-
Chapter and Conference Paper
Brain Tumor Segmentation (BraTS) Challenge Short Paper: Improving Three-Dimensional Brain Tumor Segmentation Using SegResnet and Hybrid Boundary-Dice Loss
The advancements in biotechnology and healthcare have led to the increasing use of artificial intelligence in medical imaging analysis. Recently, image recognition technology such as deep learning has become a...
-
Chapter and Conference Paper
AROA: Attention Refinement One-Stage Anchor-Free Detector for Objects in Remote Sensing Imagery
Object detection in remote sensing images is a typical computer vision application, which has broad requirements in practice. Recently, attention mechanisms have been widely utilized in a diverse range of visu...
-
Chapter and Conference Paper
A Deep Supervision CNN Network for Brain Tumor Segmentation
The brain tumor segmentation is essential for diagnosis and treatment of brain diseases. However, most of current 3D deep learning technologies require large number of magnetic resonance images (MRIs). In orde...
-
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
Superpixel-Based Saliency Guided Intersecting Cortical Model for Unsupervised Object Segmentation
Unsupervised object segmentation aims to assign same label to pixels of object region with feature homogeneity, which can be applied to object detection and recognition. Intersecting cortical model (ICM) can s...
-
Chapter and Conference Paper
Continuous Estimation of Grasp Kinematics with Real-Time Surface EMG Decomposition
The aim of the study was to apply the real-time surface electromyography (EMG) decomposition to the continuous estimation of grasp kinematics. A real-time decomposition scheme based on the convolutional compen...
-
Chapter and Conference Paper
Ten-Years Research Progress of Natural Language Understanding Based on Perceptual Formalization
This paper introduces the research progress of machinery truly understanding of natural language from three aspects. First, this paper explains why to carry out data or feature description by perceptual struct...
-
Chapter and Conference Paper
Edge Detection Based on Primary Visual Pathway
Edge is an important feature and edge detection matters a lot to image processing and pattern recognition. In consideration of high properties of human visual system in image perception, a brain-inspired edge ...
-
Chapter and Conference Paper
A Novel Algorithm of Image Fusion Based on Non-subsampled Shearlet-Contrast Transform
To solve the shortcomings of results based on image fusion algorithm, such as lack of contrast and details, we proposed a novel algorithm of image fusion based on non-subsampled Shearlet-contrast transform (NS...
-
Chapter and Conference Paper
TransT: Type-Based Multiple Embedding Representations for Knowledge Graph Completion
Knowledge graph completion with representation learning predicts new entity-relation triples from the existing knowledge graphs by embedding entities and relations into a vector space. Most existing methods fo...
-
Chapter and Conference Paper
Continuous Summarization for Microblog Streams Based on Clustering
With rapid growth of information found on microblog services, dynamic summarization of evolving information has become an important task. However, the existing work on continuous microblog stream summarization...
-
Chapter and Conference Paper
A 3D-Shape Reconstruction Method Based on Coded Structured Light and Projected Ray Intersecting Location
This paper proposes a 3D-shape reconstruction method based on coded structured light. Projecting color pseudo-random coded pattern on surface of object and using the thought of ray intersecting location, 3D sh...
-
Chapter and Conference Paper
A Feature Points Matching Method Based on Window Unique Property of Pseudo-Random Coded Image
Proposed a method for object feature points matching used in active machine vision technique. By projecting pseudo-random coded structured light onto the object to add code information, its feature points can ...
-
Chapter and Conference Paper
Optimal Tracking Performance for Unstable Processes with NMP Zeroes
This paper has investigated optimal tracking performance for unstable processes with non-minimum phase (NMP) under control energy constraint. Firstly, based on prime factorization of unstable process, a perfor...