Learn More
In real-world applications of visual recognition, many factors - such as pose, illumination, or image quality - can cause a significant mismatch between the source domain on which classifiers are trained and the target domain to which those classifiers are applied. As such, the classifiers often perform poorly on the target domain. Domain adaptation(More)
We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct classifiers with them. We propose a novel approach that jointly learn the both. Specifically, while the method identifies a(More)
We propose a new approach for metric learning by framing it as learning a sparse combination of locally discriminative metrics that are inexpensive to generate from the training data. This flexible framework allows us to naturally derive formulations for global, multi-task and local metric learning. The resulting algorithms have several advantages over(More)
The aim of this study was to exploit the possibility of combination of active targeting function of folic acid by folate receptor-mediated endocytosis and overcoming multidrug resistance (MDR) by Pluronic block copolymers to promote drug delivery to MDR tumor following intravenous administration with paclitaxel (PTX) as model drug. Folic acid functionalized(More)
Despite progress in the diagnostics and treatment of hepatocellular carcinoma (HCC), its prognosis remains poor. In this study, we globally assessed long noncoding RNAs (lncRNA) for contributions to HCC using publicly available microarray data, in vitro and in vivo assays. Here, we report that ZFAS1, encoding a lncRNA that is frequently amplified in HCC, is(More)
The aim of this work was to demonstrate the advantage of using paclitaxel (PTX)-loaded Pluronic P123/F127 mixed micelles (PF-PTX) against non-small cell lung cancer (NSCLC) compared to Taxol. Modulation of multidrug resistance (MDR) by Pluronic mixed micelles was evaluated in lung resistance protein (LRP)-overexpressing human lung adenocarcinoma A-549 cell(More)
Overlapped fingerprints are frequently encountered in latent fingerprints lifted from crime scenes. It is necessary to separate such overlapped fingerprints into component fingerprints so that existing fingerprint matchers can recognize them. The most crucial step in separating overlapped fingerprints is estimation of component orientation fields, which is(More)
An efficient decentralized algorithm for synchronized termination of a distributed computation is presented. It is assumed that distributed processes are connected via unidirectional channels into a strongly connected network, in which no central controller exists. The number of processes and the network configuration are not known a priori. The number of(More)
Inductive transfer learning and semi-supervised learning are two different branches of machine learning. The former tries to reuse knowledge in labeled out-of-domain instances while the later attempts to exploit the usefulness of unlabeled in-domain instances. In this paper, we bridge the two branches by pointing out that many semi-supervised learning(More)
An efficient algorithm for synchronized termination of iterative solution of simultaneous equations in a distributed message passing system is presented. The algorithm is based on an assumption that distributed processors are connected via unidirectional channels into a strongly connected network, in which no central controller exists. The number of(More)