546 Result(s)
-
Chapter and Conference Paper
Alpha Local Difference Loss Function for Deep Image Matting
In recent years, deep learning-based matting methods have received increasing attention due to their superior performance. The design of the loss function plays a important role in the performance of matting m...
-
Chapter and Conference Paper
Human Identification Using Tooth Based on PointNet++
Human identification using tooth plays a crucial role in disaster victim identification. Traditional tooth recognition methods like iterative closest point (ICP) require laborious pairwise registration, so in ...
-
Chapter and Conference Paper
Frame Correlation Knowledge Distillation for Gait Recognition in the Wild
Recently, large deep models have achieved significant progress on gait recognition in the wild. However, such models come with a high cost of runtime and computational resource consumption. In this paper, we i...
-
Chapter and Conference Paper
Generative AI Enables the Detection of Autism Using EEG Signals
In disease detection, generative models for data augmentation offer a potential solution to the challenges posed by limited high-quality electroencephalogram (EEG) data. The study proposes a temporal-spatial f...
-
Chapter and Conference Paper
Less-than-One Shot 3D Segmentation Hijacking a Pre-trained Space-Time Memory Network
In this paper, we propose a semi-supervised setting for semantic segmentation of a whole volume from only a tiny portion of one slice annotated using a memory-aware network pre-trained on video object segmenta...
-
Chapter and Conference Paper
Facial Adversarial Sample Augmentation for Robust Low-Quality 3D Face Recognition
Compared with traditional 3D face recognition tasks using high precision 3D face scans, 3D face recognition based on low-quality data captured by consumer depth cameras is more practicable for real-world appli...
-
Chapter and Conference Paper
Dynamic Graph-Guided Transferable Regression for Cross-Domain Speech Emotion Recognition
To deal with the problem of cross-domain speech emotion recognition (SER), in this paper, we propose a novel dynamic graph-guided transferable regression (DGTR) method. Specifically, a retargeted discriminant ...
-
Chapter and Conference Paper
Few-Shot Person Re-identification Based on Hybrid Pooling Fusion and Gaussian Relation Metric
In practical scenarios, person re-identification tasks often face the problem of insufficient available pedestrian images. In response to this problem, a few-shot person re-identification method based on hybri...
-
Chapter and Conference Paper
Multiple Temporal Aggregation Embedding for Gait Recognition in the Wild
Gait recognition in the wild is a cutting-edge topic in biometrics and computer vision. Since people is less cooperative in the wild scenario, view angles, walking direction and pace cannot be controlled. It l...
-
Chapter and Conference Paper
Finger Vein Recognition Based on Unsupervised Spiking Neural Network
At present, although the deep learning models represented by convolutional neural networks and Transformers have achieved promising recognition accuracies in finger vein (FV) recognition, there still remain so...
-
Chapter and Conference Paper
Gait Recognition with Various Data Modalities: A Review
Gait recognition aims to recognize one subject by the way she/he walks without alerting the subject, which has drawn increasing attention. Recently, gait recognition can be represented using various data modal...
-
Chapter and Conference Paper
A Novel Dual-Modal Biometric Recognition Method Based on Weighted Joint Group Sparse Representation Classification
Multi-modal biometric recognition technology is an effective method to improve the accuracy and reliability of identity recognition. However, there are some problems (such as feature space incompatibility) wit...
-
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
Blind Perceptual Quality Assessment for Single Image Motion Deblurring
Single image deblurring is a typical ill-posed problem. Although a lot of effective algorithms have been proposed, there is a lack of blind evaluation metrics for the perceptual quality of deblurred images. In...
-
Chapter and Conference Paper
Learning Optimal Transport Map** of Joint Distribution for Cross-scenario Face Anti-spoofing
Face anti-spoofing (FAS) under different scenarios is a challenging and indispensable task for a real face recognition system. In this paper, we propose a novel cross-scenario FAS method by learning the optima...
-
Chapter and Conference Paper
YoloMask: An Enhanced YOLO Model for Detection of Face Mask Wearing Normality, Irregularity and Spoofing
Wearing of surgical face masks has become the new norm of our daily life in the context of the COVID-19 pandemic. Under many conditions at various public places, it is necessary to check or monitor whether the...
-
Chapter and Conference Paper
Texture-Guided Multiscale Feature Learning Network for Palmprint Image Quality Assessment
Palmprint recognition has attracted widespread attention because of its advantages such as easy acquisition, rich texture, and security. However, most existing palmprint recognition methods focus most on featu...
-
Chapter and Conference Paper
A Deformable Convolution Encoder with Multi-scale Attention Fusion Mechanism for Classification of Brain Tumor MRI Images
The diagnosis of gliomas tumors, pituitary tumors, meningiomas tumors, and normal brain (No Tumor) on MRI images is challenging and requires diligence due to the diversity of focal regions. This has motivated ...
-
Chapter and Conference Paper
Recurrence Quantification Analysis of Cardiovascular System During Cardiopulmonary Resuscitation
Sudden cardiac arrest (CA) is a common cause of death, and cardiopulmonary resuscitation (CPR) can improve the survival rate of CA patients. However, the in-depth study of the pathophysiological mechanism of p...
-
Chapter and Conference Paper
A Finger Bimodal Fusion Algorithm Based on Improved Densenet
Compared with single-mode biometric recognition, multimodal biometric recognition has been widely used because of its high security and high accuracy. Among them, finger based multimodal biometric recognition ...