Read more
List of contents
.- Intelligent Computing in Computer Vision.
.- LAC-YOLO: Advancing Metal Surface Defect Detection with Latent Representation and Re-parameterized Feature Fusion.
.- YOLO-Xray: Massively Enhanced X-ray Detection with a Specialized YOLO Framework.
.- Classroom Teacher Action Recognition Based on Teacher Region Extraction and Temporal Pyramid Module.
.- RetinexWaveMamba: Retinex and Wavelet-based Lightweight Framework for Low-Light Image Enhancement with Mamba.
.- DOLF-SLAM: A Visual-Inertial SLAM for Dynamic Environments with Scene Flow-Based Object Filtering and Line Feature.
.- ClothAnimate: Boosting Video Virtual Try-on via Novel Attention-control Diffusion Model.
.- Echoes of the Past: No-Reference Evaluation in Digital Restoration of Ancient Murals.
.- PMNet: 3D Model based on Position Self-Supervision and Multiway Attention for Pulmonary Nodule Classification.
.- DenseViT: Densely Connected Vision Transformers for Visual Recognition.
.- GVTNet: Graph Vision Transformer for Face Super-Resolution.
.- ADHI-YOLO: Attentive SPPF with Dynamic Head Integration for Object Detection in Low-Light Environments.
.- DBNet-Enhanced Detection of Handwritten Mathematical Formulas.
.- SC-D3D: A Dual Collaborative Distillation Framework for High-Fidelity Text-to-3D Generation.
.- Cross-Modal Hybrid Loss with Enhanced Feature Feedback for RGB-T Crowd Counting.
.- WT-YOLO: A High-Accuracy Model for Wind Turbine Target Detection.
.- Ada-CAD: Adaptive distillation and Dynamic neighbor masked Attention for Continual Anomaly Detection.
.- DSNC-Match: Semi-supervised Semantic Segmentation Based on Multi-information Mining.
.- Bidirectional Feature Fusion U-Net for Infrared Small Target Detection.
.- Physics-Data Synergy in Endoscopic Imaging: A Retinex-Based Dynamic Illumination Modulation Framework for Robust Monocular Depth Estimation.
.- EIL-YOLO: A Lightweight Model for Enhanced Small Object Detection in UAV Images.
.- EduFocus-YOLO: Dynamic Multi-Scale Fusion Pyramid for Classroom Behavior Detection.
.- SADAN: A Domain Adaptive SAR Object Detection Network Based on Scale Aware Alignment.
.- NeuroSync: A Dual-Path Dynamically Modulated Framework with Spatiotemporal Compression for Human Action Recognition.
.- TG-STC: Text Guided Spatio-Temporal Contextualization for Video Quality Assessment.
.- Embodied Intelligence-Driven Framework for UAV Power Inspection Systems: Federated Reinforcement Learning for Multi-Agent Collaborative Optimization.
.- RSMA-Net: ResNet-Swin Residual Cooperative Encoding and Multi-Scale Attentional Reconstruction Network for Cardiac Boundary Segmentation.
.- HTPAN: A lightweight hybrid topk-pooling attention network for efficient plant disease detection.
.- Dual-Gradient Dynamic Splatting: Density Control with Dual-gradient for 3D Gaussian Splatting in Monocular Dynamic Scene.
.- Multi-level global-local context aggregation for video semantic segmentation.
.- FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization.
.- SnowTextNet: Detection-Guided Restoration Dual-Branch Network for Text Detection in Snowy Scenes.
.- Joint Frame and Event Object Tracking via Non-Causal State Space Duality.
.- Enhancing YOLOv8 for Multi-Class Tongue Coating Detection: An Analysis of Attention and Multi-Scale Fusion Mechanisms.
.- A Generative Face Detection Method Based on Local Artifact Metrics and Gradient-Enhanced Attention Mechanism.
.- High-Low Frequency Feature Alignment for Few-Shot Object Detection.
.- RDMAUNet: A Residual Deformable Convolution and Multi-Attention Model for Coronary Artery Segmentation.
.- Semantic Evolution and Boundary Samples Suppression for Generalized Zero-Shot Learning.
.- EMSA: An Ensemble-Based Framework for Multimodal Sentiment Analysis.
.- Research on Urban Road Obstacle Detection Method Based on ERLM-YOLOv8.
.- QACC-Net: Lightweight Clothing Keypoint Detection with Quantized Self-Attention and Learnable Coordinate Classification.
.- SATENet: Bridging Structural and Edge Semantics for Vessel Segmentation.
.- Topology-Aware Transformer for Efficient Human Mesh Recovery with Low-Dim Mesh Attention.
.- EDER-ACNN: CNN-Based Facial Expression Recognition with Morphological EDER Preprocessing.
.- TP-SAM: Fine-tuning SAM with Task-specific Prompt in the Loop.
Summary
The 12-volume set CCIS 2564-2575, together with the 28-volume set LNCS/LNAI/LNBI 15842-15869, constitutes the refereed proceedings of the 21st International Conference on Intelligent Computing, ICIC 2025, held in Ningbo, China, during July 26-29, 2025.
The 523 papers presented in these proceedings books were carefully reviewed and selected from 4032 submissions.
This year, the conference concentrated mainly on the theories and methodologies as well as the emerging applications of intelligent computing. Its aim was to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. Therefore, the theme for this conference was "Advanced Intelligent Computing Technology and Applications".
