Team members Andrea PRATI, PO, CoordinatorVittorio BERNUZZI, Research fellowMassimo BERTOZZI, PAClaudio FERRARI, RTD-aTommaso FONTANINI, Research fellowLeonardo ROSSI, Research fellowhttp://implab.ce.unipr.it
The research activity of IMP Lab is related to Computer Vision, Image Processing and Pattern Recognition with large use of machine learning and deep learning techniques. The most active research activities are related to:Geometric deep learningGenerative Adversarial networkConvolutional Neural networkUnsupervised, semi-supervised and self-supervised learningExplainability and controllability of deep learning architectures These researches have been applied to several projects, both with industries and related to national and international fundings. Current research is focused on:Generative models for unsupervised and controllable manipulation of factors of variations in imagesMask-to-face generation with automatic learned mask swappingsTeacher-student two-stage CNNs for instance segmentation Contact person: Andrea Prati – andrea.prati@unipr.it
Recent Research Projects 2022-2024: Project “LEGO.AI: LEarning the Geometry of knOwledge in AI systems”, (funds of the Italian Minsitry of Research, PRIN 2020 programme, Universities of Roma "La Sapienza", Trento, Catania)2022: Project “ROADSTER: ROAd Digital Sustainable Twins in Emilia-Romagna: artificial intelligence for industrial areas” (funds Fondazione IFAB Call for Projects 2021)
Selected publications G. Gualdi, A. Prati, R. Cucchiara, “Multi-Stage Particle Windows for Fast and Accurate Object Detection”, in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, n. 8, pp. 1589-1604, August 2012S. Calderara, A. Prati, R. Cucchiara, “Integrate tool for online analysis and offline mining of people trajectories”, in IET Computer Vision journal, vol. 6, n. 4, pp. 334-347, July 2012P. Piccinini, A. Prati, R. Cucchiara, “Real-time Object Detection and Localization with SIFT-based Clustering”, in Image and Vision Computing, vol. 30, n. 8, pp. 573-587, August 2012P. Piccinini, R. Gamberini, A. Prati, B. Rimini, R. Cucchiara, “An Automated Picking Workstation for Healthcare Applications”, in Computers & Industrial Engineering, vol. 64, n. 2, pp. 653-668, 2013M. Fornaciari, A. Prati, R. Cucchiara, “A Fast and Effective Ellipse Detector for Embedded Vision Applications”, in Pattern Recognition, vol. 47, pp. 3693-3708, 2014A. Prati, F. Qureshi, “Integrating Consumer Smart Cameras into Camera Networks: Opportunities and Obstacles”, in IEEE Computer, vol. 47, no. 5, pp. 45-51, 2014I. Huerta, C. Fernández, C. Segura, J. Hernando, A. Prati, “A deep analysis on age estimation”, in Pattern Recognition Letters, vol. 68, pag. 239-249, 2015Y.T. Tesfaye, E. Zemene, M. Pelillo, A. Prati, “Multi-object tracking using dominant sets”, in IET Computer Vision, vol. 10, no. 4, pp. 289-298, 2016V. Renò, N. Mosca, M. Nitta, T. D’Orazio, C. Guaragnella, D. Campagnoli, A. Prati, E. Stella, “A technology platform for automatic high-level tennis game analysis”, in Computer Vision and Image Understanding, vol. 159, pp. 164-175, June 2017E. Zemene, Y. Tariku, H. Idrees, A. Prati, M. Pelillo, M. Shah, “Large-scale Image Geo-Localization Using Dominant Sets”, in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, n. 1, pp. 148-161, January 2019A. Prati, C. Shan, K. Wang, “Sensors, Vision and Networks: from video surveillance to activity recognition and health monitoring”, in Journal of Ambient Intelligence and Smart Environments, vol. 11, n. 1, pp. 5-22, January 2019 L. Donati, S. Cesano, A. Prati, “A complete hand-drawn sketch vectorization framework”, in Multimedia Tools and Applications, vol. 78, no. 14, pp. 19083-19113, Springer Science+Business Media B.V, ISSN 1380-7501, 2019Y. Tariku, E. Zemene, A. Prati, M. Pelillo, M. Shah, “Multi-Target Tracking in Multiple Non-Overlapping Cameras using Fast-Constrained Dominant Sets”, in International Journal of Computer Vision, vol. 127, pp. 1303-1320, 2019 L. Donati, E. Iotti, G. Mordonini, A. Prati, “Fashion Product Classification Through Deep Learning and Computer Vision”, in MDPI Applied Sciences, vol. 9, n. 7, 2019T. Fontanini, E. Iotti, L. Donati, A. Prati, “MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning”, in Special Issue on “Deep Neural Network Representation and Generative Adversarial Learning” of Neural Network journal, vol. 131, pp. 185-200, 2020F. Magliani, L. Sani, S. Cagnoni, A. Prati, “Diffusion Parameters Analysis in a Content-Based Image Retrieval task for Mobile Vision”, in Special Issue on “Cooperative Camera Networks” of MDPI Sensors journal, 20(16), 4449, August 2020L. Donati, T. Fontanini, F. Tagliaferri, A. Prati, “An energy saving road sweeper using deep vision for garbage detection”, in MDPI Applied Sciences, vol. 10, n. 22, 2020F. Magliani, T. Fontanini, A. Prati, “Bag of Indexes: a Multi-Index Scheme for Efficient Approximate Nearest Neighbor Search”, in Multimedia Tools and Applications, pp. 1-22, 2021L. Donati, E. Iotti, A. Prati, “A Real-Time Approach for Automatic Food Quality Assessment based on Shape Analysis”, in International Journal of Computational Intelligence and Applications, vol. 20, 2021F. Magliani, A. Prati, “LSH kNN Graph for Diffusion on Image Retrieval”, in Information Retrieval journal, 2021