SPS Feed

Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as single image super-resolution. Contrary to other multi-layer dictionary models, our architecture contains L layers of analysis dictionary and soft-thresholding operators to gradually extract high-level features and a layer of synthesis dictionary which is designed to optimize the regression task at hand.

Decentralized detection is one of the key tasks that a wireless sensor network (WSN) is faced to accomplish. Among several decision criteria, the Rao test is able to cope with an unknown (but parametrically-specified) sensing model, while keeping computational simplicity. To this end, the Rao test is employed in this paper to fuse multivariate data measured by a set of sensor nodes, each observing the target (or the desired) event via a nonlinear mapping function. 

Recently, saliency detection in a single image and co-saliency detection in multiple images have drawn extensive research interest in the vision and multimedia communities. In this paper, we investigate a new problem of co-saliency detection within a single image, i.e., detecting within-image co-saliency . By identifying common saliency within an image, e.g., highlighting multiple occurrences of an object class with similar appearance, this work can benefit many important applications, such as the detection of objects of interest, more robust object recognition, reduction of information redundancy, and animation synthesis. We propose a new bottom-up method to address this problem.

We propose a new blind watermarking algorithm for 3D printed objects that has applications in metadata embedding, robotic grasping, counterfeit prevention, and crime investigation. Our method can be used on fused deposition modeling (FDM) 3D printers and works by modifying the printed layer thickness on small patches of the surface of an object. These patches can be applied to multiple regions of the object, thereby making it resistant to various attacks such as cropping, local deformation, local surface degradation, or printing errors. 

The existing neural architecture search (NAS) methods usually restrict the search space to the pre-defined types of block for a fixed macro-architecture. However, this strategy will limit the search space and affect architecture flexibility if block proposal search (BPS) is not considered for NAS. As a result, block structure search is the bottleneck in many previous NAS works. In this work, we propose a new evolutionary algorithm referred to as latency EvoNAS (LEvoNAS) for block structure search, and also incorporate it to the NAS framework by developing a novel two-stage framework referred to as Block Proposal NAS (BP-NAS). 

In this study, we propose a neural network-based face anti-spoofing algorithm using dual pixel (DP) sensor images. The proposed algorithm has two stages: depth reconstruction and depth classification. The first network takes a DP image pair as input and generates a depth map with a baseline of approximately 1 mm. Then, the classification network is trained to distinguish real individuals and planar attack shapes to produce a binary output.

Recently, deep-learning based methods have been widely used for computed tomography (CT) reconstruction. However, most of these methods need extra steps to convert the sinogrmas into CT images and so their networks are not end-to-end. In this paper, we propose an end-to-end deep network for CT image reconstruction, which directly maps sparse sinogramss to CT images. Our network has three cascaded blocks, where the first block is used to denoise and interpolate the sinograms, the second to map the sinograms to CT images and the last to denoise the CT images.

One practical requirement of the music copyright management is the estimation of music relative loudness, which is mostly ignored in existing music detection works. To solve this problem, we study the joint task of music detection and music relative loudness estimation. To be specific, we observe that the joint task has two characteristics, i.e., temporality and hierarchy, which could facilitate to obtain the solution. For example, a tiny fragment of audio is temporally related to its neighbor fragments because they may all belong to the same event, and the event classes of the fragment in the two tasks have a hierarchical relationship. Based on the above observation, we reformulate the joint task as hierarchical event detection and localization problem. To solve this problem, we further propose Hierarchical Regulated Iterative Networks (HRIN), which includes two variants, termed as HRIN-r and HRIN-cr, which are based on recurrent and convolutional recurrent modules.