-
Chapter and Conference Paper
Learned Pseudo-Random Number Generator Based on Generative Adversarial Networks
Pseudorandom number generators (PRNGs) are fundamental components of modern cryptography and information security. Due to the inherent complexity and unpredictability of neural networks, they have become an at...
-
Article
Information gain based dynamic support set construction for cold-start recommendation
A fundamental challenge for recommendation systems is the cold-start problem, i.e., recommending with no or few user-item interactions. An emerging direction alleviates the problem with meta-learning. These me...
-
Article
Morphing aircraft acceleration and deceleration task morphing strategy using a reinforcement learning method
This paper proposes a design scheme for a whole morphing strategy based on the reinforcement learning (RL) method. A novel morphing aircraft is designed, and its nonlinear dynamic equations are established bas...
-
Article
Two-stage single image reflection removal with reflection-aware guidance
Removing undesired reflection from an image captured through a glass surface is a very challenging problem with many practical applications. For improving reflection removal, cascaded deep models have been usu...
-
Article
Open AccessJoint optic disc and cup segmentation based on multi-scale feature analysis and attention pyramid architecture for glaucoma screening
Automatic segmentation of optic disc (OD) and optic cup (OC) is an essential task for analysing colour fundus images. In clinical practice, accurate OD and OC segmentation assist ophthalmologists in diagnosing...
-
Article
An improved spatial temporal graph convolutional network for robust skeleton-based action recognition
Skeleton-based action recognition methods using complete human skeletons have achieved remarkable performance, but the performance of these methods could significantly deteriorate when critical joints or frame...
-
Article
Semantic segmentation network with multi-path structure, attention reweighting and multi-scale encoding
Semantic segmentation is an active field of computer vision. It provides semantic information for many applications. In semantic segmentation tasks, spatial information, context information, and high-level sem...
-
Chapter and Conference Paper
Tiny-YOLOv7: Tiny Object Detection Model for Drone Imagery
With the rapid development of drones, tiny object detection in drone-captured scenarios has become a challenge task. However, the altitude of the drone changes while flying lead to the scale of the object chan...
-
Chapter and Conference Paper
User Adaptive Language Learning Chatbots with a Curriculum
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing. Many current educational dialog systems p...
-
Chapter and Conference Paper
Univariate Time Series Forecasting via Interactive Learning
For time series forecasting tasks, it is necessary to capture the temporal dependencies from observed variables. Although many deep learning models have gained good performance, they still lack an effective mo...
-
Chapter and Conference Paper
Can ChatGPT Replace Traditional KBQA Models? An In-Depth Analysis of the Question Answering Performance of the GPT LLM Family
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge. Therefore, there is growing interest...
-
Article
Delving into monocular 3D vehicle tracking: a decoupled framework and a dedicated metric
Acquiring 3D trajectories of on-road vehicles is an essential visual task for autonomous driving systems. Existing 3D vehicle tracking methods either rely on point cloud data or need to be trained on visual tr...
-
Chapter and Conference Paper
GRU-Attention Interpretable Knowledge Tracking Model with Forgetting Law for Intelligent Education System
The advent of intelligent education systems and widespread distance learning have revolutionized the educational landscape. Extracting meaningful insights from this wealth of information is crucial for improvi...
-
Chapter and Conference Paper
Quantifying Occupant Behavior Uncertainty in Spatio-Temporal Visual Comfort Assessment of National Fitness Halls: A Machine Learning-Based Co-simulation Framework
Occupant behavior has been recognized as the main factor influencing visual comfort gaps between simulated and actual conditions. However, existing daylight and glare simulation methods mostly fail to deal wit...
-
Article
Hybrid War** Fusion for Video Frame Interpolation
Video frame interpolation aims to synthesize new intermediate frames between existing ones, which is an important task in video enhancement. A classic direction in this field is flow-based which estimates moti...
-
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 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 ...
-
Chapter and Conference Paper
Medical Image Segmentation Using Transformer
For the past few years, the U-Net structure shows strong performance in the field of medical image segmentation. However, due to the inherent locality of convolution operations, U-shaped structures are often l...
-
Chapter and Conference Paper
Self-paced Safe Co-training for Regression
In semi-supervised learning, co-training is successfully in augmenting the training data with predicted pseudo-labels. With two independently trained regressors, a co-trainer iteratively exchanges their select...
-
Chapter and Conference Paper
Decentralized Predictive Enterprise Resource Planning Framework on Private Blockchain Networks Using Neural Networks
Theoretically, cross-department predictive modeling can improve the operational efficiency of an enterprise, particularly on enterprise resource planning. For example, a model that predicts the volume of purch...