-
Chapter and Conference Paper
A New Research on Contrast Sensitivity Function Based on Three-Dimensional Space
In this paper, we try to extend human eyes’ contrast sensitivities characteristics (CSF) to three-dimensional space, but the experimental results show that the traditional characteristics of CSF has limitation...
-
Chapter and Conference Paper
Visual Knowledge Discovery for Diffusion Kurtosis Datasets of the Human Brain
Classification and visualization of structures in the human brain provide vital information to physicians who examine patients suffering from brain diseases and injuries. In particular, this information is use...
-
Chapter and Conference Paper
Estimation of Fiber Orientations Using Neighborhood Information
Diffusion magnetic resonance imaging (dMRI) has been used to noninvasively reconstruct fiber tracts. Fiber orientation (FO) estimation is a crucial step in the reconstruction, especially in the case of crossin...
-
Chapter and Conference Paper
Stereoscopic Image Quality Assessment Based on Binocular Adding and Subtracting
There has been a great concern on blind image quality assessment in the field of 2D images, however, stereoscopic image quality assessment (SIQA) is still a challenging task. In this paper, we propose an effic...
-
Chapter and Conference Paper
Named Entity Recognition in Clinical Text Based on Capsule-LSTM for Privacy Protection
Clinical Named Entity Recognition for identifying sensitive information in clinical text, also known as Clinical De-identification, has long been critical task in medical intelligence. It aims at identifying v...
-
Chapter and Conference Paper
Multi-scale Neural Style Transfer Based on Deep Semantic Matching
Existing Neural Style Transfer (NST) algorithms do not migrate styles well to a reasonable location where the output image can render the correct spatial structure of the object being painted. We propose a dee...
-
Chapter and Conference Paper
Transfer Learning for Electrocardiogram Classification Under Small Dataset
The First China ECG Intelligent Competition is held by Tsinghua University. It is aimed to intelligently classify electrocardiogram (ECG) signals into two categories in preliminary and nine categories in remat...
-
Chapter and Conference Paper
No-Reference Image Quality Assessment via Multi-order Perception Similarity
No-reference image quality assessment (NR-IQA) aims to develop models that can predict the quality of distorted image automatically and accurately without the reference. Lack of reference makes NR-IQA based on...
-
Chapter and Conference Paper
Gated Fusion of Discriminant Features for Caricature Recognition
Caricature recognition is a challenging problem, because there are typically geometric deformations between photographs and caricatures. It is nontrivial to learn discriminant large-margin features. To combat ...
-
Chapter and Conference Paper
Immersive Storytelling in Augmented Reality: Witnessing the Kindertransport
Although hardware and software for Augmented Reality (AR) advanced rapidly in recent years, there is a paucity and gap on the design of immersive storytelling in augmented and virtual realities, especially in ...
-
Chapter and Conference Paper
Modern Workplace Ergonomics and Productivity – A Systematic Literature Review
With the development of remote collaboration platforms, the word ‘workplace’ is no longer limited to offices. With the impact of COVID-19, more and more people bring their workplaces out of the corporate offic...
-
Chapter and Conference Paper
Direct Reconstruction of Crossing Muscle Fibers in the Human Tongue Using a Deep Neural Network
The human tongue is made entirely of muscle fibers that either group in a single direction or cross orthogonally in pairs. Reconstructing the muscle fiber orientations throughout the tongue can be beneficial f...
-
Chapter and Conference Paper
Generative Self-training for Cross-Domain Unsupervised Tagged-to-Cine MRI Synthesis
Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target dom...
-
Chapter and Conference Paper
An Efficient and Reasonably Simple Solution to the Perspective-Three-Point Problem
In this work, we propose an efficient and simple method for solving the perspective-three-point (P3P) problem. This algorithm leans substantially on linear algebra, in which the rotation matrix and translation...
-
Chapter and Conference Paper
Point-to-Box Network for Accurate Object Detection via Single Point Supervision
Object detection using single point supervision has received increasing attention over the years. However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detec...
-
Chapter and Conference Paper
Unitail: Detecting, Reading, and Matching in Retail Scene
To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datase...
-
Chapter and Conference Paper
A Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified Robustness
Certified robustness guarantee gauges a model’s resistance to test-time attacks and can assess the model’s readiness for deployment in the real world. In this work, we explore a new problem setting to critical...
-
Chapter and Conference Paper
End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement
The automatic generation of floorplans given user inputs has great potential in architectural design and has recently been explored in the computer vision community. However, the majority of existing methods s...
-
Chapter and Conference Paper
Learning Ego 3D Representation as Ray Tracing
A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird’s-eye-view (BEV) coordinate frame of the ego car in order to ground downstream plann...
-
Chapter and Conference Paper
Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation
Recently, studies considering domain gaps in shape completion attracted more attention, due to the undesirable performance of supervised methods on real scans. They only noticed the gap in input scans, but ign...