331 Result(s)
within
Conference Paper
Li** Shao
English
Image Processing and Computer Vision
-
Chapter and Conference Paper
ViT-MPI: Vision Transformer Multiplane Images for Surgical Single-View View Synthesis
In this paper, we explore the use of a single imaging device to acquire immersive 3D perception in endoscopic surgery. To solve the heavily ill-posed problem caused by the unknown depth and unseen occlusion, w...
-
Chapter and Conference Paper
Model Distillation for Lane Detection on Car-Level Chips
As one of the most essential perception modules in the autonomous driving system, the lane detection module must accurately and efficiently detect each traffic lane’s location, color and type to secure the veh...
-
Chapter and Conference Paper
Domain Specific Pre-training Methods for Traditional Chinese Medicine Prescription Recommendation
Traditional Chinese Medicine (TCM) is an important constituent of medical treatment. During the development history of TCM, there have been a large number of medical records accumulated, which embody the exper...
-
Chapter and Conference Paper
Multi-graph Laplacian Feature Map** Incorporating Tag Information for Image Annotation
Automatic image annotation has exerted a tremendous fascination of many researchers with the development of multimedia and computer vision. However, most methods employ graph learning omit to combine the label...
-
Chapter and Conference Paper
Unsupervised Traditional Chinese Herb Mention Normalization via Robustness-Promotion Oriented Self-supervised Training
Herbal prescriptions are a vital aspect of Traditional Chinese Medicine (TCM) treatment. The textual representations of herbs can vary significantly across various TCM documents and records. To enhance the uti...
-
Chapter and Conference Paper
A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance ...
-
Chapter and Conference Paper
Noise-Robust Gaussian Distribution Based Imbalanced Oversampling
Imbalanced data classification has become one of the hot topics in the field of data mining and machine learning. Oversampling is one of the mainstream methods to solve the imbalance problem by synthesizing ne...
-
Chapter and Conference Paper
A Constant Air Flow Controller Based on Interval Type-2 Fuzzy PID Controller
In order to improve the sampling accuracy and the adaptability to different loads, a constant air flow controller based on closed-loop control is designed and realized. The mathematical model of this constant ...
-
Chapter and Conference Paper
A Reinforcement Learning Approach for Personalized Diversity in Feeds Recommendation
Feeds recommendation has been widely used in various applications, such as e-commerce site, where users can constantly browse products generated by never-ending feeds. It’s important to not only consider insta...
-
Chapter and Conference Paper
DeletePop: A DLT Execution Time Predictor Based on Comprehensive Modeling
The modeling and simulation of Deep Learning Training (DLT) are challenging problems. Due to the intricate parallel patterns, existing modelings and simulations do not consider enough factors that influence t...
-
Chapter and Conference Paper
Domain Incremental Learning for EEG-Based Seizure Prediction
When building seizure prediction systems, the typical research scenario is patient-specific. In this scenario, the model is limited to performing well for individual patients and cannot acquire knowledge trans...
-
Chapter and Conference Paper
SPSTN: Sequential Precoding Spatial-Temporal Networks for Railway Delay Prediction
Predicting the delay time of trains is an important task in intelligent transport systems, as an accurate prediction can provide a reliable reference for passengers and dispatchers of the railway system. Howev...
-
Chapter and Conference Paper
Learning from Hindsight Demonstrations
Learning from demonstrations (LfD) is an important technique to help reinforcement learning (RL) boost the training process, especially in the case of sparse rewards. But a major obstacle is the acquisition of...
-
Chapter and Conference Paper
The Effects of Dual Display Configuration and Users’ Experience on Performance and Preference in Complex Spatial-Verbal Tasks
Working from home has become popular during Covid-19 pandemic and it promoted the use of dual displays to handle complex information coming with multi-tasking. Previous studies have shown that the use of dual ...
-
Chapter and Conference Paper
Homomorphic Encryption-Based Privacy Protection for Palmprint Recognition
Palmprint recognition is a promising biometric technology. Currently, the research on palmprint recognition focuses on the topic of feature extraction and matching. However, due to the characteristic that biom...
-
Chapter and Conference Paper
Research on Airborne Infrared Target Recognition Method Based on Target-Environment Coupling
Airborne infrared targets are easily influenced by environmental factors, imaging angles, imaging distances, etc., resulting in decreased recognition accuracy. To address this issue, this paper proposes an air...
-
Chapter and Conference Paper
Deep Interactive Image Semantic and Instance Segmentation
Existing deep interactive segmentation methods only focus on the extraction of specific instance objects. When the target of interest to users is a category, existing methods have to perform more interactions....
-
Chapter and Conference Paper
Hindsight Balanced Reward Sha**
Sparse rewards is a tricky problem in reinforcement learning and reward sha** is commonly used to solve the problem of sparse rewards in specific tasks, but it often requires priori knowledge and manually de...
-
Chapter and Conference Paper
Multi-task Multi-instance Learning for Jointly Diagnosis and Prognosis of Early-Stage Breast Invasive Carcinoma from Whole-Slide Pathological Images
With the tremendous progress brought by artificial intelligence, many whole-slide pathological images (WSIs) based machine learning models are designed to estimate the clinical outcome of human cancers. Howeve...
-
Chapter and Conference Paper
ElDet: An Anchor-Free General Ellipse Object Detector
Ellipse detection is a fundamental task in object shape analysis. Under complex environments, the traditional image processing based approaches may under-perform due to the hand-crated features. Instead, CNN-b...
