Guest Editors' Introduction: Special Section on Higher Order Graphical Models in Computer Vision.

DeepSolar++: Understanding residential solar adoption trajectories with computer vision and technology diffusion models

This study evaluates the generalization capabilities of computer vision (CV) models for detecting cow locations in indoor free-stall barns, with a focus on quantifying the resources required for effective deployment across different farms where camera angles and lighting conditions vary. Given the increasing reliance of precision livestock farming (PLF) on object localization techniques to monitor livestock health and optimize resource management, understanding how to deploy CV models with minimal resources while maintaining high performance is critical. To assess generalization, we investigated three key hypotheses: (1) Model generalization is equally influenced by changes in lighting conditions and camera angles; (2) Higher model complexity guarantees better generalization performance; and (3) Fine-tuning with custom initial weights trained on related tasks enhances final performance compared to using pre-trained weights. The study utilized the newly released COws LOcalization (COLO) dataset, comprising 1,254 images and 11,818 cow instances captured from five distinct imaging settings with varying camera angles and lighting conditions. The first hypothesis was tested by training models on images from specific camera angles and evaluating performance on new angles. The second hypothesis was examined by comparing the performance of five different model sizes (e.g., YOLO11n with 2.6M parameters vs. YOLO11x with 56.9M parameters) on the same dataset. The third hypothesis was evaluated by pre-training a model on a subset of images from a specific barn and fine-tuning it on another subset from a similar setting to simulate transferring the training outcome to a different location within the same barn. Results indicate that changes in lighting conditions have a negligible impact on model generalization, whereas shifting from a top-view to a side-view perspective significantly reduces performance (P < 0.001). Model complexity does not always correlate with improved generalization, as optimal complexity depends on the dataset and task. Additionally, fine-tuning with custom initial weights benefits small, simple models but provides no significant (P > 0.05) advantage for larger models compared to training from scratch. As artificial intelligence adoption grows, alongside rising concerns about its environmental impact, this study provides practical guidelines for PLF researchers to optimize CV model deployment with minimal resource consumption. It also highlights key generalization challenges and leverages the COLO dataset to drive further research in resource-efficient livestock monitoring.

The informed sampler: A discriminative approach to Bayesian inference in generative computer vision models

This comprehensive volume is an essential reference tool for professional and academic researchers in the filed of computer vision, image processing, and applied mathematics. Continuing rapid advances in image processing have been enhanced by the theoretical efforts of mathematicians and engineers. This marriage of mathematics and computer vision - computational vision - has resulted in a discrete approach to image processing that is more reliable when leveraging in practical tasks. This comprehensive volume provides a detailed discourse on the mathematical models used in computational vision from leading educators and active research experts in this field. Topical areas include: image reconstruction, segmentation and object extraction, shape modeling and registration, motion analysis and tracking, and 3D from images, geometry and reconstruction. The book also includes a study of applications in medical image analysis. Handbook of Mathematical Models in Computer Vision provides a graduate-level treatment of this subject as well as serving as a complete reference work for professionals.

Computer vision systems are increasingly expanding their application in visual data analysis. Model training methods are undergoing the greatest development and improvement as the results of this stage significantly affect the final classification of objects and the interpretation of input information. Typically, computer vision systems use convolutional neural networks for training (Convolution Neural Network, CNN). The disadvantages of such systems are significant limitations in cross-modal learning, multimodality implementation, labeling of large amounts of data, etc. One of the ways to overcome these problems is to use Vision Transformers (ViT), which, compared to classical CNNs, have higher performance due to reduced inductive biases and high parallel computing efficiency. Introducing Self-Supervised Learning (SSL) technologies can significantly reduce the dependence on manually labeled data, contributing to the formation of generalized representations of images. Cross-Modal Learning (CML) expands the possibilities of processing them by combining data of different types. The development of the new approach, combined with the capabilities of cross-modal learning and self-learning in ViT in a single architecture, will ensure adaptability, efficiency, and system scalability in various applications. The research aims to provide a detailed overview of ViTs, approaches to their architecture, and methods for improving their efficiency. The mathematical foundations of the key concepts of ViT, cross-modal learning and self-learning, the main modifications of ViT, and their integration with SSL and CML technologies are considered. A comparison of methods using characteristics, performance, and efficiency is provided. The key challenges and prospects facing researchers and developers while creating universal models in computer vision are outlined. ViTs change computer vision by capturing global dependencies on images. Despite some challenges, ViTs provide excellent scalability and performance for large datasets. The active search for methods to overcome their limitations makes ViTs a key tool for improving image classification, object detection, and other computer vision tasks.

This paper covers machine learning approaches to improve the accuracy of a Deep Neural Network (DNN) inference in computer vision, particularly in image segmentation. A few benefits of object recognition aided by computer vision is to help aircraft crew avoid adversaries in various weather conditions, to offload the crew's attention from finding desired objects as well as estimating the position of those objects throughout missions. Since DNN inference is trained without explicit programming, it is challenging to precisely locate its sub-optimality when it performs less accurate prediction. This paper explores three machine learning approaches that improve a DNN model prediction accuracy: 1) Prediction result analysis using the author's original work called Directional Pixel Delta as well as Jaccard's Intersection over Union (IoU) loss function 2) Bayesian optimization hyper-parameter tuning 3) Training data optimization via Bootstrap Aggregating.

Counterfeit and substandard pharmaceuticals represent a critical global health crisis, with the World Health Organisation (WHO) reporting that falsified medicines comprise 10% of the global pharmaceutical trade, constituting one of the fastest-growing grey economies worldwide. This illicit market affects all regions, including high-income countries, causing devastating health and economic consequences that contribute to increased mortality and morbidity rates. The problem is particularly severe in developing nations with inadequate regulatory systems. Mobile health (mHealth) technologies have emerged as promising solutions for enhancing pharmaceutical supply chain integrity. However, comprehensive frameworks that integrate multiple authentication mechanisms remain limited in addressing the growing counterfeit drug crisis. The primary objective of this study is to design and implement a novel mobile health framework that integrates innovative packaging technology and computer vision to enhance pharmaceutical integrity and patient safety. This innovative approach enables consumers to authenticate genuine drugs and detect counterfeit/spurious products through advanced Quick Response (QR) code verification systems and artificial intelligence- powered tablet recognition capabilities. The proposed system utilises individual strip QR codes that enable real-time scanning at the point of sale to verify drug authenticity, directly addressing critical gaps identified in current pharmaceutical authentication methods. To overcome the practical challenge of expiration date loss when medication strips are cut at pharmacies, we developed a computer vision-based Artificial Intelligence (AI) model that automatically recognises the number of tablets remaining in a strip and correlates this information with the unique Identifier (ID). This approach leverages recent advances in computer vision for pharmaceutical applications and automated packaging inspection technologies. Each medication strip is assigned to an individual customer at the time of purchase, with pharmacists recording detailed customer information to ensure comprehensive tracking and accountability throughout the pharmaceutical supply chain. The integrated mobile application creates a robust anti-counterfeiting ecosystem by combining secure QR code authentication with intelligent visual recognition capabilities. The computer vision model provides accurate tablet counting and strip identification, maintaining continuity of medication tracking even when packaging is modified during dispensing processes, thus significantly enhancing supply chain transparency. This dual-authentication approach builds consumer confidence in pharmaceutical authenticity while directly addressing critical vulnerabilities identified in current regulatory frameworks. This comprehensive mobile health solution provides a scalable, evidence-based approach to pharmaceutical authentication that can be readily implemented across diverse healthcare systems globally, offering substantial potential for reducing the circulation of falsified medicines and improving patient safety outcomes in the ongoing battle against the pandemic of counterfeit pharmaceuticals. To overcome the practical challenge of expiration date loss when medication strips are cut at pharmacies, we developed a computer vision-based Artificial Intelligence (AI) model that automatically recognises the number of tablets remaining in a strip and correlates this information with the unique Identifier (ID). This approach leverages recent advances in computer vision for pharmaceutical applications and automated packaging inspection technologies. Each medication strip is assigned to an individual customer at the time of purchase, with pharmacists recording detailed customer information to ensure comprehensive tracking and accountability throughout the pharmaceutical supply chain. The integrated mobile application creates a robust anti-counterfeiting ecosystem by combining secure QR code authentication with intelligent visual recognition capabilities. The computer vision model provides accurate tablet counting and strip identification, maintaining continuity of medication tracking even when packaging is modified during dispensing processes, thus significantly enhancing supply chain transparency. This dual-authentication approach builds consumer confidence in pharmaceutical authenticity while directly addressing critical vulnerabilities identified in current regulatory frameworks. This comprehensive mobile health solution provides a scalable, evidence-based approach to pharmaceutical authentication that can be readily implemented across diverse healthcare systems globally, offering substantial potential for reducing the circulation of falsified medicines and improving patient safety outcomes in the ongoing battle against the pandemic of counterfeit pharmaceuticals.

Abstract. Most computer vision and photogrammetry applications rely on accurately estimating the camera pose, such as visual navigation, motion tracking, stereo photogrammetry, and structure from motion. The Essential matrix is a well-known model in computer vision that provides information about the relative orientation between two images, including the rotation and translation, for calibrated cameras with a known camera matrix. To estimate the Essential matrix, the camera calibration matrices, which include focal length and principal point location must be known, and the estimation process typically requires at least five matching points and the use of robust algorithms, such as RANSAC to fit a model to the data as a robust estimator. From the usually large number of matched points, choosing five points, the Essential matrix can be determined based on a simple solution, which could be good or bad. Obtaining a globally optimal and accurate camera pose estimation, however, requires additional steps, such as using evolutionary algorithms (EA) or swarm algorithms (SA), to prevent getting trapped in local optima by searching for solutions within a potentially huge solution space.This paper aims to introduce an improved method for estimating the Essential matrix using swarm particle algorithms that are known to efficiently solve complex problems. Various optimization techniques, including EAs and SAs, such as Particle Swarm Optimization (PSO), Gray Wolf Optimization (GWO), Improved Gray Wolf Optimization (IGWO), Genetic Algorithm (GA), Salp Swarm Algorithm (SSA) and Whale Optimization Algorithm (WOA), are explored to obtain the global minimum of the reprojection error for the five-point Essential matrix estimation based on using symmetric geometric error cost function. The experimental results on a dataset with known camera orientation demonstrate that the IGWO method has achieved the best score compared to other techniques and significantly speeds up the camera pose estimation for larger number of point pairs in contrast to traditional methods that use the collinearity equations in an iterative adjustment.

With the increasingly application of Deep Learning models in computer vision, data quality and systematic metric assessment have assumed a preponderant role in the model performance. In this paper we present the evaluation approach of a model built to provide a computer vision solution, aiming to visually identify the energy meter box in households able to be connected to the electricity grid. It is provided a discussion on the real need for a careful analysis of the metrics adopted to evaluate the assertiveness of the results obtained, highlighting the evaluation framework, the importance of image quality and the main issues that must be followed to meet such a purpose. The approach herein described turned out to be on a good methodological path, presenting prediction results able to add value to the chosen application and which can be continuously improved, how is it intrinsic to the machine learning process.

Hidden Markov models (HMMs) have become a standard tool for pattern recognition in computer vision. Although parameter and topology estimation have been studied, and still are, detailed analysis of how these estimated parameters contribute to HMM performance is rarely addressed. We develop tools for measuring such contributions and illustrate key issues in a representative task of gesture recognition - 3D motion recovery from 2D projections.

With promising results of machine learning based models in computer vision, applications on medical imaging data have been increasing exponentially. Deep learning models perform well when trained on standardized datasets from artificial settings. However, generalization and translation to real-world clinical settings are challenging. The complexity of real-world applications in healthcare emanates from different data distributions across multiple device domains, variations in image resolution, human errors, and the lack of manual grading. Moreover, healthcare applications not only suffer from scarcity in labeled data, but also face limited access to un-labeled data. These limitations pose additional challenges to developing translatable applications for clinical care. In this paper, we utilize self-supervised representation learning methods, formulated effectively in transfer learning settings, to address limited data availability and assess the importance of real-world data for generalizations to clinical settings. We show that by employing a self-supervised approach with transfer learning on a multi-domain real-world dataset, we can achieve 16% relative improvement on a standardized dataset over supervised baselines.

MP07-16 COMPUTER VISION ANALYSIS OF UPPER TRACT UROTHELIAL CARCINOMA TO PREDICT HIGH VS LOW GRADE PATHOLOGY

How do we understand the complex patterns of neural responses that underlie scene understanding? Studies of the network of brain regions held to be scene-selective—the parahippocampal/lingual region (PPA), the retrosplenial complex (RSC), and the occipital place area (TOS)—have typically focused on single visual dimensions (e.g., size), rather than the high-dimensional feature space in which scenes are likely to be neurally represented. Here we leverage well-specified artificial vision systems to explicate a more complex understanding of how scenes are encoded in this functional network. We correlated similarity matrices within three different scene-spaces arising from: (1) BOLD activity in scene-selective brain regions; (2) behavioral measured judgments of visually-perceived scene similarity; and (3) several different computer vision models. These correlations revealed: (1) models that relied on mid- and high-level scene attributes showed the highest correlations with the patterns of neural activity within the scene-selective network; (2) NEIL and SUN—the models that best accounted for the patterns obtained from PPA and TOS—were different from the GIST model that best accounted for the pattern obtained from RSC; (3) The best performing models outperformed behaviorally-measured judgments of scene similarity in accounting for neural data. One computer vision method—NEIL (“Never-Ending-Image-Learner”), which incorporates visual features learned as statistical regularities across web-scale numbers of scenes—showed significant correlations with neural activity in all three scene-selective regions and was one of the two models best able to account for variance in the PPA and TOS. We suggest that these results are a promising first step in explicating more fine-grained models of neural scene understanding, including developing a clearer picture of the division of labor among the components of the functional scene-selective brain network.

Colorectal cancer (CRC) is the third most diagnosed cancer form globally and the second leading cause of cancer-related death after lung cancer. A precise histological categorization of CRC tissue is critical for diagnosis and patient management decisions. However, the variety of tissue patterns in CRC histological images makes the classification a challenging problem. This study applies Vision Transformers, a new class of deep-learning models in computer vision, to perform a multiclass tissue classification of a publicly available CRC histology images dataset. The data set consists of 5000 images with eight categories of tissue. We trained two variants of Transformers, namely Vision Transformer and Compact Convolutional Transformer, and achieved 93.3% and 95% accuracy, respectively. Our results outperform the original paper (87.4%) on the same dataset. Furthermore, our study highlights the opportunities of using Transformers in the histopathological image domain.

A Recognition System for Diagnosing Salivary Gland Neoplasms Based on Vision Transformer