We introduce a new algorithm for video retargeting that uses discontinuous seam-carving in both space and time for resizing videos. Our algorithm relies on a novel appearance-base...
Matthias Grundmann, Vivek Kwatra, Mei Han, Irfan E...
Abstract. We propose a fully automatic framework to detect and extract arbitrary human motion volumes from real-world videos collected from YouTube. Our system is composed of two s...
Juan Carlos Niebles, Bohyung Han, Andras Ferencz, ...
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and...
Siome Goldenstein, Christian Vogler, Dimitris N. M...
Abstract— Inter frame prediction technique significantly improves the compression efficiency in the hybrid video coding schemes. However, this technique causes the decoding dep...
Xiaopeng Fan, Oscar C. Au, Yan Chen, Jiantao Zhou,...
Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated ...