Výsledky vyhledávání

Report

For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archives

Autor: Morra, Lia, Santangelo, Antonio, Basci, Pietro, Piano, Luca, Garcea, Fabio, Lamberti, Fabrizio, Leone, Massimo

Publikováno v: Computer Vision and Image Understanding 249 (2024) 104187

Social networks are creating a digital world in which the cognitive, emotional, and pragmatic value of the imagery of human faces and bodies is arguably changing. However, researchers in the digital humanities are often ill-equipped to study these ph

Externí odkaz: http://arxiv.org/abs/2407.03268

Zobrazit plný text záznamu

Report

Toward a Realistic Benchmark for Out-of-Distribution Detection

Autor: Recalcati, Pietro, Garcea, Fabio, Piano, Luca, Lamberti, Fabrizio, Morra, Lia

Publikováno v: 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)

Deep neural networks are increasingly used in a wide range of technologies and services, but remain highly susceptible to out-of-distribution (OOD) samples, that is, drawn from a different distribution than the original training set. A common approac

Externí odkaz: http://arxiv.org/abs/2404.10474

Zobrazit plný text záznamu

Report

HOLMES: HOLonym-MEronym based Semantic inspection for Convolutional Image Classifiers

Autor: Dibitonto, Francesco, Garcea, Fabio, Panisson, André, Perotti, Alan, Morra, Lia

Publikováno v: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1902. Springer, Cham

Convolutional Neural Networks (CNNs) are nowadays the model of choice in Computer Vision, thanks to their ability to automatize the feature extraction process in visual tasks. However, the knowledge acquired during training is fully subsymbolic, and

Externí odkaz: http://arxiv.org/abs/2403.08536

Zobrazit plný text záznamu

Report

Optimal calibration of optical tweezers with arbitrary integration time and sampling frequencies -- A general framework

Autor: Pérez-Garcéa, Laura, Selin, Martin, Ciarlo, Antonio, Magazzu, Alessandro, Pesce, Giuseppe, Sasso, Antonio, Volpe, Giovanni, Castillo, Isaac Pérez, Arzola, Alejandro V.

Optical tweezers (OT) have become an essential technique in several fields of physics, chemistry, and biology as precise micromanipulation tools and microscopic force transducers. Quantitative measurements require the accurate calibration of the trap

Externí odkaz: http://arxiv.org/abs/2305.07245

Zobrazit plný text záznamu