Davide Abati

I am a senior engineer at Qualcomm AI Research, working on deep learning for efficient video processing with Amirhossein Habibian.

I got my Ph.D. at AimageLab, at the University of Modena and Reggio Emilia, in Italy. I worked under the supervision of Prof. Rita Cucchiara.

Email  /  CV  /  Google Scholar  /  Github

profile photo

I am currently working on efficient video processing, investigating techniques such as conditional computation and distillation to speed up operations over sequences of frames. In my previous Ph.D. life, I have worked on computer vision for automotive applications, out-of-distribution detection and continual learning.

A full publication list can be found on my scholar page.

ResQ: Residual Quantization for Video Perception
Davide Abati, Haitam Ben Yahia, Markus Nagel, Amirhossein Habibian
ICCV, 2023
arXiv  /  bibtex

When processing a video, residuals in frame representations can be processed at a very low integer precision, with very low quantization error.

Region-of-Interest Based Neural Video Compression
Yura Perugachi Diaz, Guillaume Sautière, Davide Abati, Yang Yang, Amirhossein Habibian, Taco Cohen
BMVC, 2022 (Oral presentation)
arXiv  /  bibtex

Enabling neural based video codecs to improve distortion within regions of interest, while spending less bits on background areas.

Delta Distillation for Efficient Video Processing
Amirhossein Habibian, Haitam Ben Yahia, Davide Abati, Efstratios Gavves, Fatih Porikli
ECCV, 2022
arXiv  /  bibtex  /  code

Instead of distilling neural networks activations, we teach a student network to regress their temporal differences, allowing an improved cost-performance tradeoff.

Efficient Video Super Resolution by Gated Local Self Attention
Davide Abati, Amir Ghodrati, Amirhossein Habibian
BMVC, 2021

An efficient frame alignment operator for Video Super Resolution based on local self attention. Alignment is carried out only at specific locations as specified by a learnable gating function.

Skip-Convolutions for Efficient Video Processing
Amirhossein Habibian, Davide Abati, Taco Cohen, Babak Ehteshami Bejnordi
CVPR, 2021
arXiv  /  bibtex  /  code

By selectively applying convolutions only on locations that carry meaningful information, the computational cost of neural networks on video can be reduced by 4~5 times.

Dark Experience for General Continual Learning: a Strong, Simple Baseline
Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, Simone Calderara
NeurIPS, 2020
arXiv  /  bibtex  /  code

We tackle general continual learning, where an agent is required to learn multiple tasks in a sequence under minimal assumptions about their nature. We run an extensive comparison of many existing methods and introduce a simple model based on knowledge distillation outperforming all of them.

Conditional Channel Gated Networks for Task-Aware Continual Learning
Davide Abati, Jakub Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, Babak Ehteshami Bejnordi
CVPR, 2020 (Oral presentation)
arXiv  /  bibtex  /  talk  /  lecture

A continual learning model based on the framework of conditional computation.

Latent Space Autoregression for Novelty Detection
Davide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara
CVPR, 2019
arXiv  /  code  /  poster  /  bibtex

Applying autoregression in an autoencoder's latent space increases its out-of-distribution detection capabilities.

Predicting the Driver's Focus of Attention: the DR(eye)VE Project
Andrea Palazzi, Davide Abati, Francesco Solera, Simone Calderara, Rita Cucchiara
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
arXiv  /  dataset  /  code  /  video  /  bibtex

We introduce a dataset of human fixations while driving, and a model to predict them given an urban scene.

Past reviewing service (now retired)


  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

  • IEEE Transactions on Multimedia (TMM)

  • IEEE Transactions on Intelligent Transportation Systems (TITS)

  • Neural Networks (NEUNET)

  • Pattern Recognition Letters (PRL)


  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Outstanding reviewer 2021

  • IEEE International Conference on Computer Vision (ICCV)

  • Neural Information Processing Systems (NeurIPS)

  • International Conference on Representation Learning (ICLR)

  • International Conference on Machine Learning (ICML)

  • International Joint Conferences on Artificial Intelligence (IJCAI)


I like this website.