Learn More
Figure 1: The one-way procedure from localization to template alignment makes each module rely on results from the previous one. Contrarily, back-propagation highlighted by dashed arrow makes it possible to refine localization according to the classification and alignment results. It forms a bi-directional refinement process. Fine-grained object recognition(More)
Images now come in different forms – color, near-infrared, depth, etc. – due to the development of special and powerful cameras in computer vision and computational photography. Their cross-modal correspondence establishment is however left behind. We address this challenging dense matching problem considering structure variation possibly existing in these(More)
Color, infrared, and flash images captured in different fields can be employed to effectively eliminate noise and other visual artifacts. We propose a two-image restoration framework considering input images in different fields, for example, one noisy color image and one dark-flashed near-infrared image. The major issue in such a framework is to handle(More)
Antisense oligonucleotide (AO)-mediated exon-skipping therapeutics shows great promise for Duchenne muscular dystrophy (DMD) patients. However, recent failure with drisapersen, an AO candidate drug in phase 3 trial, highlights the importance of exploring other effective AO chemistries for DMD. Previously, we demonstrated the appreciable biological activity(More)
Color, infrared and flash images captured in different fields can be employed to effectively eliminate noise and other visual artifacts. We propose a two-image restoration framework considering input images from different fields, for example, one noisy color image and one dark-flashed near-infrared image. The major issue in such a framework is to handle all(More)