Delocalizzare potere. Se Savona impossibile provare con La Spezia. #scusepernonfareilgoverno

An army of Amazon workers around the world listen to and transcribe what users tell Alexa (whether it’s by intent or by accident). The most interesting/intimate recordings are, like with the NSA, shared amongst colleagues for support or laughs. bloomberg.com/news/articles/…

"Governments should use that leverage to demand that companies share data in properly-protected databases with access granted to appropriately insulated, publicly-funded researchers. Industry participation in policy panels should be strictly limited." nature.com/articles/d4158…

nytimes.com/2019/05/09/opi…

If you have used Subversion or Mercurial in your career, you are old. I'm sorry. Welcome.

We show how data-learned sensor fusion strategies can improve accuracy and robustness in deep VIO when dealing with noisy/corrupted data, while adding interpretability. Thu 20, 10:00am #CVPR2019 changhaoc.github.io/selective_sens…

Best paper award at #CVPR2019 main idea: seeing around the corner at non-line-of-sight (NLOS) objects by using Fermat paths, which is a new theory of how NLOS photons follow specific geometric paths. imaging.cs.cmu.edu/fermat_paths/a…

Our work on large scale point cloud segmentation accepted at #cvpr2020. We show that random sampling can achieve SOA performances with a major speedup: github.com/QingyongHu/Ran…

2010: some people put papers on ArXiv 2012: we put papers on ArXiv after peer-review is done 2016: we put papers on ArXiv the day after deadline 2018: we just put stuff on on ArXiv 2020: you wake up with a headache and wonder if you drunk-posted something on ArXiv you will regret

Roger Penrose – awarded this year’s #NobelPrize in Physics – was born in 1931 in Colchester, UK. He is a professor at University of Oxford, UK. maths.ox.ac.uk/people/roger.p…

October 8th 2020: Roger Penrose in a Roger Penrose design mask on the Roger Penrose tiling. Almost worth a #NobelPrize.

The brain's consensus algorithm demonstrated:

Check out this work on large-scale point cloud segmentation by Qingyong Hu et al.: ieeexplore.ieee.org/document/94406…

Our latest work “Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions” @ #ICCV2025 next week (highlight) hsp-iit.github.io/embodied-capti…