Urban environments are evolving rapidly in big cities; keeping track of these changes is becoming harder. Information regarding urban features, such as the number of trees, lights, or shops in a particular region, can be crucial for tasks, such as urban planning, commercial campaigns, or inferring various social indicators. StreetScouting is a platform that aims to automate the process of detecting, visualizing, and exporting the urban features of a particular region. Recently, the advent of deep learning has revolutionized the way many computer vision tasks are tackled. In this work, we present StreetScouting, an extensible platform for the automatic detection of particular urban features of interest. StreetScouting utilizes several state-of-the-art computer vision approaches including Cascade R-CNN and RetinaFace architectures for object detection, the ByteTrack method for object tracking, DNET architecture for depth estimation, and DeepLabv3+ architecture for semantic segmentation. As a result, the platform is able to detect and geotag urban features from visual data. The extracted information can be utilized by many commercial or public organizations, eliminating the need for manual inspection.
The vast volume of media content, combined with the costs of manual annotation, challenges scalable codebook analysis and risks reducing decision-making accuracy. This study evaluates the effectiveness of large language models (LLMs) and multi-agent teams in structured media content analysis based on codebook-driven annotation. We construct a dataset of 200 news articles on U.S. tariff policies, manually annotated using a 26-question codebook encompassing 122 distinct codes, to establish a rigorous ground truth. Seven state-of-the-art LLMs, spanning low- to high-capacity tiers, are assessed under a unified zero-shot prompting framework incorporating role-based instructions and schema-constrained outputs. Experimental results show weighted global F1-scores between 0.636 and 0.822, with Claude-3-7-Sonnet achieving the highest direct-prompt performance. To examine the potential of agentic orchestration, we propose and develop a multi-agent system using Meta’s Llama 4 Maverick, incorporating expert role profiling, shared memory, and coordinated planning. This architecture improves the overall F1-score over the direct prompting baseline from 0.757 to 0.805 and demonstrates consistent gains across binary, categorical, and multi-label tasks, approaching commercial-level accuracy while maintaining a favorable cost–performance profile. These findings highlight the viability of LLMs, both in direct and agentic configurations, for automating structured content analysis.
The recent advancements in the field of deep learning have fundamentally altered the manner in which certain challenges and problems are addressed. One area that stands to greatly benefit from such innovations is the realm of urban planning, where the utilization of these tools can facilitate the automatic detection of landscape objects in a given area. However, it must be noted that these data-driven methodologies necessitate significant amounts of training data to attain desired results. This challenge can be mitigated through the application of transfer learning techniques, which reduce the amount of required data and permit the customization of these models through fine-tuning. The present study presents street-level imagery, which can be utilized for fine-tuning and deployment of custom object detectors in urban environments. The dataset comprises 763 images, each accompanied by bounding box annotations for five landscape object classes, including trees, waste bins, recycling bins, shop storefronts, and lighting poles. Furthermore, the dataset includes sequential frame data obtained from a camera mounted on a vehicle, capturing a total of three hours of driving, encompassing various regions within the city center of Thessaloniki.
The damaging effects of hate speech on social media are evident during the last few years, and several organizations, researchers and social media platforms tried to harness them in various ways. Despite these efforts, social media users are still affected by hate speech. The problem is even more apparent to social groups that promote public discourse, such as journalists. In this work, we focus on countering hate speech that is targeted to journalistic social media accounts. To accomplish this, a group of journalists assembled a definition of hate speech, taking into account the journalistic point of view and the types of hate speech that are usually targeted against journalists. We then compile a large pool of tweets referring to journalism-related accounts in multiple languages. In order to annotate the pool of unlabeled tweets according to the definition, we follow a concise annotation strategy that involves active learning annotation stages. The outcome of this paper is a novel, publicly available collection of Twitter datasets in five different languages. Additionally, we experiment with state-of-the-art deep learning architectures for hate speech detection and use our annotated datasets to train and evaluate them. Finally, we propose an ensemble detection model that outperforms all individual models.
16 December 2023 in International Journal on Digital Libraries
The purpose of the current article is to provide an overview of an open-access audiovisual aggregation and search service platform developed for Greek audiovisual content during the OAVA (Open Access AudioVisual Archive) project. The platform allows the search of audiovisual resources utilizing metadata descriptions, as well as full-text search utilizing content generated from automatic speech recognition (ASR) processes through deep learning models. A dataset containing reliable Greek audiovisual content providers and their resources (1710 in total) is created. Both providers and resources are reviewed according to specific criteria already established and used for content aggregation purposes, to ensure the quality of the content and to avoid copyright infringements. Well-known aggregation services and well-established schemas for audiovisual resources have been studied and considered regarding both aggregated content and metadata. Most Greek audiovisual content providers do not use established metadata schemas when publishing their content, nor technical cooperation with them is guaranteed. Thus, a model is developed for reconciliation and aggregation. To utilize audiovisual resources the OAVA platform makes use of the latest state-of-the-art ASR approaches. OAVA platform supports Greek and English speech-to-text models. Specifically for Greek, to mitigate the scarcity of available datasets, a large-scale ASR dataset is annotated to train and evaluate deep learning architectures. The result of the above-mentioned efforts, namely selection of content, metadata, development of appropriate ASR techniques, and aggregation and enrichment of content and metadata, is the OAVA platform. This unified search mechanism for Greek audiovisual content will serve teaching, research, and cultural activities. OAVA platform is available at: https://openvideoarchives.gr/.