67 Result(s)
within
Conference Paper
Jun-Cheng **
-
Chapter and Conference Paper
Blendshape-Based Migratable Speech-Driven 3D Facial Animation with Overlap** Chunking-Transformer
Speech-driven 3D facial animation has attracted an amount of research and has been widely used in games and virtual reality. Most of the latest state-of-the-art methods employ Transformer-based architecture wi...
-
Chapter and Conference Paper
Autoencoder and Masked Image Encoding-Based Attentional Pose Network
Despite recent advances in single-image-based 3D human pose and shape estimation, partial occlusion remains a major challenge for many methods, leading to significant prediction errors. Some existing methods ...
-
Chapter and Conference Paper
MixPose: 3D Human Pose Estimation with Mixed Encoder
The fusion of spatio-temporal information is crucial for 3D human pose estimation in video. Existing methods usually extract temporal information from the spatially encoded poses, which may lead to limited spa...
-
Chapter and Conference Paper
Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning
Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise...
-
Chapter and Conference Paper
Wall Thickness Estimation from Short Axis Ultrasound Images via Temporal Compatible Deformation Learning
Structural parameters of the heart, such as left ventricular wall thickness (LVWT), have important clinical significance for cardiac disease. In clinical practice, it requires tedious labor work to be obtained...
-
Chapter and Conference Paper
RA Loss: Relation-Aware Loss for Robust Person Re-identification
Previous relation-based losses in person re-identification (ReID) typically comprise two sequential steps: they firstly sample both positive pair and negative pair and then deploy constraints to simultaneously...
-
Chapter and Conference Paper
Heuristic Semantic Segmentation Using the Weights of Local Voxel Structure
In recent years, with the rise of autonomous driving, more and more researchers focus on the field of point cloud semantic segmentation. They have increased the overall mIoU to over 70% and the speed to over 2...
-
Chapter and Conference Paper
Vision Transformer with Information Bottleneck for Fine-Grained Visual Classification
Fine-grained visual classification focus on accurately identifying the subordinate categories from a base class. One key of this task is to find discriminative local parts. Convolutional neural network-based m...
-
Chapter and Conference Paper
Multi-IMU with Online Self-consistency for Freehand 3D Ultrasound Reconstruction
Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities. Freehand 3D US is a technique that provides a deeper understanding of scanned region...
-
Chapter and Conference Paper
MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
Early diagnosis of renal cancer can greatly improve the survival rate of patients. Contrast-enhanced ultrasound (CEUS) is a cost-effective and non-invasive imaging technique and has become more and more freque...
-
Chapter and Conference Paper
Mitral Regurgitation Quantification from Multi-channel Ultrasound Images via Deep Learning
Mitral regurgitation (MR) is the most common heart valve disease. Prolonged regurgitation can cause changes in the heart size, lead to impaired systolic and diastolic capacity, and even threaten life. In clini...
-
Chapter and Conference Paper
KinStyle: A Strong Baseline Photorealistic Kinship Face Synthesis with an Optimized StyleGAN Encoder
High-fidelity kinship face synthesis is a challenging task due to the limited amount of kinship data available for training and low-quality images. In addition, it is also hard to trace the genetic traits betw...
-
Chapter and Conference Paper
Personalized Diagnostic Tool for Thyroid Cancer Classification Using Multi-view Ultrasound
Over the past decades, the incidence of thyroid cancer has been increasing globally. Accurate and early diagnosis allows timely treatment and helps to avoid over-diagnosis. Clinically, a nodule is commonly eva...
-
Chapter and Conference Paper
CT2CXR: CT-based CXR Synthesis for Covid-19 Pneumonia Classification
Chest X-ray (CXR) is a common imaging modality for examination of pneumonia. However, some pneumonia signs which are visible in CT may not be clearly identifiable in CXR. It is challenging to create a good gro...
-
Chapter and Conference Paper
Triplet Ratio Loss for Robust Person Re-identification
Triplet loss has been proven to be useful in the task of person re-identification (ReID). However, it has limitations due to the influence of large intra-pair variations and unreasonable gradients. In this pap...
-
Chapter and Conference Paper
VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-Based Convolutional Autoencoder
Visual Place Recognition (VPR) is a challenging task in Visual Simultaneous Localization and Map** (VSLAM), which expects to find out paired images corresponding to the same place in different conditions. Al...
-
Chapter and Conference Paper
An Investigation on the Microstructure and Mechanical Properties of the Hot-Dip-Aluminized-Q235/AZ91D Bimetallic Material Produced by Solid–Liquid Compound Casting
hot-dip-aluminized-Q235/AZ91D bimetallic material was acquired by casting into the mould where the hot-dip-aluminized-Q235 had been inserted to achieve the lightweight with optimal . The and of the h...
-
Chapter and Conference Paper
Cycle Structure and Illumination Constrained GAN for Medical Image Enhancement
The non-uniform illumination or imbalanced intensity in medical images brings challenges for automated screening, examination and diagnosis of diseases. Previously, CycleGAN was proposed to transform input ima...
-
Chapter and Conference Paper
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions, by only leveraging normal images in training phase. Normal images from healthy subject...
-
Chapter and Conference Paper
The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification
In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative info...
