Learn More
The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth, and/or power are limited. The summarization process inevitably introduces(More)
Recently, hashing based Approximate Nearest Neighbor (ANN) techniques have been attracting lots of attention in computer vision. The data-dependent hashing methods, e.g., Spectral Hashing, expects better performance than the data-blind counterparts, e.g., Locality Sensitive Hash-ing (LSH). However, most data-dependent hashing methods only employ a single(More)
Septins are conserved guanosine triphosphate-binding cytoskeletal proteins involved in membrane remodeling. In budding yeast, five mitotic septins (Cdc3, Cdc10, Cdc11, Cdc12, and Shs1), which are essential for cytokinesis, transition during bud growth from a patch to a collar, which splits into two rings in cytokinesis and is disassembled before the next(More)
The serine/threonine phosphatase protein phosphatase 2A (PP2A) plays an essential role in many aspects of cellular functions and has been shown to be an important tumor suppressor. The core enzyme of PP2A comprises a 65 kDa scaffolding subunit and a 36 kDa catalytic subunit. Here we report the crystal structures of the PP2A core enzyme bound to two of its(More)
—The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX(More)
—The need to quickly and accurately classify Internet traffic for security and QoS control has been increasing significantly with the growing Internet traffic and applications over the past decade. Pattern recognition by learning the features in the training samples to classify the unknown flows is one of the main methods. However, many methods developed in(More)
Head pose appearances under the pan and tilt variations span a high dimensional manifold that has complex structures and local variations. For pose estimation purpose, we need to discover the subspace structure of the manifold and learn discriminative subspaces/metrics for head pose recognition. The performance of the head pose estimation is heavily(More)
V ideo copy-detection, the purpose of which is to find a video copy in a repository, is important for many applications. 1-3 Our research focuses on locating video clips that are copied but maintain frame correspondence. Although this issue has been investigated for several years in multimedia research, efficient and scalable copy-detection is still a(More)