Ruohui Wang

Learn More
—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(More)
In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint(More)
An intrinsic Fabry-Perot interferometeric sensor based on a microfiber has been demonstrated. The micro-size suspended core is created by chemical etching a photonics crystal fiber, of which the cladding has a micrometer-spaced, hexagonal array of air holes. The sensing head is fabricated by chemical etching a short section of photonics crystal fiber(More)
  • 1