-
Article
Generalized Gradient Flow Based Saliency for Pruning Deep Convolutional Neural Networks
Model filter pruning has shown efficiency in compressing deep convolutional neural networks by removing unimportant filters without sacrificing the performance. However, most existing criteria are empirical, a...
-
Article
Open AccessIdentification and validation of novel prognostic signatures based on m5C methylation patterns and tumor EMT profiles in head and neck squamous cell carcinoma
The role of 5-methylcytosine (m5C) in tumor initiation and progression has been increasingly recognized. However, the precise association between the regulation of m5C and the progression, metastasis, and prog...
-
Article
A Strip Dilated Convolutional Network for Semantic Segmentation
There are frequently a large number of strip objects in segmentation scenarios, and the use of conventional square convolution may yield redundant information. Based on our previously proposed SA-FFNet (Zhou e...
-
Article
Adversarial learning based intermediate feature refinement for semantic segmentation
Image semantic segmentation is a meaningful task that requires both accuracy and efficiency in computer vision. At present, most current deep learning based semantic segmentation methods needs extensive comput...
-
Article
Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation
Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal network structure that can run...
-
Article
Polymerization mechanism of polyferric aluminum phosphatic sulfate (PFAPS) and its flocculation effect on simulated dye wastewater
Inorganic polymer flocculants play an important role in water treatment. The copolymerization of Al3+ and Fe3+ in proportion can prepare polyferric aluminum (PFA), which can improve the flocculation performance o...
-
Chapter and Conference Paper
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, lottery ticket hypothesis has shown that DNNs contai...
-
Chapter and Conference Paper
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks...
-
Chapter and Conference Paper
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB map** problem, wher...
-
Chapter and Conference Paper
UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Dis...
-
Chapter and Conference Paper
Real Image Super Resolution via Heterogeneous Model Ensemble Using GP-NAS
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image super-resolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections. W...
-
Chapter and Conference Paper
Description and Findings of OPPO’s Machine Translation Systems for CCMT 2020
This paper demonstrates our machine translation systems for the CCMT 2020, which is composed of four parts. The last three parts report our results in the contest, each respectively focuses on English-Chinese ...
-
Chapter and Conference Paper
Joint Demosaicking and Denoising for CFA and MSFA Images Using a Mosaic-Adaptive Dense Residual Network
Color filter array (CFA) has been a basis for modern photography and recently multispectral filter array (MSFA) has gradually found its wide application. A deep learning network capable of joint demosaicking a...
-
Article
Enhanced thermoelectric performance of bismuth-doped magnesium silicide synthesized under high pressure
Polycrystalline Mg2Si1−xBi x compounds were prepared with high-pressure synthesis followed by spark plasma sintering. The structural and compositional analyses indicate a domina...
-
Article
Hot deformation behaviour and processing maps of AA6061-10 vol.% SiC composite prepared by spark plasma sintering
AA6061-10 vol.% SiC composite was successfully prepared by spark plasma sintering. The deformation behaviour of this composite was studied using the uniaxial compression test, which was conducted at temperatur...
-
Article
Superfluous oxygen diffusion induced amorphization of ZrC0.6O0.4 and transformation of amorphous layer under electron beam irradiation
On the powder surface of oxygen-ordered ZrC0.6O0.4 obtained via isothermal heating of vacancy-ordered ZrC0.6 at 300 °C, an amorphous ZrC0.6Oy >0.4 layer in nanoscaled thickness is found to form if the heating las...
-
Article
Fabrication and characterization of Ti3SiC2-SiC nanocomposite by in situ reaction synthesis of TiC/Si/Al powders
The microstructure and mechanical properties of Ti3SiC2-SiC nanocomposite fabricated by in situ hot pressing (HP) synthesis process were studied. The results show that dense Ti3SiC2-SiC composite contained minor ...
-
Article
Contourlet-Based Features for Computerized Tumor Detection in Capsule Endoscopy Images
This article presents a computer-aided detection system for capsule endoscopy (CE) images using contourlet-based color textural features to recognize tumors in the digestive tract. As tumor exhibits rich infor...
-
Chapter and Conference Paper
Adaptive Nonlinear Diffusion Filter for Capsule Endoscopy Images
Different diseases in small intestine can be prevented and cured through early detection. The traditional detection methods such as endoscopy, ultrasound, and CT scan suffer from different shortcomings such as...
-
Article
Effect of shear stress on efferent lymph-derived lymphocytes in contact with activated endothelial monolayers
Lymphocyte interactions with endothelial cells in microcirculation are an important regulatory step in the delivery of lymphocytes to peripheral sites of inflammation. In normal circumstances, the predicted wa...