Lorenzo Seidenari

Lorenzo Seidenari

Assistant Professor of Computer Engineering

University of Florence

Biography

I am an Associate Professor of Computer Engineering at the Department of Information Engineering of the University of Florence. I obtained my PhD degree working at the Media Integration and Communication Center of University of Florence under the supervision of Prof. Alberto Del Bimbo 2012. I was a visiting scholar at Silvio Savarese Laboratory at University of Michigan (now at Stanford) from February 2013 till August 2013. I was a PostDoc at Visual Information and Media Lab at Media Integration and Communication Center of University of Florence untile January 2018.

My research interests are focused on application of pattern recognition and machine learning to computer vision and specifically in the field of human activity recognition.

I am member of the UNIMORE ELLIS Unit. ELLIS is a European Network of excellence for Artificial Intelligence with the goal of attracting talented researchers in AI and fostering exchanges between units.

I am also co-founder and Scientific Advisor of Small Pixels a startup working on video processing and compression.

Interests
  • Artificial Intelligence
  • Computer Vision
  • Deep Learning
  • Information Retrieval
Education

  • PhD in Computer Engineering, 2012

    University of Florence

  • MEng in Artificial Intelligence, 2008

    University of Florence

Accomplish­ments

ELLIS Scholar
ELLIS Society Jul 2021
Associate Professor Habilitation for Computer Science (01/B1)
MIUR Aug 2018 – Aug 2027
Associate Professor Habilitation for Computer Engineering (09/H1)
MIUR Jul 2018 – Jul 2027

Recent Posts

ACM MM 2024 Area Chair!
I am going to serve again as AC for ACM MultiMedia this year!
Last updated on Apr 14, 2023 0 min read
ACM MM 2024 Area Chair!
BMVC 2024 Area Chair!
I am going to serve again as AC for British Machine Vision Conference (BMVC) this year!
Last updated on Apr 14, 2023 0 min read
BMVC 2024 Area Chair!
BMVC 2023 Area Chair!
I am going to serve again as AC for British Machine Vision Conference (BMVC) this year!
Apr 14, 2023 0 min read
BMVC 2023 Area Chair!

Projects

WILD.AI

WILD.AI

improving WILDlife camera trapping data processing and analytics through Artificial Intelligence

AI4MEDIA

AI4MEDIA

Network of excellence of researchers across Europe.

IMRA-SD

IMRA-SD

Deep Learning for Multiple Trajectory Prediction.

Recent & Upcoming Talks

ACM MM 19 TPC Meeting Workshop
Improving Quality of Compressed Video Using GAN
Jun 19, 2019

Teaching

Generative Models
Second year Master’s Course in A.I. In this course we will cover all about modern deep generative models. We will start from basics on probabilities and deep learning models and then move onto more advanced models.
Sep 19, 2023
Generative Models
Deep Learning Applications - Adversarial Machine Learning
Second year Master’s Course in Artificial Intelligence. In this course’s module we will cover topics regarding the robustness and explainability of Deep Neural Networks. Course material will be available online: (https://e-l.
Aug 19, 2023
Deep Learning Applications - Adversarial Machine Learning
Fundamentals of Computer Programming
First year Bachelor’s Course in Mechanical and Industrial engineering. In this course we learn how to design basic algorithms and how to code such algorithms in the python language. Basic data structures (list, trees), sorting and searching algorithms are covered.
Sep 19, 2022
Fundamentals of Computer Programming
Fundamentals of Machine Learning - Deep Learning
Second year Master’s Course in Computer Engineering. In this course’s module on Deep Learning we will cover the basics of Deep Neural Network, their design and optimization with practical examples in pytorch.
Sep 19, 2022
Fundamentals of Machine Learning - Deep Learning

Featured Publications

January 2023 IEEE Transactions on Pattern Analysis and Machine Intelligence
SMEMO: social memory for trajectory forecasting
Cite Project DOI
August 2022 Pattern Recognition
A Full Data Augmentation Pipeline for Small Object Detection based on Generative Adversarial Networks
PDF Cite Project DOI
June 2020 International Conference on Computer Vision and Pattern Recognition (CVPR)
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
PDF Cite Project Video
January 2020 Proceedings of the 28th ACM International Conference on Multimedia
Increasing Video Perceptual Quality with GANs and Semantic Coding
PDF Cite
January 2017 Proc. of International Conference on Computer Vision
Deep Generative Adversarial Compression Artifact Removal
PDF Cite
January 2017 IEEE Transactions on Image Processing
Spatio-temporal Closed-Loop Object Detection
PDF Cite DOI
January 2014 Transactions on Pattern Analisys and Machine Intelligence
Local Pyramidal Descriptors for Image Recognition
PDF Cite DOI

Recent Publications

Quickly discover relevant content by filtering publications.
Deep Variational Learning for 360 Adaptive Streaming
Quentin Guimard, Lucile Sassatelli, Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
PDF Cite
FLODCAST: Flow and depth forecasting via multimodal recurrent architectures
Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo, others
Cite Project
COMPUTER-IMPLEMENTED METHOD FOR PREDICTING MULTIPLE FUTURE TRAJECTORIES OF MOVING OBJECTS
Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo, others
Cite Project
Explainable Sparse Attention for Memory-Based Trajectory Predictors
Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
Cite
Explaining autonomous driving with visual attention and end-to-end trainable region proposals
Luca Cultrera, Federico Becattini, Lorenzo Seidenari, Pietro Pala, Alberto Del Bimbo
PDF Cite Project
See all publications

Popular Topics

"audio guide" "computer vision" "context recognition" "cultural heritage" "gans" "image retrieval" "real-time enhancement" "video compression" "video quality enhancement" "video streaming" 360 videos action recognition Autonomous Driving Deep Learning forecasting image enhancement image quality assessment Object Detection self-supervised learning Trajectory Prediction

Contact