| Rita Cucchiara | |
| Birth Place: | Modena, Italy |
| Fields: | Computer engineering |
| Workplaces: | University of Modena and Reggio Emilia |
| Alma Mater: | University of Bologna University of Ferrara |
| Known For: | Artificial intelligence and deep learning algorithms for human behavior understanding |
| Awards: | 2018 Women in Robotics You Need To Know - Robohub, 2018 Maria Petrou Prize of IAPR, 2016 Facebook Artificial intelligence Research Grant |
Rita Cucchiara (born 1965)[1] is an Italian electrical and computer engineer, and professor in Computer engineering and Science in the Enzo Ferrari Department of Engineering at the University of Modena and Reggio Emilia (UNIMORE) in Italy. She helds the courses of “Computer Architecture” and “Computer Vision and Cognitive Systems”. Cucchiara's research work focuses on artificial intelligence, specifically deep network technologies and computer vision for human behavior understanding (HBU) and visual, language and multimodal generative AI. She is the scientific coordinator of the AImage Lab at UNIMORE and is director of the Artificial Intelligence Research and Innovation Center (AIRI) as well as the ELLIS (European Labs of Learning and Intelligent Systems) Unit at Modena. She was founder and director from 2018 to 2021 of the Italian National Lab of Artificial Intelligence and intelligent systems AIIS of CINI. Cucchiara was also president of the CVPL (Italian Association of Computer Vision, Machine Learning and Pattern Recognition) from 2016 to 2018. Rita Cucchiara is IAPR Fellow since 2006 and ELLIS Fellow since 2020.
Cucchiara received her diploma in classical studies at Liceo Classico "San Carlo" in Modena, Italy in 1983 and then pursued her academic education at the University of Bologna where graduated magna cum laude in 1989 in Electronic and Computer Engineering.[2] Cucchiara completed her PhD in 1992 working on parallel architectures for Image Processing and Robot Vision, neural networks and genetic algorithms for clustering. During the PhD, under the grant of “Progetto finalizzato Robotica” from CNR, she designed a SIMD parallel Computer “GIOTTO” for image processing.[3] Cucchiara became a research assistant at the University of Ferrara from 1993 until 1998,[4] and associate professor in the Enzo Ferrari Department of Computer Science and Engineering at the University of Modena and Reggio Emilia (UNIMORE) in Italy in 1998. In 2005, she was promoted to Full Professor.[5] At UNIMORE, she has been deputy dean of the Engineering Faculty in Modena from 2008 to 2012 and Director of the Inter-departmental center of Research “Softech-ICT” from 2011 to 2018. Since 2021 she is Director of the Center of Artificial Intelligence and innovation AIRI of UNIMORE. She has been Director of the “ICT Platform”, the ICT Council of the high Technology Network of Emilia from 2014 to 2018 ad Delegate of UNIMORE.
Cucchiara's research focuses in Computer Vision and Artificial Intelligence, mainly on computational aspects of deep learning applied to visual, language and multimodal data. Rita Cucchiara pioneered studies in Video Surveillance, and human behavior understanding, since 2003 with the project SakBot (Statistical and knowledge-based object tracking) for detecting moving Object, Ghosts and shadows. She contributed in the collection of several datasets for human understanding, surveillance, and automotive applications, such as the pioneering open platform called ViSOR (Video Surveillance Online Repository) funded by the EU project VidiVideo in 2014,[6] the ALOV++ for single-object tracking together with Arnold Smeulders of University of Amsterdam,[7] the DukeMTMC-Groups dataset defined by Duke University and used for people group tracking,[8] and in 2020 the MotSynth Dataset for pose estimation.[9] Cucchiara's team has also explored the use of egocentric vision and depth cameras in automotive fields, for driver attention analysis in the project Dri(Eye)ve,[10] and for estimating head and shoulder position of humans in images with a neural network architecture called POSEidon+ which takes three images as an input and outputs the 3D pose angles.[11]
Since the beginning of the COVID-19 pandemic, Cucchiara has been modifying and applying her innovations to help with pandemic.[12] Cucchiara and her team had designed a tool able to use artificial intelligence to measure the space between people in a crowd to enforce social distancing regulations in public spaces. Her project is called "Inter-Homines", and is a privacy-preserving methodology for human analysis in 3D space. Since 2018, Cucchiara is working In Generative AI, for generating Saliency maps and text from images. The SAM Saliency Attentive Maps architecture won the LSUN SaliencyChallenge at CVPR 2017, held in Honolulu, Hawaii. The architectures for image captioning and textual description of visual data are used In several applications from fashion analysis to human-robot interaction.
Rita Cucchiara is a member of Board of Directors of Italian Institute of Technology since 2017. member of Advisory Board of Max Planck Institute for Intelligent Systems (Tübingen, Germany) and of the CVC Computer Vision Center (Barcelona, Spain).
Cucchiara has been quoted or had his research featured in various national media outlets, including La Repubbica, Corriere della Sera, Il Sole 24 Ore and Rai Scuola.[17] She parteciapted at several TEDx, such as TEDxOrtygia "AI and Human Beings" in 2019 and TEDxModenaSalon "The Future of Visual Intelligence".
She is author of the book “Intelligenza non e’ Artificiale" (Ed. Mondadori).[18]