127 Result(s)
-
Chapter and Conference Paper
Neural Distinguishers on \(\texttt {TinyJAMBU-128}\) and \(\texttt {GIFT-64}\)
In CRYPTO 2019, Gohr first introduced a pioneering attempt, and successfully applied neural differential distinguisher ( \(\mathcal {NDD}\) ...
-
Chapter and Conference Paper
On Quantifying Local Geometric Structures of Fiber Tracts
In diffusion MRI, fiber tracts, represented by densely distributed 3D curves, can be estimated from diffusion weighted images using tractography. The spatial geometric structure of white matter fiber tracts is...
-
Chapter and Conference Paper
Cross-Project Issue Classification Based on Ensemble Modeling in a Social Coding World
The simplified and deformalized contribution mechanisms in social coding are attracting more and more contributors involved in the collaborative software development. To reduce the burden on the side of projec...
-
Chapter and Conference Paper
Employ Decision Values for Soft-Classifier Evaluation with Crispy References
Evaluation of classification performance has been comprehensively studied for both crispy and fuzzy classification tasks. In this paper, we address the hybrid case: evaluating fuzzy prediction results against ...
-
Chapter and Conference Paper
One-Pass Multi-task Convolutional Neural Networks for Efficient Brain Tumor Segmentation
The model cascade strategy that runs a series of deep models sequentially for coarse-to-fine medical image segmentation is becoming increasingly popular, as it effectively relieves the class imbalance problem....
-
Chapter and Conference Paper
Improved Nuclear Segmentation on Histopathology Images Using a Combination of Deep Learning and Active Contour Model
Automated nuclear segmentation on histopathological images is a prerequisite for a computer-aided diagnosis system. It becomes a challenging problem due to the nucleus occlusion, shape variation, and image bac...
-
Chapter and Conference Paper
Robust Segmentation of Overlap** Cells in Cervical Cytology Using Light Convolution Neural Network
Automated segmentation of cells in cervical cytology images poses a great challenge due to the presence of fuzzy and overlap** cells, noisy background, and poor cytoplasmic contrast. We present an improved m...
-
Chapter and Conference Paper
Synthesizing Missing PET from MRI with Cycle-consistent Generative Adversarial Networks for Alzheimer’s Disease Diagnosis
Multi-modal neuroimages (e.g., MRI and PET) have been widely used for diagnosis of brain diseases such as Alzheimer’s disease (AD) by providing complementary information. However, in practice, it is unavoidabl...
-
Chapter and Conference Paper
GPU Accelerated Image Matching with Cascade Hashing
SIFT feature is widely used in image matching. However, matching massive images is time consuming because SIFT feature is a high dimensional vector. In this paper, we proposed a GPU accelerated image matching ...
-
Chapter and Conference Paper
Crowd Counting Based on MMCNN in Still Images
Accurately estimate the crowd count from a still image with arbitrary perspective and arbitrary crowd density is one of the difficulties of crowd analysis in surveillance videos. Conventional methods are scene...
-
Chapter and Conference Paper
Robust Visual Tracking Using Oriented Gradient Convolution Networks
Convolutional networks have been successfully applied to visual tracking to extract some useful feature. However, deep networks are time-consuming to offline training and usually extract the feature from raw p...
-
Chapter and Conference Paper
CAD Model Based on NN and PCA in Prostate Tumor MRI
Aiming to feature redundancy problem in MRI Prostate Tumor ROI high dimension representation, a model, Prostate Tumor CAD Model based on NN with PCA feature-level fusion in MRI, is proposed in this paper. Firs...
-
Chapter and Conference Paper
A Novel Representation for Abnormal Crowd Motion Detection
A lot of methods of abnormal crowd motion detection in videos have been proposed in recent years. Most of them are still based on low semantic features, such gray value, velocity and gradient. Usually, the low...
-
Chapter and Conference Paper
Relevance and Coherence Based Image Caption
The attention-based image caption framework has been widely explored in recent years. However, most techniques generate next word conditioned on previous words and current visual contents, while the relationsh...
-
Chapter and Conference Paper
Hypergraph-Based Data Reduced Scheduling Policy for Data-Intensive Workflow in Clouds
Data-intensive computing is expected to be the next-generation IT computing paradigm. Data-intensive workflows in clouds are becoming more and more popular. How to schedule data-intensive workflow efficiently ...
-
Chapter and Conference Paper
Further Analysis of Candlestick Patterns’ Predictive Power
Since the candlestick patterns were mined, there is a contentious dispute on whether the candlestick patterns have predictive power in academia. To help resolve the debate, this paper uses the data mining meth...
-
Chapter and Conference Paper
Subspace Clustering by Capped \(l_1\) Norm
Subspace clustering, as an important clustering problem, has drawn much attention in recent years. State-of-the-art methods generally try to design an efficient model to regularize the coefficient matrix while...
-
Chapter and Conference Paper
Yet Another Schatten Norm for Tensor Recovery
In this paper, we introduce a new class of Schatten norms for tensor recovery. In the new norm, unfoldings of a tensor along not only every single order but also all combinations of orders are taken into accou...
-
Chapter and Conference Paper
A Swarm Intelligence Algorithm Inspired by Twitter
For many years, evolutionary computation researchers have been trying to extract the swarm intelligence from biological systems in nature. Series of algorithms proposed by imitating animals’ behaviours have es...
-
Chapter and Conference Paper
Landmark Selecting on 2D Shapes for Constructing Point Distribution Model
A new method of selecting landmarks on 2D shapes which are represented by Centripetal Catmull-Rom spline is proposed in this paper. Firstly, a mean shape is generated from training set and landmarks on mean sh...