Radu-Daniel Vatavu

I am a Professor of Computer Science (HDR) at the "Ștefan cel Mare" University of Suceava, where I conduct research in Human-Computer Interaction (HCI), Ambient Intelligence (AmI), Augmented and Mixed Reality (AR/MR), and Entertainment Computing. I direct the Machine Intelligence and Information Visualization Lab (MintViz), an interdisciplinary research laboratory within the MANSiD Research Center.

While I am broadly interested in Human-Computer Interaction, I have focused prioritarily on gesture technology for effective interaction with computing systems, from large public displays to personal mobile and wearable devices and gadgets. I am also interested in accessible computing, and my work has often addressed interaction design for young children or people with visual or motor impairments; see the Research Projects section.

My full Curriculum Vitae is available here

My work has received paper awards at CHI (2023, 2016, 2015), EICS (2019), ICMI (2024, 2023, 2022, 2012), IEEE Pervasive (2022), IMX (2023, 2021, 2020), ISAmI (2021), MobileHCI (2018), TVX (2015), W4A (2022), and has been yearly recognized with Research Awards (2021-2012) by UEFISCDI, the Romanian Executive Agency for Funding Higher Education, Research, Development, and Innovation. For my work on "Smart Pockets," I received in 2019 the "Mihai Draganescu" Award of the Romanian Academy, Romania's highest cultural and scientific forum. In 2022, the $P gesture recognizer received the Ten-Year Technical Impact Award from ACM ICMI. I received the 1st Place Blue Sky Award at ICMI 2023 and ICMI 2024 for my vision papers about non-natural interaction and multimodal interaction with AI-embodied modalities, respectively.

I regularly release, with the help of collaborators, software tools, source code, and datasets that are freely available to download and use for research purposes, such as the $P, $P+, and $Q gesture recognizers, the Agreement Analysis Toolkit (AGATe) for gesture elicitation studies, the Gesture Heatmaps Toolkit (GHoST), or the KeyTime and GATO web apps for predicting touch gesture production times; see the Code, Tools, and Datasets section for all the resources.

• 
  ACM
• 
  DBLP
• 
  Scholar
• 
  ORCID
• 
  Publons
• 
  R-Gate
• 
  Springer
• 
  channel
• 
  LinkedIn