Learn More
The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work. Existing solutions to this problems largely rely on hand-craft features and vanishing lines, and they often fail in highly cluttered indoor rooms. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages:(More)
In this work, we propose an Expert Decision Fusion (EDF) system to tackle the large-scale indoor/outdoor image classification problem using two key ideas, namely, data grouping and decision stacking. By data grouping, we partition the entire data space into multiple disjoint sub-spaces so that a more accurate prediction model can be trained in each(More)
This paper presents a circular piezoelectric unimorph with the edge clamped for the use of ultrasound transducer engineering. The unimorph consists of one PZT layer and one elastic layer, and the diameter of the PZT layer is a crucial factor on its performance. By modeling and analyzing the flexural motions with first order lamination theory, the lateral(More)
An approach that extracts global attributes from outdoor images to facilitate geometric layout labeling is investigated in this work. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. First, by following a classical method, we use local features to provide initial labels for all super-pixels.(More)
In this work, we propose a technique that utilizes a fully convolutional network (FCN) to localize image splicing attacks. We first evaluated a single-task FCN (SFCN) trained only on the surface label. Although the SFCN is shown to provide superior performance over existing methods, it still provides a coarse localization output in certain cases. Therefore,(More)
Object proposal generation has been an important preprocessing step for object detectors in general and the convolutional neural network (CNN) detectors in particular. Recently, people start to use the CNN to generate object proposals but most of these methods suffer from the localization bias problem, like other objectness-based methods. Since contours(More)
Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems. However, all tags are treated as equally important in these systems, which may result in misalignment between visual and textual modalities during MIR training. This(More)
A kind of high redundancy control system of snake robot is investigated by studying the redundancy control and combining the mechanism of annelid's nervous system with circulation system. The system consists of a three-tier communication bus and a variable information channel structure. As some local damage exists, the communication system rebuilds the(More)
  • 1