LMPNet for Weakly-supervised Keypoint Discovery

In this work, we explore the task of semantic object keypoint discovery weakly-supervised by only category labels. This is achieved by transforming discriminatively-trained intermediate layer filters into keypoint detectors. We begin by identifying three preferred characteristics of keypoint detectors: (i) spatially sparse activations, (ii) consistency and (iii) diversity. Instead of relying on hand-crafted loss terms, a novel computationally-efficient leaky max pooling (LMP) layer is proposed to explicitly encourage final conv-layer filters to learn "non-repeatable local patterns" that are well aligned with object keypoints. Informed by visualizations, a simple yet effective selection strategy is proposed to ensure consistent filter activations and attention mask-out is then applied to force the network to distribute its attention to the whole object instead of just the most discriminative region. For the final keypoint prediction, a learnable clustering layer is proposed to group keypoint proposals into keypoint predictions. The final model, named LMPNet, is highly interpretable in that it directly manipulates network filters to detect predefined concepts. Our experiments show that LMPNet can (i) automatically discover semantic keypoints that are robust to object pose and (ii) achieves strong prediction accuracy comparable to a supervised pose estimation model.

Robust Component Detection for Flexible Manufacturing: A Deep Learning Approach to Tray-Free Object Recognition under Variable Lighting

Flexible manufacturing systems in Industry 4.0 require robots capable of handling objects in unstructured environments without rigid positioning constraints. This paper presents a computer vision system that enables industrial robots to detect and grasp pen components in arbitrary orientations without requiring structured trays, while maintaining robust performance under varying lighting conditions. We implement and evaluate a Mask R-CNN-based approach on a complete pen manufacturing line at ZHAW, addressing three critical challenges: object detection without positional constraints, robustness to extreme lighting variations, and reliable performance with cost-effective cameras. Our system achieves 95% detection accuracy across diverse lighting conditions while eliminating the need for structured component placement, demonstrating a 30% reduction in setup time and significant improvement in manufacturing flexibility. The approach is validated through extensive testing under four distinct lighting scenarios, showing practical applicability for real-world industrial deployment.

Fair Deepfake Detectors Can Generalize

Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently conflicting, revealing a trade-off between them. In this paper, we, for the first time, uncover and formally define a causal relationship between fairness and generalization. Building on the back-door adjustment, we show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions. Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals. Across three cross-domain benchmarks, DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art detectors, validating both its theoretical foundation and practical effectiveness.

Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss

The task of Human-Object conTact (HOT) detection involves identifying the specific areas of the human body that are touching objects. Nevertheless, current models are restricted to just one type of image, often leading to too much segmentation in areas with little interaction, and struggling to maintain category consistency within specific regions. To tackle this issue, a HOT framework, termed \textbf{P3HOT}, is proposed, which blends \textbf{P}rompt guidance and human \textbf{P}roximal \textbf{P}erception. To begin with, we utilize a semantic-driven prompt mechanism to direct the network's attention towards the relevant regions based on the correlation between image and text. Then a human proximal perception mechanism is employed to dynamically perceive key depth range around the human, using learnable parameters to effectively eliminate regions where interactions are not expected. Calculating depth resolves the uncertainty of the overlap between humans and objects in a 2D perspective, providing a quasi-3D viewpoint. Moreover, a Regional Joint Loss (RJLoss) has been created as a new loss to inhibit abnormal categories in the same area. A new evaluation metric called ``AD-Acc.'' is introduced to address the shortcomings of existing methods in addressing negative samples. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art performance in four metrics across two benchmark datasets. Specifically, our model achieves an improvement of \textbf{0.7}$\uparrow$, \textbf{2.0}$\uparrow$, \textbf{1.6}$\uparrow$, and \textbf{11.0}$\uparrow$ in SC-Acc., mIoU, wIoU, and AD-Acc. metrics, respectively, on the HOT-Annotated dataset. Code is available at https://github.com/YuxiaoWang-AI/P3HOT.

Deep learning-based segmentation of T1 and T2 cardiac MRI maps for automated disease detection

Objectives Parametric tissue mapping enables quantitative cardiac tissue characterization but is limited by inter-observer variability during manual delineation. Traditional approaches relying on average relaxation values and single cutoffs may oversimplify myocardial complexity. This study evaluates whether deep learning (DL) can achieve segmentation accuracy comparable to inter-observer variability, explores the utility of statistical features beyond mean T1/T2 values, and assesses whether machine learning (ML) combining multiple features enhances disease detection. Materials & Methods T1 and T2 maps were manually segmented. The test subset was independently annotated by two observers, and inter-observer variability was assessed. A DL model was trained to segment left ventricle blood pool and myocardium. Average (A), lower quartile (LQ), median (M), and upper quartile (UQ) were computed for the myocardial pixels and employed in classification by applying cutoffs or in ML. Dice similarity coefficient (DICE) and mean absolute percentage error evaluated segmentation performance. Bland-Altman plots assessed inter-user and model-observer agreement. Receiver operating characteristic analysis determined optimal cutoffs. Pearson correlation compared features from model and manual segmentations. F1-score, precision, and recall evaluated classification performance. Wilcoxon test assessed differences between classification methods, with p < 0.05 considered statistically significant. Results 144 subjects were split into training (100), validation (15) and evaluation (29) subsets. Segmentation model achieved a DICE of 85.4%, surpassing inter-observer agreement. Random forest applied to all features increased F1-score (92.7%, p < 0.001). Conclusion DL facilitates segmentation of T1/ T2 maps. Combining multiple features with ML improves disease detection.

Out-of-Distribution Detection Methods Answer the Wrong Questions

To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained on in-distribution data. In this paper, we critically re-examine this popular family of OOD detection procedures, and we argue that these methods are fundamentally answering the wrong questions for OOD detection. There is no simple fix to this misalignment, since a classifier trained only on in-distribution classes cannot be expected to identify OOD points; for instance, a cat-dog classifier may confidently misclassify an airplane if it contains features that distinguish cats from dogs, despite generally appearing nothing alike. We find that uncertainty-based methods incorrectly conflate high uncertainty with being OOD, while feature-based methods incorrectly conflate far feature-space distance with being OOD. We show how these pathologies manifest as irreducible errors in OOD detection and identify common settings where these methods are ineffective. Additionally, interventions to improve OOD detection such as feature-logit hybrid methods, scaling of model and data size, epistemic uncertainty representation, and outlier exposure also fail to address this fundamental misalignment in objectives. We additionally consider unsupervised density estimation and generative models for OOD detection, which we show have their own fundamental limitations.

DigiT4TAF -- Bridging Physical and Digital Worlds for Future Transportation Systems

In the future, mobility will be strongly shaped by the increasing use of digitalization. Not only will individual road users be highly interconnected, but also the road and associated infrastructure. At that point, a Digital Twin becomes particularly appealing because, unlike a basic simulation, it offers a continuous, bilateral connection linking the real and virtual environments. This paper describes the digital reconstruction used to develop the Digital Twin of the Test Area Autonomous Driving-Baden-W\"urttemberg (TAF-BW), Germany. The TAF-BW offers a variety of different road sections, from high-traffic urban intersections and tunnels to multilane motorways. The test area is equipped with a comprehensive Vehicle-to-Everything (V2X) communication infrastructure and multiple intelligent intersections equipped with camera sensors to facilitate real-time traffic flow monitoring. The generation of authentic data as input for the Digital Twin was achieved by extracting object lists at the intersections. This process was facilitated by the combined utilization of camera images from the intelligent infrastructure and LiDAR sensors mounted on a test vehicle. Using a unified interface, recordings from real-world detections of traffic participants can be resimulated. Additionally, the simulation framework's design and the reconstruction process is discussed. The resulting framework is made publicly available for download and utilization at: https://digit4taf-bw.fzi.de The demonstration uses two case studies to illustrate the application of the digital twin and its interfaces: the analysis of traffic signal systems to optimize traffic flow and the simulation of security-related scenarios in the communications sector.

A Novel Tuning Method for Real-time Multiple-Object Tracking Utilizing Thermal Sensor with Complexity Motion Pattern

Multi-Object Tracking in thermal images is essential for surveillance systems, particularly in challenging environments where RGB cameras struggle due to low visibility or poor lighting conditions. Thermal sensors enhance recognition tasks by capturing infrared signatures, but a major challenge is their low-level feature representation, which makes it difficult to accurately detect and track pedestrians. To address this, the paper introduces a novel tuning method for pedestrian tracking, specifically designed to handle the complex motion patterns in thermal imagery. The proposed framework optimizes two-stages, ensuring that each stage is tuned with the most suitable hyperparameters to maximize tracking performance. By fine-tuning hyperparameters for real-time tracking, the method achieves high accuracy without relying on complex reidentification or motion models. Extensive experiments on PBVS Thermal MOT dataset demonstrate that the approach is highly effective across various thermal camera conditions, making it a robust solution for real-world surveillance applications.

AI Meets Maritime Training: Precision Analytics for Enhanced Safety and Performance

Traditional simulator-based training for maritime professionals is critical for ensuring safety at sea but often depends on subjective trainer assessments of technical skills, behavioral focus, communication, and body language, posing challenges such as subjectivity, difficulty in measuring key features, and cognitive limitations. Addressing these issues, this study develops an AI-driven framework to enhance maritime training by objectively assessing trainee performance through visual focus tracking, speech recognition, and stress detection, improving readiness for high-risk scenarios. The system integrates AI techniques, including visual focus determination using eye tracking, pupil dilation analysis, and computer vision; communication analysis through a maritime-specific speech-to-text model and natural language processing; communication correctness using large language models; and mental stress detection via vocal pitch. Models were evaluated on data from simulated maritime scenarios with seafarers exposed to controlled high-stress events. The AI algorithms achieved high accuracy, with ~92% for visual detection, ~91% for maritime speech recognition, and ~90% for stress detection, surpassing existing benchmarks. The system provides insights into visual attention, adherence to communication checklists, and stress levels under demanding conditions. This study demonstrates how AI can transform maritime training by delivering objective performance analytics, enabling personalized feedback, and improving preparedness for real-world operational challenges.

SComCP: Task-Oriented Semantic Communication for Collaborative Perception

Reliable detection of surrounding objects is critical for the safe operation of connected automated vehicles (CAVs). However, inherent limitations such as the restricted perception range and occlusion effects compromise the reliability of single-vehicle perception systems in complex traffic environments. Collaborative perception has emerged as a promising approach by fusing sensor data from surrounding CAVs with diverse viewpoints, thereby improving environmental awareness. Although collaborative perception holds great promise, its performance is bottlenecked by wireless communication constraints, as unreliable and bandwidth-limited channels hinder the transmission of sensor data necessary for real-time perception. To address these challenges, this paper proposes SComCP, a novel task-oriented semantic communication framework for collaborative perception. Specifically, SComCP integrates an importance-aware feature selection network that selects and transmits semantic features most relevant to the perception task, significantly reducing communication overhead without sacrificing accuracy. Furthermore, we design a semantic codec network based on a joint source and channel coding (JSCC) architecture, which enables bidirectional transformation between semantic features and noise-tolerant channel symbols, thereby ensuring stable perception under adverse wireless conditions. Extensive experiments demonstrate the effectiveness of the proposed framework. In particular, compared to existing approaches, SComCP can maintain superior perception performance across various channel conditions, especially in low signal-to-noise ratio (SNR) scenarios. In addition, SComCP exhibits strong generalization capability, enabling the framework to maintain high performance across diverse channel conditions, even when trained with a specific channel model.