Roman Norris (coalbody2)

5% higher than that of Region Proposal Network (RPN), surpassing all the existing region proposal approaches. We also integrate SC-RPN into Fast R-CNN and Faster R-CNN to test its effectiveness on object detection task, the experimental results achieve a gain of 3.2% and 3.8% in terms of mAP compared to the original ones.Human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) studies conduct their saliency predictions via a multitask methodology in which pixelwise saliency regression and segmentation-like saliency refinement are conducted simultaneously. However, this multitask methodology has one critical limitation the semantic information embedded in feature backbones might be degenerated during the training process. Our visual attention is determined mainly by semantic information, which is evidenced by our tendency to pay more attention to semantically salient regions even if these regions are not the most perceptually salient at first glance. This fact clearly contradicts the widely used multitask methodology mentioned above. To address this issue, this paper divides the SOD problem into two sequential steps. First, we devise a lightweight, weakly supervised deep network to coarsely locate the semantically salient regions. Next, as a postprocessing refinement, we selectively fuse multiple off-the-shelf deep models on the semantically salient regions identified by the previous step to formulate a pixelwise saliency map. Compared with the state-of-the-art (SOTA) models that focus on learning the pixelwise saliency in single images using only perceptual clues, our method aims at investigating the object-level semantic ranks between multiple images, of which the methodology is more consistent with the human attention mechanism. Our method is simple yet effective, and it is the first attempt to consider salient object detection as mainly an object-level semantic reranking problem.This paper describes a high-resolution 3D navigation and tracking system using magnetic field gradients, that can replace X-Ray fluoroscopy in high-precision surgeries. Monotonically varying magnetic fields in X, Y and Z directions are created in the field-of-view (FOV) to produce magnetic field gradients, which encode each spatial point uniquely. Highly miniaturized, wireless and battery-less devices, capable of measuring their local magnetic field, are designed to sense the gradient field. One such device can be attached to an implant inside the body and another to a surgical tool, such that both can simultaneously measure and communicate the magnetic field at their respective locations to an external receiver. The relative location of the two devices on a real-time display can enable precise surgical navigation without using X-Rays. A prototype device is designed consisting of a micro-chip fabricated in 65nm CMOS technology, a 3D magnetic sensor and an inductor-coil. Planar electromagnetic coils are designed for creating the 3D magnetic field gradients in a 20x20x10cm3 of scalable FOV. Unambiguous and orientation-independent spatial encoding is achieved by (i) using the gradient in the total field magnitude instead of only the Z-component; and (ii) using a combination of the gradient fields to correct for the non-linearity and non-monotonicity in X and Y gradients. The resultant X and Y FOV yield ≥90% utilization of their respective coil-span. The system is tested in vitro to demonstrate a localization accuracy of less then 100μm in 3D, the highest reported to the best of our knowledge.Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net con