Yu-Ting Su

Learn More
New variants of the influenza A(H1N1)pdm09 and A(H3N2) viruses were detected in Taiwan between 2012 and 2013. Some of these variants were not detected in clinical specimens using a common real-time reverse transcription-PCR (RT-PCR) assay that targeted the conserved regions of the viral matrix (M) genes. An analysis of the M gene sequences of the new(More)
A novel avian influenza A (H7N9) virus causes severe human infections and was first identified in March 2013 in China. The H7N9 virus has exhibited two epidemiological peaks of infection, occurring in week 15 of 2013 and week 5 of 2014. Taiwan, which is geographically adjacent to China, faces a large risk of being affected by this virus. Through extensive(More)
Discovering visual dynamics during human actions is a challenging task for human action recognition. To deal with this problem, we theoretically propose the multi-task conditional random fields model and explore its application on human action recognition. For visual representation, we propose the part-induced spatiotemporal action unit sequence to(More)
This paper originally proposes the clique-graph and further presents a clique-graph matching method by preserving global and local structures. Especially, we formulate the objective function of clique-graph matching with respective to two latent variables, the clique information in the original graph and the pairwise clique correspondence constrained by the(More)
Background noise is a significant factor influencing the performance of speech perception. Previous studies showed that the temporal fine structure (TFS) plays an important role in speech perception for normal hearing (NH) and hearing loss individuals. The frequency amplitude modulation encoding (FAME) is a successful approach to enhance the TFS information(More)
View-based 3-D model retrieval is one of the most important techniques in numerous applications of computer vision. While many methods have been proposed in recent years, to the best of our knowledge, there is no benchmark to evaluate the state-of-the-art methods. To tackle this problem, we systematically investigate and evaluate the related methods by: 1)(More)
Attributes are expected to narrow down the semantic gap between low-level visual features and high-level semantic meanings. Such superiority motivates us to explore pedestrian attributes which has became a critical problem to boost image understanding and improve the performance of pedestrian detection, retrieval, re-identification, etc. Based on the PETA(More)
The Internet has changed from an information tool to a social tool. More and more people use social networking sites such as Facebook to build and maintain numerous interpersonal relationships. The benefits of online social interaction can be manifested in bridging and bonding social capital. This study examined how the four dimensions of perceived(More)
We designed a special course based on Service Learning theory to train the undergraduate students to teach the elderly people in community college to learn using smartphones for health. A 2-credit course was designed, composed of lecture & discussion and community service. 20 undergrduate stundents from university and 26 seniors from community college(More)
  • 1