Urban mobility is on the cusp of transformation with the emergence of shared, connected, and cooperative automated vehicles. Yet, for them to be accepted by customers, trust in their punctuality is vital. Many pilot initiatives operate without a fixed schedule, thus enhancing the importance of reliable arrival time (AT) predictions. This study presents an AT prediction system for autonomous shuttles, utilizing separate models for dwell and running time predictions, validated on real-world data from five cities. Alongside established methods such as XGBoost, we explore the benefits of integrating spatial data using graph neural networks (GNN). To accurately handle the case of a shuttle bypassing a stop, we propose a hierarchical model combining a random forest classifier and a GNN. The results for the final AT prediction are promising, showing low errors even when predicting several stops ahead. Yet, no single model emerges as universally superior, and we provide insights into the characteristics of pilot sites that influence the model selection process. Finally, we identify dwell time prediction as the key determinant in overall AT prediction accuracy when autonomous shuttles are deployed in low-traffic areas or under regulatory speed limits. This research provides insights into the current state of autonomous public transport prediction models and paves the way for more data-informed decision-making as the field advances.

The challenge task is about training a sound event detection system using the soft labels, to investigate if leveraging information Classification systems are normally trained by minimizing the from the soft labels is beneficial for the acoustic models. However, cross-entropy between system outputs and reference labels, which the evaluation is done using hard labels and hard metrics. Converting makes the Kullback-Leibler divergence a natural choice for measuring soft labels into binary requires choosing a threshold value, and how closely the system can follow the data. Non-binary references finding a good one is not a trivial task. The most straightforward can arise from various sources, and it is often beneficial to use way is to use 0.5 as the threshold, and this is also how the reference the soft labels for training instead of the binarized data. In addition data for the challenge is binarized. However, as a consequence, six to the cross-entropy based measures, precision and recall provide event classes out of 17 are left out from the evaluation, as there are another perspective for measuring the performance of a classification not enough segments with a soft label value above the threshold.

Generative artificial intelligence (AI) is a widely popular technology that will have a profound impact on society and individuals. Less than a decade ago, it was thought that creative work would be among the last to be automated - yet today, we see AI encroaching on many creative domains. In this paper, we present the findings of a survey study on people's perceptions of text-to-image generation. We touch on participants' technical understanding of the emerging technology, their fears and concerns, and thoughts about risks and dangers of text-to-image generation to the individual and society. We find that while participants were aware of the risks and dangers associated with the technology, only few participants considered the technology to be a personal risk. The risks for others were more easy to recognize for participants. Artists were particularly seen at risk. Interestingly, participants who had tried the technology rated its future importance lower than those who had not tried it. This result shows that many people are still oblivious of the potential personal risks of generative artificial intelligence and the impending societal changes associated with this technology.

This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed prompt engineering for quality, coherence, and diversity. FALL-E was evaluated by an objective measure as well as listening tests in the DCASE 2023 challenge Task 7. The submission achieved the second place on average, while achieving the best score for diversity, second place for audio quality, and third place for class fitness.

Few-shot bioacoustic event detection consists in detecting sound events of specified types, in varying soundscapes, while having access to only a few examples of the class of interest. This task ran as part of the DCASE challenge for the third time this year with an evaluation set expanded to include new animal species, and a new rule: ensemble models were no longer allowed. The 2023 few shot task received submissions from 6 different teams with F-scores reaching as high as 63% on the evaluation set. Here we describe the task, focusing on describing the elements that differed from previous years. We also take a look back at past editions to describe how the task has evolved. Not only have the F-score results steadily improved (40% to 60% to 63%), but the type of systems proposed have also become more complex. Sound event detection systems are no longer simple variations of the baselines provided: multiple few-shot learning methodologies are still strong contenders for the task.

If you'd like to know more about each area, please scroll down.

Scandit is a high-growth tech scaleup from Switzerland with offices in Zurich, Boston, Warsaw, London, Singapore, Tokyo, and Tampere. Our market-leading smart data capture technology enables businesses to use any standard mobile phone to extract data from barcodes, ID documents, text, and objects. To see our software in action, check out our videos. The barcode decoding team at Scandit builds cutting edge decoding solutions. Our mission is to replace every laser scanner in the world with a Scandit powered mobile app.

TAMPERE, Finland--(BUSINESS WIRE)--Tampere, one of Finland's largest cities, is the first in Europe to introduce the Liveable Well-Being City indicators, which Japan uses to measure well-being factors from the perspective of residents in its 27 cities. The indicators will provide important information to support knowledge management on the state of the urban environment, the quality of services and the well-being of citizens. The co-operation between Tampere and Japan will start with the application of the indicators developed in co-operation between Smart City Institute Japan and several research institutes and universities. The model utilises both objective and subjective data collected from urban residents to improve well-being and streamline everyday life. The data is an important foundation for knowledge management: it enables cities to identify their success points and development needs from the residents' perspective.

Scandit is a high-growth tech scaleup from Switzerland with offices in Zurich, Boston, Warsaw, London and Tampere. Our technology for recognizing any barcode with any standard mobile phone is leading in the market today. To see our software in action, check out our videos. We are now looking for a new colleague to join our passionate team of computer vision engineers and help us make the next steps. Together with the other team members, you will be responsible for further improving our scanning performance and making it work in even more challenging conditions by applying and optimizing computer vision and deep learning algorithms.

At Scandit, we develop real-time computer vision solutions for smartphones, wearables and robots that combine modern machine learning approaches with computer vision. To expand our engineering team, we are looking for an engineer who is passionate about machine learning and has a solid track record in it, to work on deep learning applications for our computer vision pipelines. As a part of our growing team in Tampere, you will be working with image processing and computer vision specialists to develop algorithms for real-time barcode decoding, text recognition and object detection for robust real-world performance. The solutions you develop will be running on hundreds of millions of mobile devices on which our real-time computer vision products are deployed today. Scandit enables enterprises and consumers to change the way they interact with everyday objects and augment the physical world with real-time data captured by scanning barcodes and recognizing text, objects, and other visual identifiers using smartphones, tablets, wearables, drones and robots.