Lu Fang, Jian Pei, Guangtao Zhai, Ruiping Wang (eds.) Artificial Intelligence

Springer, 2024. — 599 p.This book presents research advancements in the dynamics of systems with time delay conducted by the group led by Professor Jian Xu. Addressing the challenges arising from the joint impact of time delay and nonlinearity, novel theoretical approaches are developed to formulate the nonlinear response of the system. This facilitates the classification of complex nonlinear dynamics, especially the non-resonant and resonant double Hopf bifurcation. In contrast to systems without time delay, time delay systems require specific considerations when identifying system parameters, particularly the time delay. Consequently, inverse problems of systems with time delay are also explored in this book. Moreover, detailed investigations on vibration suppression methods and experimental prototypes based on time delay, such as time delay isolators with quasi-zero stiffness, are conducted. Simultaneously, this book is enriched with a large number of case studies ranging from manufacturing, network science, biology, and public transportation, illuminating the mechanisms of delay-induced nonlinear dynamics in practical applications. This book is suitable for graduate students and researchers who are eager to understand the delay-induced nonlinear dynamics, or technical personnel in whose projects small variations of time delay may cause significant changes in system responses.Organization.
Contents – Part I.
Contents – Part II.
Computer Vision.
MARS: An Instance-Aware, Modular, and Realistic Simulator for Autonomous Driving.
Concealed Object Segmentation with Hierarchical Coherence Modeling.
ViT-MPI: Vision Transformer Multiplane Images for Surgical Single-View View Synthesis.
Dual-Domain Network for Restoring Images from Under-Display Cameras.
Sliding Window Detection and Distance-Based Matching for Tracking on Gigapixel Images.
Robust Self-contact Detection Based on Keypoint Condition and ControlNet-Based Augmentation.
Explicit Composition of Neural Radiance Fields by Learning an Occlusion Field.
LEAD: LiDAR Extender for Autonomous Driving.
Fast Hierarchical Depth Super-Resolution via Guided Attention.
A Hybrid Approach for Segmenting Non-ideal Iris Images Using CGAN and Geometry Constraints.
3D-B2U: Self-supervised Fluorescent Image Sequences Denoising.
Equivariant Indoor Illumination Map Estimation from a Single Image.
Weakly-Supervised Grounding for VQA with Dual Visual-Linguistic Interaction.
STU3: Multi-organ CT Medical Image Segmentation Model Based on Transformer and UNet.
Integrating Human Parsing and Pose Network for Human Action Recognition.
Lightweight Rolling Shutter Image Restoration Network-Based on Undistorted Flow.
An Efficient Graph Transformer Network for Video-Based Human Mesh Reconstruction.
Multi-scale Transformer with Decoder for Image Quality Assessment.
Low-Light Image Enhancement via Unsupervised Learning.
GLCANet: Context Attention for Infrared Small Target Detection.
Fast Point Cloud Registration for Urban Scenes via Pillar-Point Representation.
PMPI: Patch-Based Multiplane Images for Real-Time Rendering of Neural Radiance Fields.
EFPNet: Effective Fusion Pyramid Network for Tiny Person Detection in UAV Images.End-to-end object-levell Contrastive Pretraining for Detection via Semantic-Aware Localization.
PointerNet with Local and Global Contexts for Natural Language Moment Localization.
Self-supervised Meta Auxiliary Learning for Actor and Action Video Segmentation from Natural Language.
RsMmFormer: Multimodal Transformer Using Multiscale Self-attention for Remote Sensing Image Classification.
Fashion Label Relation Networks for Attribute Recognition.
A Modified Fuzzy Markov Random Field Incorporating Multiple Features for Liver Tumor Segmentation.
Weakly Supervised Optical Remote Sensing Salient Object Detection Based on Adaptive Discriminative Region Suppression.
SPCTNet: A Series-Parallel CNN and Transformer Network for 3D Medical Image Segmentation.
LANet: A Single Stage Lane Detector with Lightweight Attention.
Visible and NIR Image Fusion Algorithm Based on Information Complementarity.
Data Mining.
End-to-end optimizationn of Quantization-Based Structure Learning and Interventional Next-Item Recommendation.
Multi-trends Enhanced Dynamic Micro-video Recommendation.
Parameters Efficient Fine-Tuning for Long-Tailed Sequential Recommendation.
Heterogeneous Link Prediction via Mutual Information Maximization Between Node Pairs.
Explainability, Understandability, and Verifiability of AI.
ADAPT Action-Aware Driving Caption Transformer.
Structural Recognition of Handwritten Chinese Characters Using a Modified Part Capsule Auto-encoder.
Natural Language Processing.
Sequential Style Consistency Learning for Domain-Generalizable Text Recognition.
MusicGAIL: A Generative Adversarial Imitation Learning Approach for Music Generation.
Unsupervised Traditional Chinese Herb Mention Normalization via Robustness-Promotion Oriented Self-supervised Training.
Feature Fusion Gate: Improving Transformer Classifier Performance with Controlled Noise.
Multi-round Dialogue State Tracking by Object-Entity Alignment in Visual Dialog.
Multi-modal Dialogue State Tracking for Playing GuessWhich Game.
Diagnosis Then Aggregation: An Adaptive Ensemble Strategy for Keyphrase Extraction.