160 Result(s)
-
Chapter and Conference Paper
Complex Glyph Enhancement for License Plate Generation
The complex glyphs of license plates usually comes with a long-tail distribution, leading to poor recognition performance of the tail class. Supplementing the training data with generated license plates is an ...
-
Chapter and Conference Paper
A Survey of Domain Generalization-Based Face Anti-spoofing
In recent years, remarkable research attention has been attracted to improve the generalization ability of face anti-spoofing methods, and domain generalization techniques have been widely exploited for adapti...
-
Chapter and Conference Paper
Survey on Deep Learning Based Fusion Recognition of Multimodal Biometrics
We take multimodal as a new research paradigm. This research paradigm is based on the premise that all human interactions with the outside world required the support of multimodal sensory systems. Deep learnin...
-
Chapter and Conference Paper
Adaptive Registration for Multi-type Remote Sensing Images via Dynamic Feature Selection
Remote sensing image registration (RSIR) has been performed in various RS applications for decades. However, how to adaptively register multi-type (multi-view, multi-temporal, and multi-sensor) RS images remai...
-
Chapter and Conference Paper
Gaussian Distribution Prior Based Multi-view Self-supervised Learning for Serous Retinal Detachment Segmentation
Assessment of serous retinal detachment (SRD) plays an important role in the diagnosis of central serous chorioretinopathy (CSC). In this paper, we propose an unsupervised method, called Gaussian distribution pri...
-
Chapter and Conference Paper
Hard Negative Sample Mining for Contrastive Representation in Reinforcement Learning
In recent years, contrastive learning has become an important technology of self-supervised representation learning and achieved SOTA performances in many fields, which has also gained increasing attention in ...
-
Chapter and Conference Paper
Uncertainty-Aware Label Rectification for Domain Adaptive Mitochondria Segmentation
Mitochondria segmentation from electron microscopy images has seen great progress, especially for learning-based methods. However, since the learning of model requires massive annotations, it is time and labou...
-
Chapter and Conference Paper
Learning Neuron Stitching for Connectomics
The pipeline of connectomics usually divides the large-scale electron microscopy volumes into multiple 3D blocks and segments them independently. The segmentation results in adjacent blocks demand subtle mergi...
-
Chapter and Conference Paper
Attention Guided Slit Lamp Image Quality Assessment
Learning human visual attention into a deep convolutional network contributes to classification performance improvement. In this paper, we propose a novel attention-guided architecture for image quality assess...
-
Chapter and Conference Paper
SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection
Accurate bone segmentation and landmark detection are two essential preparation tasks in computer-aided surgical planning for patients with craniomaxillofacial (CMF) deformities. Surgeons typically have to com...
-
Chapter and Conference Paper
Automatic Severity Rating for Improved Psoriasis Treatment
Psoriasis is a chronic skin disease which occurs to 2%–3% of the world’s entire population. If treated properly, patients can still maintain a relatively high quality of life. Otherwise, Psoriasis could cause ...
-
Chapter and Conference Paper
Data-Dependence Dual Path Network for Choroidal Neovascularization Segmentation in SD-OCT Images
Choroidal neovascularization (CNV) is a typical clinical manifestation of age-related macular degeneration (AMD) and an important factor leading to blindness in AMD patients. Automated CNV lesion segmentation ...
-
Chapter and Conference Paper
Hole Detection with Texture-Suppression on Wooden Plate Surfaces
We devote to the detection of holes on the surface of household panels. Due to the wide variety of furniture panel patterns, the most critical problem is to eliminate the interference of the texture attached t...
-
Chapter and Conference Paper
MSC-Fuse: An Unsupervised Multi-scale Convolutional Fusion Framework for Infrared and Visible Image
Lacking the labeled data, how to establish an unsupervised learning method is essential for the infrared and visible image fusion task. As such, this article introduces a novel unsupervised learning fusion fra...
-
Chapter and Conference Paper
Monocular 3D Target Detection Based on Cross-Modal and Mass Perceived Loss
In recent years, the monocular 3D target detection algorithm based on pseudo-LiDAR has achieved great accuracy improvement on the KITTI data set. However, due to the large amount of noise contained in the poin...
-
Chapter and Conference Paper
Cross-Corpus Speech Emotion Recognition Based on Sparse Subspace Transfer Learning
Cross-corpus speech emotion recognition (SER) has become a hot-spot research topic in recent years. In actual situations, the problem that how to efficiently find the corpus invariant feature representations i...
-
Chapter and Conference Paper
CDLRS: Collaborative Deep Learning Model with Joint Regression and Segmentation for Automatic Fovea Localization
With the development of information technology, eyes are easily overworked for modern people, which increases the burden of ophthalmologists. This leads to the urgent need of the computer-aided early screening...
-
Chapter and Conference Paper
An Arcloss-Based and Openset-Test-Oriented Finger Vein Recognition System
Finger vein recognition has advantages that can’t be replaced by other biometrics. Our designed system employs the feature vectorization pattern and multiple strategies, such as Arcloss, image enhancement desi...
-
Chapter and Conference Paper
Using Conv-LSTM to Refine Features for Lightweight Image Super-Resolution Network
In this paper, we propose a lightweight network that uses conv-LSTM for feature fusion (LFN) to improve image super-resolution performance and save the number of parameters. The network extracts features of di...
-
Chapter and Conference Paper
Identifying Quantitative and Explanatory Tumor Indexes from Dynamic Contrast Enhanced Ultrasound
Contrast-enhanced ultrasound (CEUS) has been one of the most promising imaging techniques in tumor differential diagnosis since the real-time view of intra-tumor blood microcirculation. Existing studies primar...