I am a PostDoc Researcher at FBK (Fondazione Bruno Kessler) in the Data and Knowledge Management Unit led by Prof. Luciano Serafini. I obtained a Ph.D. with Flying Colors in Brain, Mind and Computer Science (BMCS) at the University of Padova (Italy). I am part of the "Visual Intelligence and Machine Perception Group" (VIMP) led by Professor Lamberto Ballan. I'm primarily interested in Embodied AI, with a strong focus on developing autonomous agents for ObjectGoal, MultiObjectGoal, and Social Navigation. Previously I obtained a Master's cum Laude in computer science from the University of Padua and a Bachelor's in computer science from the University of Parma.
Email: tommaso.campari [at] fbk.eu
[July 2023] "Exploiting socially-aware tasks for embodied social navigation" accepted at ICCV2023 [PDF]
[March 2023] "Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions" accepted at IJCAI2023 [PDF]
[March 2022] "Incremental Learning of Reusable Abstract Models for Object Goal Navigation" accepted at CVPR2022! [ArXiv]
[20/06/2021] My "Memory Driven Approach" for the MultiON challenge obtained 3rd place in the CVPR2021 Embodied AI workshop, here the spotlight video.
[14/09/2020] I am part of the Technical Program Committee at the first "International Workshop on Video Question Answering and Image Question Answering" [Site]
[24/08/2020] "Exploiting Scene-specific Features for ObjectGoal Navigation" pre-printed on ArXiv [PDF]
[03/08/2020] Accepted "Exploiting Scene-specific Features for ObjectGoal Navigation" at the ACVR2020 ECCV Workshop!