Description
Book Synopsis.- YOLOv8_ODY:An Object Detection Model for Traffic SignsT.
.- Mask-Based Matching Enhancement for Unsupervised Point Cloud Registration.
.- Driver action recognition based on Dynamic Adaptive Transformer.
.- SimNET: A Deep learning macroscopic traffic simulation model for signal controlled urban road network.
.- UAV-LMDN: Lightweight Multi-Scale Small Object Detection Network for Unmanned Aerial Vehicle Perspective.
.- LRDN: Lightweight Risk Detection Network for Power System Operations.
.- Personalized Federated Learning by Model Pruning via Batch Normalization Layers.
.- IT-HMDM: Invertible Transformer for Human Motion Diffusion Model.
.- Fashion Image Retrieval Based on Multimodal Features Enhancement and Fusion.
.- Syntactic Enhanced Multi-Channel Graph Convolutional Network for Aspect-based Sentiment Analysis.
.- Intelligent Helmet System for Hazardous Area Detection based on Digital Twin Technology.
.- An Evaluation of a Simulation System for Visitors in Exhibit Halls.
.- Foley Agent: Automatic Sound Design and Mixing Agent for Silent Videos Driven by LLMs.
.- Deep Metric Learning with Feature Aggregation for Generalizable Person Re-Identification.
.- Diverse 3D Human Pose Generation in Scenes based on Decoupled Structure.
.- A Combination Simulation Method for Low Orbit Large Scale Satellites via STK and NS2.
.- Semantic-Guided Prompt Learning Network for Generalized Zero-Shot Learning.
.- MiT-Unet: Mixed Transformer Unet for Transmission Line Segmentation in UAV Images.
.- Semantic-driven multi-character multi-motion 3D animation generation.
.- MSAR: A Mask Branch Module Integrating Multi-scale Attention And RefineNet.
.- Multi-level Knowledge Distillation for Class Incremental Learning.
.- Research on the algorithm of helmet-wearing detection based on the optimized Mobilevit and Centernet.
.- Better Sampling, towards Better End-to-end small Object Detection.
.- Stealthily Launch Backdoor Attacks Against Deep Neural Network Models via Steganography.
.- Seat belt wearing detection based on Efficient Det_Ad.
.- DHNet: A Depth wise Separable Convolution-based High-Resolution Full Projector Compensation Network.
.- Denoising Implicit Feedback for Extractive Question Answering.
.- Iterative Consistent Attentional Diffusion Model for Multi-Contrast MRISuper-Resolution.
