Computer Analysis of Images and Patterns: 21st International Conference, CAIP 2025, Las Palmas de Gran Canaria, Spain, September 22–25, 2025, Proceedings, Part I(15621 Lecture Notes in Computer Science)

The volume set LNCS 15621-15622 constitutes the refereed proceedings of the 21st International Conference on Computer Analysis of Images and Patterns, CAIP 2025, which took place in Las Palmas de Gran Canaria, Spain, during September 22-25, 2025. The 65 full papers were carefully reviewed and selected from 109 submissions. The proceedings focus on Facial and Video Recognition, Image Segmentation, Object Detection and Applications, 3D Vision and Reconstruction, Biomedical Imaging and Diagnostics, Model Robustness and Generalization, Multimodal and Vision-Language Models, Robotics, Interaction and Intelligent Systems, Emerging Methods and Vision Applications.

Table of Contents:
​PAR Contest 2025.- An extended dataset and a baseline for pedestrian attribute recognition with advanced neural networks.- Leveraging Generalist VQA Models to improve Zero-Shot Pedestrian Attribute Recognition.- Multi-Task Pedestrian Attribute Classification Using ConvNeXt with Advanced Data Augmentation.- A Region-Aware Multi-Modal Framework for Pedestrian Attribute Recognition via CLIP and Graph Neural Networks.- Facial and Video Recognition.- Adapting to the Wild: From Human Face to Animal Face Recognition.- Enhanced Deep Learning DeepFake Detection Integrating Handcrafted Features.- Fast and Accurate 3D Face Reconstruction from Multiple Uncalibrated Images.- PAYMENT PENDING Seeing through Wearables: A Comprehensive Face Recognition Dataset from Body Worn Cameras.- SMSCI: Simultaneous Modeling of Social and Contextual Interactions for Multi Pedestrian Trajectory Prediction.- SPL-BEV: Soccer Player Localization and Birds-Eye-View Estimation.- CANpose: A Cross-Attention Framework for Human Pose Recognition.- RTFVE: Realtime Face Video Enhancement.- Image Segmentation.- Walk the Lines 2: Contour Tracking for Detailed Segmentation of Infrared Ships and Other Objects.- Dirichlet Process Mixture Model and Markov Random Field for PolSAR Image Segmentation.- Semantic Segmentation for Coastal Monitoring: Region Extraction and Overtopping Detection.- A Deep-Learning-Based Method for Real-Time Barcode Segmentation on Edge CPUs.- Edge-Aware Camouflaged Object Detection.- DVS-StereoInsect: An Event-based Stereo Dataset for Foreground-Background Insect Segmentation.- ColorEM-Net: Automated Segmentation of Structures in Large-Scale Electron Microscopy Using Element-Derived Ground Truth.- Object Detection and Applications.- LTBoost: Boosting Recall Uniformity in Long-Tailed Learning for Camera Trap Datasets.- Enhancing Agricultural Disease Diagnosis: YOLO-Based Detection of Root Rot in Beans.- Vision on the Move: Automated Hazardous Material Plate Detection in Freight Transport.- VIGIA-E: Density-Aware Patch Selection for Edge-Based Small Object Detection with PTZ Cameras.- Exploring Open-Vocabulary Models for Category-Free Detection.- Synthetic Data for Robust Runway Detection.- Identification of Buriti (Mauritia flexuosa) and Palmito Ju¸cara (Euterpe edulis) Species Using RT-DETR through High-Resolution Images Captured by UAV.- 3D Vision and Reconstruction.- Framework for Generation of Moment Invariants by Tensor Method.- HAME-NeRF: High Accuracy Mesh Extraction Leveraging Neural Radiance Fields.- FaDeN: Fast Depth-Supervised NeRFs with RGB-D Cameras.- AnthroFormer3D: Automating 3D Body Measurement Extraction via Vision Transformers Using a Novel Dataset.- Sphere-Depth: A Benchmark for Depth Estimation Methods with Varying Spherical Camera Orientations.- Image Valuation in NeRF-Based 3D Reconstruction.- VolE++: A Text-Guided Point-cloud Framework for Food 3D Reconstruction and Volume Estimation.