Advanced Intelligent Computing Technology and Applications -

. .

Résumé :

This 20-volume set LNCS 15842-15861 constitutes - in conjunction with the 4-volume set LNAI 15862-15865 and the 4-volume set LNBI 15866-15869 - the refereed proceedings of the 21st International Conference on Intelligent Computing, ICIC 2025, held in Ningbo, China, during July 26-29, 2025.

The total of 1206 regular papers 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....

Sommaire:
.- Intelligent Computing in Computer Vision .- SCHAL-Net: Synergistic Constraint of Holistic and Local Features for Cross Modality Place Recognition. .- Body part-aware cross-modal feature interaction learning for medical vision question answering. .- HybridScale-GuideTokens DETR: Enhancing Object Detection with GuideToken-Optimized Multi-Scale Feature Fusion in a Transformer Model. .- RiceSeg-YOLO: A Multi-Scale Attention-Based Instance Segmentation Model for Rice Leaf Rolling in Complex Paddy Environments. .- EdgeSAM-CASD: Lightweight Mural Damage Segmentation via Convolutional Adapter. .- MFCI-Net: Image Aesthetic Assessment Integrating Multilevel Deep Features and Composition Cognition. .- BTPose: 3D Pose Estimation from Bone to Pose with Efficient Multi Hypothesis Aggregation. .- DB-MFNet: A Dual-Branch Cross-Modal Fusion Network for High Resolution Remote Sensing Semantic Segmentation. .- Eliminating Ambiguities in One-Shot Medical Landmark Detection via Mask Drawing. .- Sensitive Target Hiding in Remote Sensing Images Based on Diffusion Models. .- MDFNet: Multimodal Remote Sensing Image Segmentation Method Based on Multilevel Discrepancy Feature Fusion. .- AWAD-Fusion: Dynamic Multi-Sensor Fusion Framework for Robust 3D Object Detection in Adverse Weather. .- LP-DETR: Layer-wise Progressive Relation for Object Detection. .- Wind Turbine Blade Surface Defect Detection Based on FFDA-YOLO. .- Scene Knowledge Enhanced Multimodal Retrieval Model for Dense Video Captioning. .- ABDet: Adaptive Feature Enhancement and Boundary Alignment Loss for Object Detection. .- A Cross-Font Image Retrieval Network for Recognizing Undeciphered Oracle Bone Inscriptions. .- A Novel Efficient Lightweight Multi-Scale Network for Apple Leaf Disease Identification. .- HDF-YOLO: A High-Precision Ship Detection Method in SAR Images Based on Improved YOLOv11. .- YOLO-MOB-C3: A Lightweight Pavement Defect Detection Model based on Highly Parameterized Structure and Residual Module. .- Macro and Micro-Expressions Spotting Based on Cross-Attention Transformer Progressive Fusion Network. .- SCR-T: Vehicle Video Frame Interpolation Based on Spatial-Channel Reconstruction and Transformers. .- WCAT: The Multi-scale Wavelet Channel Attention Module for Deepfake Detection. .- Center Corrective Representative Points for Oriented Object Detection. .- Enhancing Lane Perception and Topology Understanding Using SD and Satellite Maps. .- Cross-modal Matching with Noisy Correspondence via Neighbor Replacing. .- FMNV: A Dataset of Media-Published News Videos for Fake News Detection. .- IDD: An Identity Disentanglement Framework for Deepfake Detection. .- DEVR: Train an efficient Vision-RWKV model with improved knowledge distillation. .- CNNFormer: A CNN-Transformer Hybrid Model for Referring Image Segmentation. .- Interpretable Action Quality Assessment with Temporal Parsing. .- A multi-scale feature extraction and alignment method for cross-modal person re-identification. .- CLIO: A Unified Framework for Consistency-Aware Learning and Intra Modal Optimization in Text-Based Person Re-identification. .- PPCC-CD: Cross-Domain Plant Point Cloud Completion Based on Feature Low-Rank Mapping and Dual Frequency Prompts. .- PB-CLIP: Enhancing CLIP's Compositional Reasoning with Pixel-Level Image Hard Negatives and Balanced Multi-level Contrastive Learning. .- FreeForm-Prior: Parametric-Guided Model-Free 3D Human Mesh Reconstruction. .- Dual Attention Guidance with Vision-Language Models for Exposure-Consistent IlluminationEnhancement. .- Robustness and Fairness-Oriented Adaptive Federated Learning based on Shapley Value. .- VAMP: Visual Attribute-Guided Multi-dimensional Perception for Nasal Endoscopy Report Generation. .- LoRA-CLIP: Low-Rank Adaptation of Text Prompts for Visio...