Driving is a routine activity for many, but it is far from simple. Drivers deal with multiple concurrent tasks, such as keeping the vehicle in the lane, observing and anticipating the actions of other road users, reacting to hazards, and dealing with distractions inside and outside the vehicle. Failure to notice and respond to the surrounding objects and events can cause accidents. The ongoing improvements of the road infrastructure and vehicle mechanical design have made driving safer overall. Nevertheless, the problem of driver inattention has remained one of the primary causes of accidents. Therefore, understanding where the drivers look and why they do so can help eliminate sources of distractions and identify unsafe attention patterns. Research on driver attention has implications for many practical applications such as policy-making, improving driver education, enhancing road infrastructure and in-vehicle infotainment systems, as well as designing systems for driver monitoring, driver assistance, and automated driving. This report covers the literature on changes in drivers' visual attention distribution due to factors, internal and external to the driver. Aspects of attention during driving have been explored across multiple disciplines, including psychology, human factors, human-computer interaction, intelligent transportation, and computer vision, each offering different perspectives, goals, and explanations for the observed phenomena. We link cross-disciplinary theoretical and behavioral research on driver's attention to practical solutions. Furthermore, limitations and directions for future research are discussed. This report is based on over 175 behavioral studies, nearly 100 practical papers, 20 datasets, and over 70 surveys published since 2010. A curated list of papers used for this report is available at \url{//github.com/ykotseruba/attention_and_driving}.
相關內容
Attention機制最早是在視覺圖像領域提出來的，但是真正火起來應該算是google mind團隊的這篇論文《Recurrent Models of Visual Attention》[14]，他們在RNN模型上使用了attention機制來進行圖像分類。隨后，Bahdanau等人在論文《Neural Machine Translation by Jointly Learning to Align and Translate》 [1]中，使用類似attention的機制在機器翻譯任務上將翻譯和對齊同時進行，他們的工作算是是第一個提出attention機制應用到NLP領域中。接著類似的基于attention機制的RNN模型擴展開始應用到各種NLP任務中。最近，如何在CNN中使用attention機制也成為了大家的研究熱點。下圖表示了attention研究進展的大概趨勢。
Blockchain systems come with a promise of decentralization that often stumbles on a roadblock when key decisions about modifying the software codebase need to be made. This is attested by the fact that both of the two major cryptocurrencies, Bitcoin and Ethereum, have undergone hard forks that resulted in the creation of alternative systems, creating confusion and opportunities for fraudulent activities. These events, and numerous others, underscore the importance of Blockchain governance, namely the set of processes that blockchain platforms utilize in order to perform decision-making and converge to a widely accepted direction for the system to evolve. While a rich topic of study in other areas, governance of blockchain platforms is lacking a well established set of methods and practices that are adopted industry wide. This makes the topic of blockchain governance a fertile domain for a thorough systematization that we undertake in this work. We start by distilling a comprehensive array of properties for sound governance systems drawn from academic sources as well as grey literature of election systems and blockchain white papers. These are divided into seven categories, confidentiality, verifiability, accountability, sustainability, Pareto efficiency, suffrage and liveness that capture the whole spectrum of desiderata of governance systems. We proceed to classify ten well-documented blockchain systems. While all properties are satisfied, even partially, by at least one system, no system that satisfies most of them. Our work lays out a foundation for assessing blockchain governance processes. While it highlights shortcomings and deficiencies in currently deployed systems, it can also be a catalyst for improving these processes to the highest possible standard with appropriate trade-offs, something direly needed for blockchain platforms to operate effectively in the long term.
Graph analytics attract much attention from both research and industry communities. Due to the linear time complexity, the $k$-core decomposition is widely used in many real-world applications such as biology, social networks, community detection, ecology, and information spreading. In many such applications, the data graphs continuously change over time. The changes correspond to edge insertion and removal. Instead of recomputing the $k$-core, which is time-consuming, we study how to maintain the $k$-core efficiently. That is, when inserting or deleting an edge, we need to identify the affected vertices by searching for more vertices. The state-of-the-art order-based method maintains an order, the so-called $k$-order, among all vertices, which can significantly reduce the searching space. However, this order-based method is complicated for understanding and implementation, and its correctness is not formally discussed. In this work, we propose a simplified order-based approach by introducing the classical Order Data Structure to maintain the $k$-order, which significantly improves the worst-case time complexity for both edge insertion and removal algorithms. Also, our simplified method is intuitive to understand and implement; it is easy to argue the correctness formally. Additionally, we discuss a simplified batch insertion approach. The experiments evaluate our simplified method over 12 real and synthetic graphs with billions of vertices. Compared with the existing method, our simplified approach achieves high speedups up to 7.7x and 9.7x for edge insertion and removal, respectively.
With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traor\'e et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be successful, struggle or fail on a target task. Our study leverages this methodology in the context of searching across sensors, including sensor data fusion. In particular, we apply the Fitness Landscape Footprint to the real-world image classification problem of So2Sat LCZ42, in order to identify the most beneficial sensor to our neural network hyper-parameter optimization problem. From the perspective of distributions of fitness, our findings indicate a similar behaviour of the search space for all sensors: the longer the training time, the larger the overall fitness, and more flatness in the landscapes (less ruggedness and deviation). Regarding sensors, the better the fitness they enable (Sentinel-2), the better the search trajectories (smoother, higher persistence). Results also indicate very similar search behaviour for sensors that can be decently fitted by the search space (Sentinel-2 and fusion).
Researchers and practitioners have recently proposed many Microservices Architecture (MSA) patterns and strategies covering various aspects of microservices system life cycle, such as service design and security. However, selecting and implementing these patterns and strategies can entail various challenges for microservices practitioners. To this end, this study proposes decision models for selecting patterns and strategies covering four MSA design areas: application decomposition into microservices, microservices security, microservices communication, and service discovery. We used peer-reviewed and grey literature to identify the patterns, strategies, and quality attributes for creating these decision models. To evaluate the familiarity, understandability, completeness, and usefulness of the decision models, we conducted semi-structured interviews with 24 microservices practitioners from 12 countries across five continents. Our evaluation results show that the practitioners found the decision models as an effective guide to select microservices patterns and strategies.
Responsible Artificial Intelligence (AI) - the practice of developing, evaluating, and maintaining accurate AI systems that also exhibit essential properties such as robustness and explainability - represents a multifaceted challenge that often stretches standard machine learning tooling, frameworks, and testing methods beyond their limits. In this paper, we present two new software libraries - hydra-zen and the rAI-toolbox - that address critical needs for responsible AI engineering. hydra-zen dramatically simplifies the process of making complex AI applications configurable, and their behaviors reproducible. The rAI-toolbox is designed to enable methods for evaluating and enhancing the robustness of AI-models in a way that is scalable and that composes naturally with other popular ML frameworks. We describe the design principles and methodologies that make these tools effective, including the use of property-based testing to bolster the reliability of the tools themselves. Finally, we demonstrate the composability and flexibility of the tools by showing how various use cases from adversarial robustness and explainable AI can be concisely implemented with familiar APIs.
International public health policies increasingly favor mandatory immunization. If its short-term effects on vaccine coverage are well documented, there has been little consideration to its effects on public attitudes towards vaccines. In this paper, we examine Google searches related to vaccines in five countries (Australia, France, Germany, Italy, Serbia) and two American states (California) which experienced at least one vaccine mandate extension in the past decade. We found that the effects of a new mandate implementation heavily depends on the context in each specific country or state. We also observed that there is little indication that the passing of new or extended mandates attenuated public doubt towards vaccines.
Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.
The task of session search focuses on using interaction data to improve relevance for the user's next query at the session level. In this paper, we formulate session search as a personalization task under the framework of learning to rank. Personalization approaches re-rank results to match a user model. Such user models are usually accumulated over time based on the user's browsing behaviour. We use a pre-computed and transparent set of user models based on concepts from the social science literature. Interaction data are used to map each session to these user models. Novel features are then estimated based on such models as well as sessions' interaction data. Extensive experiments on test collections from the TREC session track show statistically significant improvements over current session search algorithms.
Recommender systems play a fundamental role in web applications in filtering massive information and matching user interests. While many efforts have been devoted to developing more effective models in various scenarios, the exploration on the explainability of recommender systems is running behind. Explanations could help improve user experience and discover system defects. In this paper, after formally introducing the elements that are related to model explainability, we propose a novel explainable recommendation model through improving the transparency of the representation learning process. Specifically, to overcome the representation entangling problem in traditional models, we revise traditional graph convolution to discriminate information from different layers. Also, each representation vector is factorized into several segments, where each segment relates to one semantic aspect in data. Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge. In this way, the proposed model can learn interpretable and meaningful representations for users and items. Unlike traditional methods that need to make a trade-off between explainability and effectiveness, the performance of our proposed explainable model is not negatively affected after considering explainability. Finally, comprehensive experiments are conducted to validate the performance of our model as well as explanation faithfulness.
Music recommender systems (MRS) have experienced a boom in recent years, thanks to the emergence and success of online streaming services, which nowadays make available almost all music in the world at the user's fingertip. While today's MRS considerably help users to find interesting music in these huge catalogs, MRS research is still facing substantial challenges. In particular when it comes to build, incorporate, and evaluate recommendation strategies that integrate information beyond simple user--item interactions or content-based descriptors, but dig deep into the very essence of listener needs, preferences, and intentions, MRS research becomes a big endeavor and related publications quite sparse. The purpose of this trends and survey article is twofold. We first identify and shed light on what we believe are the most pressing challenges MRS research is facing, from both academic and industry perspectives. We review the state of the art towards solving these challenges and discuss its limitations. Second, we detail possible future directions and visions we contemplate for the further evolution of the field. The article should therefore serve two purposes: giving the interested reader an overview of current challenges in MRS research and providing guidance for young researchers by identifying interesting, yet under-researched, directions in the field.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191