Guglielmo Camporese (gool-yell-moe)

Research Engineer at The Walt Disney Studios

Ph.D. in Brain, Mind and Computer Science

guglielmocamporese [at] gmail [dot] com
bio news publications scholar github linkedin twitter cv extra

Hi there! I'm Guglielmo - here I try to describe sparsely what I do. I'm interested in artificial intelligence, computer vision and art. I worked on video understanding, and currently I'm focused on generative AI and foundation models.

My Experience

02/2024-Present
Research Engineer
The Walt Disney Studios
Zürich, Switzerland
07/2023-01/2024
AI Researcher & Engineer Freelancer
Italy
04-07/2023
Research Intern
Disney Research
Zürich, Switzerland
12/2021-09/2022
Applied Scientist Intern
Amazon Web Services AI Labs
Seattle, WA, USA
06-09/2020
Applied Scientist Intern
Amazon Alexa AI
Turin, Italy
2019-2023
Ph.D. in Brain, Mind and Computer Science
University of Padova, VIMP
Padova, Italy
11/2018-10/2019
Computer Vision Scientist Intern
Aquifi Inc.
Palo Alto, CA, USA
2016-2019
M.Sc. in Telecommunication Engineering
University of Padova
Padova, Italy
2012-2016
B.Sc. in Information Engineering
University of Padova
Padova, Italy

Publications (selected)

* indicates equal contribution.

Empowering Convolutional Neural Nets with MetaSin Activation

F Salehi, T O Aydin, A Gaillard, G Camporese, Y Wang

NeurIPS 2023

[paper] [bib]

Early Action Recognition with Action Prototypes

G Camporese, A Bergamo, X Lin, J Tighe, D Modolo

arXiv 2023

[arxiv] [bib]

Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer

G Camporese, E Izzo, L Ballan

BMVC 2022 (oral spotlight)

CVPRw 2022 (oral spotlight)

[arXiv] [code] [bib] [wicv]

TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction

N Osman, G Camporese, L Ballan

ICASSP 2023 (oral)

[arXiv] [code] [bib]

Conditional Variational Capsule Network for Open Set Recognition

Y Guo*, G Camporese*, W Yang, A Sperduti, L Ballan

ICCV 2021

[arXiv] [paper] [code] [bib]

Improved Robustness to Disfluencies in Rnn-Transducer Based Speech Recognition

V Mendelev, T Raissi, G Camporese, M Giollo

ICASSP 2021

[arXiv] [paper] [Amazon Science Blog] [bib]

SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos

N Osman, G Camporese, P Coscia, L Ballan

ICCVw 2021

[arXiv] [paper] [code] [bib]