Ústav počítačové grafiky a multimédií

Browse

Now showing 1 - 5 of 12

LMVSegRNN and Poseidon3D: Addressing Challenging Teeth Segmentation Cases in 3D Dental Surface Orthodontic Scans
(MDPI, 2024-10-01) Kubík, Tibor; Španěl, Michal
The segmentation of teeth in 3D dental scans is difficult due to variations in teeth shapes, misalignments, occlusions, or the present dental appliances. Existing methods consistently adhere to geometric representations, omitting the perceptual aspects of the inputs. In addition, current works often lack evaluation on anatomically complex cases due to the unavailability of such datasets. We present a projection-based approach towards accurate teeth segmentation that operates in a detect-and-segment manner locally on each tooth in a multi-view fashion. Information is spatially correlated via recurrent units. We show that a projection-based framework can precisely segment teeth in cases with anatomical anomalies with negligible information loss. It outperforms point-based, edge-based, and Graph Cut-based geometric approaches, achieving an average weighted IoU score of 0.971220.038 and a Hausdorff distance at 95 percentile of 0.490120.571 mm. We also release Poseidon's Teeth 3D (Poseidon3D), a novel dataset of real orthodontic cases with various dental anomalies like teeth crowding and missing teeth.
Orbis Pictus: Zpřístupnění netextových dat z digitálních knihoven
(Slovak Centre of Scientific and Technical Information, 2024-10-25) Lehečka, Dalibor; Jebavý, Filip; Kersch, Filip; Pavčík, Filip; Jana, Hrzinová; Fremrová, Květa; Kišš, Martin; Lhoták, Martin; Dvořáková, Martina; Bežová, Michaela; Hradiš, Michal; Žabička, Petr; Jiroušek, Václav
Účel - Projekt "Orbis Pictus - oživení knihy pro kulturní a kreativní odvětví" si klade za cíl zpřístupnit netextový obsah českých digitálních knihoven, který je ve srovnání s textovými daty obtížně dosažitelný a neprohledatelný. Tento článek přináší přehled plánovaných výstupů projektu s důrazem na klíčové výsledky dosažené v prvních dvou letech. Metody - Zpřístupnění netextových objektů v digitalizovaných dokumentech lze rozdělit na tři úlohy: detekci, popis a vyhledání. Identifikaci, lokalizaci a kategorizaci objektů zajistí nástroj AnnoPage, který umožní extrakci popisů objektů a jejich uložení ve standardizovaném formátu. V dalších fázích projektu naváže na AnnoPage nástroj PeopleGator, který identifikuje osoby na fotografiích či kresbách a umožní propojení dokumentů s vyobrazením stejné osoby a vytvoření databáze identifikovaných osob. Projekt bude zakončen softwarovým řešením integrujícím všechny vyvinuté nástroje. Výsledky - V prvních dvou letech projektu byla vytvořena metodika pro zpracování obrazových dokumentů. Ta popisuje způsob detekce netextových objektů, jejich rozdělení do 25 kategorií a zápis informací pomocí mezinárodních standardů, čímž pokládá základ pro nástroj AnnoPage. K detekci objektů je využíván detektor trénovaný na vlastní datové sadě. Detekované objekty jsou popsány pomocí vektorových reprezentací a textových popisů. Originalita/hodnota - Výstupy projektu budou integrovány do České digitální knihovny, což umožní využívání vyvinutých nástrojů širokému spektru knihoven, které platforma agreguje. Orbis Pictus je unikátní projekt v oblasti digital humanities díky rozsáhlému shromáždění netextových dat. Výsledky najdou uplatnění nejen v identifikaci objektů a metadat, ale i ve výzkumu a kulturním a kreativním průmyslu, kde mohou zpřístupněné objekty sloužit jako inspirace pro marketing, vzdělávání, gamifikaci nebo umělou inteligenci.
Exploring the benefits and challenges of AI-driven large language models in gastroenterology: Think out of the box
(PALACKY UNIV, MEDICAL FAC, 2024-12-01) Král, Jan; Hradiš, Michal; Bužga, Marek; Kunovský, Lumír
Artificial Intelligence (AI) has evolved significantly over the past decades, from its early concepts in the 1950s to the present era of deep learning and natural language processing. Advanced large language models (LLMs), such as Chatbot Generative Pre-Trained Transformer (ChatGPT) is trained to generate human-like text responses. This technology has the potential to revolutionize various aspects of gastroenterology, including diagnosis, treatment, education, and The benefits of using LLMs in gastroenterology could include accelerating diagnosis and treatment, providing personalized care, enhancing education and training, assisting in decision-making, and improving communication with patients. However, drawbacks and challenges such as limited AI capability, training on possibly biased data, data errors, security and privacy concerns, and implementation costs must be addressed to ensure the responsible and effective use of this technology. The future of LLMs in gastroenterology relies on the ability to process and analyse large amounts of data, identify patterns, and summarize information and thus assist physicians in creating personalized treatment plans. As AI advances, LLMs will become more accurate and efficient, allowing for faster diagnosis and treatment of gastroenterological conditions. Ensuring effective collaboration between AI developers, healthcare professionals, and regulatory bodies is essential for the responsible and effective use of this technology. By finding the right balance between AI and human expertise and addressing the limitations and risks associated with its use, LLMs can play an increasingly significant role in gastroenterology, contributing to better patient care and supporting doctors in their work.
Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals
(Springer Nature, 2024-11-12) Pešán, Jan; Juřík, Vojtěch; Růžičková, Alexandra; Svoboda, Vojtěch; Janoušek, Oto; Němcová, Andrea; Bojanovská, Hana; Aldabaghová, Jasmína; Kyslík, Filip; Vodičková, Kateřina; Sodomová, Adéla; Bartys, Patrik; Chudý, Peter; Černocký, Jan
Early identification of cognitive or physical overload is critical in fields where human decision making matters when preventing threats to safety and property. Pilots, drivers, surgeons, and operators of nuclear plants are among those affected by this challenge, as acute stress can impair their cognition. In this context, the significance of paralinguistic automatic speech processing increases for early stress detection. The intensity, intonation, and cadence of an utterance are examples of paralinguistic traits that determine the meaning of a sentence and are often lost in the verbatim transcript. To address this issue, tools are being developed to recognize paralinguistic traits effectively. However, a data bottleneck still exists in the training of paralinguistic speech traits, and the lack of high-quality reference data for the training of artificial systems persists. Regarding this, we present an original empirical dataset collected using the BESST experimental protocol for capturing speech signals under induced stress. With this data, our aim is to promote the development of pre-emptive intervention systems based on stress estimation from speech.
Pessimistic Off-Policy Optimization for Learning to Rank
(IOS Press, 2024-10-21) Čief, Matej; Kompan, Michal
Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are recommended and thus logged more frequently than others. This is further perpetuated when recommending a list of items, as the action space is combinatorial. To address this challenge, we study pessimistic off-policy optimization for learning to rank. The key idea is to compute lower confidence bounds on parameters of click models and then return the list with the highest pessimistic estimate of its value. This approach is computationally efficient, and we analyze it. We study its Bayesian and frequentist variants and overcome the limitation of unknown prior by incorporating empirical Bayes. To show the empirical effectiveness of our approach, we compare it to off-policy optimizers that use inverse propensity scores or neglect uncertainty. Our approach outperforms all baselines and is both robust and general.

Browse

Recent Submissions