The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet [1] and VGG [2], novel object detection frameworks such as R-CNN [3] and its successors, Fast R-CNN [4] and Faster R-CNN [5], play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this work, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing stillimage detection frameworks when they are applied to videos. It is called T-CNN, i.e. tubelets with convolutional neueral networks. The proposed framework won newly introduced object-detectionfrom-video (VID) task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC 2015). Code is publicly available at https://github.com/myfavouritekk/T-CNN.

No abstract

No abstract

A novel reflective refractometer based on a thin-core fiber (TCF) sandwiched between a leading single-mode fiber (SMF) and a fiber Bragg grating (FBG) imprinted SMF stub was demonstrated. The reflection from the fiber stub occurs in two well-defined wavelength bands, corresponding to the Bragg core mode and cladding modes. The TCF section functions as a tailorable bridge between the FBG core mode reflection and the surrounding refractive index (SRI). Linear response with enhanced sensitivity of 133.26 dB/refractive index unit for temperature-immune SRI measurement within the biologically desirable sensing range of 1.33-1.41 has been achieved via cost-effective power detection.

No abstract