The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV). Three challenges categories are considered: (i) UAV-based Maritime Object Tracking with Re-identification, (ii) USV-based Maritime Obstacle Segmentation and Detection, (iii) USV-based Maritime Boat Tracking. The USV-based Maritime Obstacle Segmentation and Detection features three sub-challenges, including a new embedded challenge addressing efficicent inference on real-world embedded devices. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 195 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi24.

Radiology report generation (RRG) aims to automatically generate free-text descriptions from clinical radiographs, e.g., chest X-Ray images. RRG plays an essential role in promoting clinical automation and presents significant help to provide practical assistance for inexperienced doctors and alleviate radiologists' workloads. Therefore, consider these meaningful potentials, research on RRG is experiencing explosive growth in the past half-decade, especially with the rapid development of deep learning approaches. Existing studies perform RRG from the perspective of enhancing different modalities, provide insights on optimizing the report generation process with elaborated features from both visual and textual information, and further facilitate RRG with the cross-modal interactions among them. In this paper, we present a comprehensive review of deep learning-based RRG from various perspectives. Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions. Overall, the goal of this paper is to serve as a tool for understanding existing literature and inspiring potential valuable research in the field of RRG.

Predictive modeling in healthcare continues to be an active actuarial research topic as more insurance companies aim to maximize the potential of Machine Learning approaches to increase their productivity and efficiency. In this paper, the authors deployed three regression-based ensemble ML models that combine variations of decision trees through Extreme Gradient Boosting, Gradient-boosting Machine, and Random Forest) methods in predicting medical insurance costs. Explainable Artificial Intelligence methods SHapley Additive exPlanations and Individual Conditional Expectation plots were deployed to discover and explain the key determinant factors that influence medical insurance premium prices in the dataset. The dataset used comprised 986 records and is publicly available in the KAGGLE repository. The models were evaluated using four performance evaluation metrics, including R-squared, Mean Absolute Error, Root Mean Squared Error, and Mean Absolute Percentage Error. The results show that all models produced impressive outcomes; however, the XGBoost model achieved a better overall performance although it also expanded more computational resources, while the RF model recorded a lesser prediction error and consumed far fewer computing resources than the XGBoost model. Furthermore, we compared the outcome of both XAi methods in identifying the key determinant features that influenced the PremiumPrices for each model and whereas both XAi methods produced similar outcomes, we found that the ICE plots showed in more detail the interactions between each variable than the SHAP analysis which seemed to be more high-level. It is the aim of the authors that the contributions of this study will help policymakers, insurers, and potential medical insurance buyers in their decision-making process for selecting the right policies that meet their specific needs.

The proliferation of Internet of Things (IoT) devices and applications has generated massive amounts of data that require advanced analytics and machine learning techniques for meaningful insights. However, traditional centralized machine learning models face challenges such as data privacy, security, and scalability. Federated learning (FL) [1] is an emerging technique that addresses these challenges by enabling decentralized model training on distributed data sources while preserving data privacy and security. Despite its promise, FL still faces several technical challenges such as non-iid data distribution, communication overhead, and straggler nodes [2]. In the traditional FL approach, multiple devices work together to train a machine learning model while retaining their data locally, without sharing it with other participating devices; thus, data resides on trusted nodes. This scenario is particularly convenient for IoT applications, where devices often generate sensitive data that must be protected from unauthorized access. Model updates are exchanged between these nodes for aggregation, contributing to enrich the global model without exposing their raw data. Consequently, by retaining their data locally and collaborating on model training through the exchange of model updates, the devices can effectively contribute to the learning process while maintaining data privacy and security. However, this exchange of model updates introduces new security and privacy concerns, as it makes the models potentially vulnerable to various types of attacks. Therefore, FL encounters additional security-related challenges, including data poisoning attacks where malicious nodes inject corrupted or misleading data into the training process, compromising the accuracy of the global model. Model inversion attacks pose another threat, as adversaries aim to reconstruct individual data samples from aggregated model updates, potentially revealing sensitive information. Furthermore, sibyl attacks occur when malicious entities create multiple fake nodes to disproportionately influence the federated learning process, and collusion attacks involve a group of malicious nodes conspiring to manipulate the global model [3]. To address these challenges, recent research has proposed FL solutions that leverage blockchain technology for secure and efficient data sharing, model training, and prototype storage in a distributed environment. Blockchain technology [4], by providing a tamper-proof distributed ledger for storing and sharing data, models, and training results, enables collaboration among multiple parties without the need for a central authority, thereby significantly enhancing data privacy and security in the process.

Neural network ensembles have been effectively used to improve generalization by combining the predictions of multiple independently trained models. However, the growing scale and complexity of deep neural networks have led to these methods becoming prohibitively expensive and time consuming to implement. Low-cost ensemble methods have become increasingly important as they can alleviate the need to train multiple models from scratch while retaining the generalization benefits that traditional ensemble learning methods afford. This dissertation introduces and formalizes a low-cost framework for constructing Subnetwork Ensembles, where a collection of child networks are formed by sampling, perturbing, and optimizing subnetworks from a trained parent model. We explore several distinct methodologies for generating child networks and we evaluate their efficacy through a variety of ablation studies and established benchmarks. Our findings reveal that this approach can greatly improve training efficiency, parametric utilization, and generalization performance while minimizing computational cost. Subnetwork Ensembles offer a compelling framework for exploring how we can build better systems by leveraging the unrealized potential of deep neural networks.

We present a novel approach for saliency prediction in images, leveraging parallel decoding in transformers to learn saliency solely from fixation maps. Models typically rely on continuous saliency maps, to overcome the difficulty of optimizing for the discrete fixation map. We attempt to replicate the experimental setup that generates saliency datasets. Our approach treats saliency prediction as a direct set prediction problem, via a global loss that enforces unique fixations prediction through bipartite matching and a transformer encoder-decoder architecture. By utilizing a fixed set of learned fixation queries, the cross-attention reasons over the image features to directly output the fixation points, distinguishing it from other modern saliency predictors. Our approach, named Saliency TRansformer (SalTR), achieves metric scores on par with state-of-the-art approaches on the Salicon and MIT300 benchmarks.

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising result is further analysed using an attribution method-Integrated Gradients. Using this attribution method, we are able to better understand both quantitatively and qualitatively exactly the nature in which the compression affects the zero-shot recognition accuracy of this model. We evaluate this extensively on CIFAR-10 and STL-10. Our work provides the basis to understand this vulnerability of CLIP and can help us develop more effective methods to improve the robustness of CLIP and other vision-language models.

In the rapidly evolving landscape of human-robot collaboration, effective communication between humans and robots is crucial for complex task execution. Traditional request-response systems often lack naturalness and may hinder efficiency. In this study, we propose a novel approach that employs human-like conversational interactions for vocal communication between human operators and robots. The framework emphasizes the establishment of a natural and interactive dialogue, enabling human operators to engage in vocal conversations with robots. Through a comparative experiment, we demonstrate the efficacy of our approach in enhancing task performance and collaboration efficiency. The robot's ability to engage in meaningful vocal conversations enables it to seek clarification, provide status updates, and ask for assistance when required, leading to improved coordination and a smoother workflow. The results indicate that the adoption of human-like conversational interactions positively influences the human-robot collaborative dynamic. Human operators find it easier to convey complex instructions and preferences, fostering a more productive and satisfying collaboration experience.

Autonomous vehicles (AVs) have the potential to significantly revolutionize society by providing a secure and efficient mode of transportation. Recent years have witnessed notable advancements in autonomous driving perception and prediction, but the challenge of validating the performance of AVs remains largely unresolved. Data-driven microscopic traffic simulation has become an important tool for autonomous driving testing due to 1) availability of high-fidelity traffic data; 2) its advantages of enabling large-scale testing and scenario reproducibility; and 3) its potential in reactive and realistic traffic simulation. However, a comprehensive review of this topic is currently lacking. This paper aims to fill this gap by summarizing relevant studies. The primary objective of this paper is to review current research efforts and provide a futuristic perspective that will benefit future developments in the field. It introduces the general issues of data-driven traffic simulation and outlines key concepts and terms. After overviewing traffic simulation, various datasets and evaluation metrics commonly used are reviewed. The paper then offers a comprehensive evaluation of imitation learning, reinforcement learning, deep generative and deep learning methods, summarizing each and analyzing their advantages and disadvantages in detail. Moreover, it evaluates the state-of-the-art, existing challenges, and future research directions.

Developmental psychologists have long-established the importance of socio-cognitive abilities in human intelligence. These abilities enable us to enter, participate and benefit from human culture. AI research on social interactive agents mostly concerns the emergence of culture in a multi-agent setting (often without a strong grounding in developmental psychology). We argue that AI research should be informed by psychology and study socio-cognitive abilities enabling to enter a culture too. We discuss the theories of Michael Tomasello and Jerome Bruner to introduce some of their concepts to AI and outline key concepts and socio-cognitive abilities. We present The SocialAI school - a tool including a customizable parameterized uite of procedurally generated environments, which simplifies conducting experiments regarding those concepts. We show examples of such experiments with RL agents and Large Language Models. The main motivation of this work is to engage the AI community around the problem of social intelligence informed by developmental psychology, and to provide a tool to simplify first steps in this direction. Refer to the project website for code and additional information: https://sites.google.com/view/socialai-school.