![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
129 Result(s)
-
Chapter and Conference Paper
Split and Merge: Component Based Segmentation Network for Text Detection
This paper presents a novel component-based detector to locate scene texts with arbitrary orientations, shapes and lengths. Our approach detects text by predicting four components like text region (TR), text s...
-
Chapter and Conference Paper
CycleGAN-Based Image Translation for Near-Infrared Camera-Trap Image Recognition
Due to its invisibility, NIR (Near-infrared) flash has been widely used to capture the images of wild animals in the night. Although the animals can be captured without notice, the gray NIR images are short of...
-
Chapter and Conference Paper
Research on Prediction Algorithm for Heavy Overload of Main Equipment in Distribution Network
Distribution transformer is the basic unit of power grid operation and the carrier of data in power grid construction. In real life, heavy overload of equipment in the distribution network will damage the equi...
-
Chapter and Conference Paper
Melanoma Classification Method Based on Ensemble Convolutional Neural Network
Melanoma is the most serious form of skin cancer, with more than 123,000 new cases worldwide each year. Reliable automatic melanoma screening system will be a great help for clinicians to detect malignant skin...
-
Chapter and Conference Paper
Chinese Text Classification Based on Adversarial Training
As the most basic and important application in the field of natural language processing, text classification has always been a hot research topic in the field of natural language processing. So far, a large nu...
-
Chapter and Conference Paper
Depth Estimation Based on Optical Flow and Depth Prediction
Depth sensing is essential for 3D reconstruction and scene understanding. Depth sensors can support dense depth results. But often face the difficult of environmental interference such as the restricted operat...
-
Chapter and Conference Paper
A Study of kind Metaphors and Simile Annotation Using Dependency Parsing and ConceptNet
Metaphors are pervasive in human language, but the understanding of metaphors still poses a challenge for artificial intelligence (AI), cognitive science, and linguistics. To understand metaphorical expression...
-
Chapter and Conference Paper
A Multi-scale Fusion Method for Dense Crowd Counting
We propose a dense crowd detection network, called MSFNet, which can deal with highly dense crowd scenes, make accurate counting estimation and generate high-quality density maps by deep learning. The network ...
-
Chapter and Conference Paper
Document Domain Randomization for Deep Learning Document Layout Extraction
We present document domain randomization (DDR), the first successful transfer of CNNs trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document page...
-
Chapter and Conference Paper
LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further inv...
-
Chapter and Conference Paper
Image Collation: Matching Illustrations in Manuscripts
Illustrations are an essential transmission instrument. For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other. This ...
-
Chapter and Conference Paper
Automated Kidney Tumor Segmentation with Convolution and Transformer Network
Kidney cancer is one of the most common malignancies worldwide. Early diagnosis is an effective way to reduce the mortality and automated segmentation of kidney tumor in computed tomography scans is an importa...
-
Chapter and Conference Paper
Research on Splicing of Horizontal and Longitudinal Shredded Paper Based on Hungarian Algorithm
In order to solve the problems of traditional heuristic algorithm for solving the splicing of horizontal and longitudinal shredded paper, such as high complexity and low success rate when the order of magnitud...
-
Chapter and Conference Paper
Multimodal Brain Tumor Segmentation Using Contrastive Learning Based Feature Comparison with Monomodal Normal Brain Images
Many deep learning (DL) based methods for brain tumor segmentation have been proposed. Most of them put emphasis on elaborating deep network’s internal structure to enhance the capacity of learning tumor-relat...
-
Chapter and Conference Paper
Deep Learning-Based Head and Neck Radiotherapy Planning Dose Prediction via Beam-Wise Dose Decomposition
Accurate dose map prediction is key to external radiotherapy. Previous methods have achieved promising results; however, most of these methods learn the dose map as a black box without considering the beam-sha...
-
Chapter and Conference Paper
Semantic-Aware Registration with Weakly-Supervised Learning
Medical image registration is a fundamental task for many clinical applications. Most deep learning-based image registrations methods have achieved brilliant performance owing to the incorporation of mask info...
-
Chapter and Conference Paper
Uncertainty-Guided Lung Nodule Segmentation with Feature-Aware Attention
Since radiologists have different training and clinical experiences, they may provide various segmentation annotations for a lung nodule. Conventional studies choose a single annotation as the learning target ...
-
Chapter and Conference Paper
Curvature-Enhanced Implicit Function Network for High-quality Tooth Model Generation from CBCT Images
In digital dentistry, high-quality tooth models are essential for dental diagnosis and treatment. 3D CBCT images and intra-oral scanning models are widely used in dental clinics to obtain tooth models. However...
-
Chapter and Conference Paper
Interaction-Oriented Feature Decomposition for Medical Image Lesion Detection
Common lesion detection networks typically use lesion features for classification and localization. However, many lesions are classified only by lesion features without considering the relation with global con...
-
Chapter and Conference Paper
Bio-ATT-CNN: A Novel Method for Identification of Glioblastoma
Through the years, many learning methods which made remarkable feat are raised in many industries. Many focus had been paid to attention-convolution (ATT-CNN). Achievements have been made in image processing, ...