Davide Mazzini

Deep Learning Researcher @standardAI, AI enthusiast

[Nick Locascio @Nick_Locascio]

We at @StandardAI are thrilled to introduce StandardSim, a Photorealistic Synthetic #dataset for #AI research in Retail Environments! 25K+ high-resolution multi-view renders with pixel-perfect labels 🚀

https://t.co/weEWOtfWyK
https://t.co/4HqxRSFMIp

[Alfredo Canziani @ ICML @alfcnz]

Learn all about self-supervised learning for vision with @imisra_!

In this lecture, Ishan covers pretext invariant rep learning (PIRL), swapping assign. of views (SwAV), audiovisual discrimination (AVID + CMA), and Barlow Twins redundancy reduction.
https://t.co/HI9qjjjiJt

[Ross Wightman @wightmanr]

After numerous experiments and code tweaks, my #PyTorch EfficientDet impl is finally stable. I've managed to reproduce D0 and D1 COCO training results from scratch on 2-4 modest GPUs -- the only impl I'm aware of that's achieved this. Give it a try https://t.co/xyLzftOh3D

[Joshua Wong 黃之鋒 😷 @joshuawongcf]

Hong Kong's out-of-control police must be stopped.

[Davide Mazzini @DavideMazzini]

@TommiPans @PieBongio Macché capi brigata io ero già un giovane nerd! Prima che i nerd diventassero cool (almeno in Valtellina) @PieBongio invece sapeva difendersi

[Denny Britz @dennybritz]

Many papers have truly interesting ideas, but instead of presenting them clearly, they mix them with all kinds of other params and models to get SOTA, like:

ours = okay
ours + baseline + optimizer X = sota!!!

Can we just agree that a paper can be interesting w/o SOTA?

[Davide Mazzini @DavideMazzini]

@moiseev_igor !

[Davide Mazzini @DavideMazzini]

Our new paper is on Arxiv!
Light3DPose: Real-time Multi-Person 3D Pose Estimation from Multiple Views. With @elmuz and Pietro

Handles 10 cameras at 6 FPS on a single 1080Ti GPU

Arxiv: https://t.co/tYDFR406Qw
Demo Video: https://t.co/6EzFlXDlOc

[Davide Mazzini @DavideMazzini]

@PieBongio @CarloStagnaro Dopo anni di programmazione sento che mi potrebbe capitare.

[Davide Mazzini @DavideMazzini]

@PieBongio @TommiPans Super top!

[Chip Huyen @chipro]

I've been at this startup for less than a month and I've been exposed to so many problems I didn't even know existed. I'm of the increasing belief that everyone should try a startup early in their career, e.g. within the first 3 years/before settling into complacency.

[Davide Mazzini @DavideMazzini]

@TommiPans @andreabeltrama Beh dai dal 12 agosto al 30 ottobre è durato un po'

[Giulia Pompili @giuliapompili]

Mentre a Pechino si celebra la grandezza cinese, a Hong Kong la polizia comincia a sparare. Proiettili veri.

#HongKongProtests #China70years

[Alberto Magnani @AlbMagna17]

Cosa rischia un paese che ha smesso di investire sui giovani? Provo a raccontarlo in Gioventù sprecata, il mio libro per @CastelvecchiEd sulla questione generazionale in Italia. Con i (preziosi) interventi, fra gli altri di @AleRosina68 e @FabioSdogati

[Dan Hendrycks @hendrycks]

Natural Adversarial Examples are real-world and unmodified examples which cause classifiers to be consistently confused. The new dataset has 7,500 images, which we personally labeled over several months.
Paper: https://t.co/L5YMIHZGbz
Dataset and code: https://t.co/4UzQWC4TjG

[David Güera @dgueraco]

The moment has arrived! Say goodbye to bounding boxes. Come see @javiriberaprat presenting at the Terrace Theater our paper “Locating Objects Without Bounding Boxes” at 2:16PM #CVPR2019. We will happy to answer you questions at poster #33

[Adam R. Kosiorek @arkosiorek]

I'm proud to share our work on a new version of capsule networks, called Stacked Capsule Autoencoders, with @sabour_sara, @yeewhye and @geoffreyhinton: https://t.co/tBD8ag0dCF

[Luigi Celona @luigi_celona]

Spatial Sampling Network for Fast Scene Understanding - @DavideMazzini poster #24 almost ready 2 present @ Workshop on Autonomous Driving @cvpr2019
- Pacific Arena Ballroom (main conference center)
#imagingandvisionlaboratory #CVPR2019 #AutonomousVehicles #workshop #LongBeach

[hardmaru @hardmaru]

Adversarial attacks in the real world

[jacopo iacoboni @jacopo_iacoboni]

È in corso la deportazione dei 320 migranti del Cara di Castelnuovo di Porto. Molti lavoravano e erano ormai perfettamente inseriti

Il governo di Lega e Movimento cinque stelle sta facendo questo. Lo combatteremo fino alla fine, con le poche armi che abbiamo. promesso