Read more
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".
List of contents
.- Intelligent Computing in Computer Vision.
.- SiamMFT: Siamese MultiFrame network in infrared small target Tracking.
.- DSF-SL: A Dual-Stream Fusion Network with Soft Labels for Robust Facial Expression Recognition.
.- CDS-YOLO: An underwater object detection algorithm based on improved YOLOv10s.
.- Adaptive Drone-based Tilt Photogrammetry and Real-time 3D Reconstruction for Interactive Digital Scenography.
.- ASFST: Adaptive Spectral Filters Sparse Transformer for Hyperspectral Image Denoising.
.- STD-DETR: A Multi-Scale Feature Fusion Network based on RT-DETR for Small Object Detection.
.- VI-YOLO: A Vehicle Detection Method Based on Bimodal Fusion for Drones.
.- DSCformer: Dynamic Spectrum Coordination Transformer for Multi-Scale Image Deraining.
.- LBA: Multi-scale Video Segment Sampling for Open-Ended Video Question Answering.
.- EmoGaussian: High-Fidelity Emotional Talking Head Generation with 3D Gaussian Splatting.
.- YOLO-GH: An Enhanced Oriented Object Detection for Greenhouses in Remote Sensing Images.
.- Facial Keypoint-Based Segment-Level Driver Yawning Detection by Graph Temporal Convolutional Neural Network Model.
.- DRIM-Net: Diversity-Enhanced Robust Information Mining Network for Visible-Infrared Person Re-Identification.
.- Classifier Recalibration for Human-Object Interaction Detection.
.- HyDiffVeg: A Hybrid Diffusion-Based Framework for Uncertainty-Aware Vegetation Forecasting.
.- Enhancing Small Object Detection in UAV Aerial Imagery with DCI-DETR: A Deep Learning Approach.
.- FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection.
.- An Improved Multi-Task Model for Instance Segmentation and Pose Estimation Based on YOLOv11.
.- DictAvatar: Expressive Facial Avatar Reconstruction with Facial Feature Dictionary.
.- UniMamba: A Unified CNN-Mamba Model for Infrared Small Target Detection.
.- Unified Identity and Attribute Learning for Visible-Infrared Person Re Identification.
.- Hybrid Positional Encoding for Spatiotemporal Feature Separation in Sign Language Recognition.
.- Enhancing CLIP for Pedestrian Image-Text Retrieval via Bi-Level Alignment and Weighted Similarity Distribution Matching Loss.
.- Image Manipulation Localization via Enhanced Cross-Modal Fusion with Edge Supervision.
.- Zero-Shot Scene Graph Generation with Bias Correction and Unseen Space Optimization.
.- HomoMamba for Self-Supervised Homography Estimation.
.- Hierarchical Local-Latent Diffusion Model for Efficient Video Deblurring.
.- CropAug: Controllable Region Cropping for Fine-grained Data Augmentation.
.- WGMVSNet: An Efficient Dual-Branch Self-Supervised Multi-View Stereo Network for 3D Reconstruction.
.- Catching Inter-Modal Artifacts: A Cross-Modal Framework for Temporal Forgery Localization.
.- An Immersive Virtual Reality Training System for Enhancing Orientation and Mobility in Individuals with Visual Impairments.
.- StoryWeaver: Consistent Multi-Character Open-Ended Story Generation.
.- Efficient Surface Defect Detection via Multi-scale Features and Lightweight Attention.
.- Landmark-Guided Knowledge for Vision-and-Language Navigation.
.- MAS-ZSAS: A Zero-Shot Anomaly Segmentation Framework with Multi Attribute Guided Text Prompt.
.- HLD-DETR: A Lightweight Transformer-based Model for Underwater Seafood Detection.
.- MBFSNet: Multi-scale Binocular Fusion Semantic Co-occurrence Network for Multi-label Fundus Disease Diagnosis.
.- Visibility-Guided GCN-Transformer: Enhancing 2D Pose Estimation under Occlusion.
.- STPEFormer: Spatio-Temporal Pose Embedding-Enhanced Transformer for Energy Expenditure Estimation.
.- Detail Aware CompletionNet for Point Cloud Completion.
.- Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation.
.- Information Bottleneck Driven Masked Autoencoders for Data-Efficient Auxiliary Learning.
Summary
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".
