-
Chapter and Conference Paper
HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D ha...
-
Article
Safe optimal robust control of nonlinear systems with asymmetric input constraints using reinforcement learning
External disturbances and asymmetric input constraints may cause a major problem to the optimal control of the system. Aiming at such problem, this article presents a safe and optimal robust control method bas...
-
Article
Anti-Bandit for Neural Architecture Search
Neural Architecture Search (NAS) is a highly challenging task that requires consideration of search space, search efficiency, and adversarial robustness of the network. In this paper, to accelerate the trainin...
-
Article
An efficient lightweight convolutional neural network for industrial surface defect detection
Since surface defect detection is significant to ensure the utility, integrality, and security of productions, and it has become a key issue to control the quality of industrial products, which arouses interes...
-
Article
Knowledge Reconstruction for Dynamic Multi-objective Particle Swarm Optimization Using Fuzzy Neural Network
Many real−world applications are dynamic multi−objective optimization problems (DMOPs). The transfer of knowledge in the evolutionary process is believed to have advantages in solving DMOPs. However, most exis...
-
Chapter and Conference Paper
Ternary Data, Triangle Decoding, Three Tasks, a Multitask Learning Speech Translation Model
Direct end-to-end approaches for speech translation (ST) are now competing with the traditional cascade solutions. However, end-to-end models still suffer from the challenge of ST data scarcity. How to effecti...
-
Chapter and Conference Paper
A Stable Long-Term Tracking Method for Group-Housed Pigs
In recent years, computer vision technologies have been increasingly applied to livestock farming for improving efficiency and reducing the labor force in surveillance. Tracking of group-housed pigs is an impo...
-
Chapter and Conference Paper
PCDialogEval: Persona and Context Aware Emotional Dialogue Evaluation
Endowing dialogue systems with emotional intelligence is an essential strategy for machines to achieve deep social interaction with users, for which effective evaluation metrics for emotional dialogue are in u...
-
Chapter and Conference Paper
Identifying miRNA-Disease Associations Based on Simple Graph Convolution with DropMessage and Jum** Knowledge
MiRNAs play an important role in the occurrence and development of human disease. Identifying potential miRNA-disease associations is valuable for disease diagnosis and treatment. Therefore, it is very urgent ...
-
Article
Video super-resolution based on deep learning: a comprehensive survey
Video super-resolution (VSR) is reconstructing high-resolution videos from low resolution ones. Recently, the VSR methods based on deep neural networks have made great progress. However, there is rarely system...
-
Article
Filter pruning via expectation-maximization
The redundancy in convolutional neural networks (CNNs) causes a significant number of extra parameters resulting in increased computation and less diverse filters. In this paper, we introduce filter pruning vi...
-
Chapter and Conference Paper
Towards Defending Adversarial Attacks with Temperature Regularization in Automatic Modulation Recognition
Deep learning has been shown to perform extremely well at various machine learning tasks. However, these same architectures are highly vulnerable to adversarial examples: malicious inputs carefully crafted by ...
-
Chapter and Conference Paper
A Study on Lexical Knowledge and Semantic Features of Speech Act Verbs Based on Language Facts
Semantic feature is an important dimension of lexical semantics, which has long been a concern of linguistics, psychology and cognitive neuroscience. Based on the connectionism theory, this research combines s...
-
Chapter and Conference Paper
Effective ML-Block and Weighted IoU Loss for Object Detection
In computer vision tasks, better performance of the transformer model is due to self-attention mechanism and learning of global information. However, it also largely increases parameters and calculations. In t...
-
Chapter and Conference Paper
Reversible Image Watermarking Based on Deep Learning
Reversible image watermarking refers to technology that can restore an image to its original state after extracting the watermark. The scheme based on prediction error expansion (PEE) can achieve greater embed...
-
Chapter and Conference Paper
Where are the Children with Autism Looking in Reality?
Social difficulties are hallmarks of individuals with autism spectrum disorder (ASD), of which atypical visual attention is one of the most important characteristics. Learning and modeling the atypical visual ...
-
Chapter and Conference Paper
Weighted Multi-task Sparse Representation Classifier for 3D Face Recognition
Rapid development of 3D face recognition can help people overcome some bottlenecks in 2D recognition. But still susceptible to changes in facial expressions. At the same time, due to the large number of 3D poi...
-
Chapter and Conference Paper
Classroom Teaching Effect Monitoring and Evaluation System with Deep Integration of Artificial Intelligence
With the progress and development of the times, education informatization has become the primary content to promote the progress of education. However, with the rapid advancement of technology, many problems ...
-
Chapter and Conference Paper
Multi-service Communication Isolation of Underground Pipe Gallery Based on WiFi6
There are a variety of services in underground pipe gallery, and these services should be isolated during data transmission to ensure communication security. WiFi6(802.11ax) has the advantages of fast transmis...
-
Chapter and Conference Paper
Multi Recursive Residual Dense Attention GAN for Perceptual Image Super Resolution
Single image super-resolution (SISR) has achieved great progress based on convolutional neural networks (CNNs) such as generative adversarial network (GAN). However, most deep learning architectures cannot uti...