional color based video summarization technique. ...
A linkage is a collection of line segments, called bars, possibly joined at their ends, called joints. Straightening a tree linkage is a continuous motion of their bars from an ini...
This paper studies automatic segmentation of multiple
motions from tracked feature points through spectral embedding
and clustering of linear subspaces. We show that
the dimensi...