Paper accepted as highlight at CVPR 2023 · 03/02/2023

We are glad to announce that our paper "Positive-Augmented Constrastive Learning for Image and Video Captioning Evaluation" has been accepted to CVPR 2023 as highlight paper (top 2.5% of submissions). Arxiv and Github.

Paper accepted at ICRA 2023 · 02/02/2023

Our paper "Embodied Agents for Efficient Exploration and Smart Scene Description" has been accepted to ICRA 2023 (arxiv).

Best paper award at CBMI 2022 · 08/02/2022

Our paper "Retrieval-Augmented Transformer for Image Captioning" has been selected as best paper at the International Conference on Content-based Multimedia Indexing (CBMI 2022)!

Best Student Paper Award at ICIAP 2021 · 05/27/2022

Our paper "Investigating Bidimensional Downsampling in Vision Transformer Models" by Paolo Bruno, Roberto Amoroso, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, and Rita Cucchiara has been selected for the Best Student Paper Award at ICIAP 2021.

Computational Aspects of Deep Learning (CADL) workshop accepted at ECCV · 03/27/2022

Together with NVAITC, we are organizing the second Workshop on Computational Aspects of Deep Learning (CADL), which will be hosted at ECCV 2022. Check out the website.

From Show to Tell: A Survey on Image Captioning accepted at TPAMI · 01/18/2022

Interested in Image Captioning? Our definitive guide to techniques, datasets and variants has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence. Check it out!

ELLIS Scholar · 07/29/2021

I have been elected as an ELLIS Scholar in the ELLIS society, the European Laboratory for Learning and Intelligent Systems.

Interview with La Repubblica · 09/23/2020

I have been interviewed by Jaime D'Alessandro on Rep: Scienze, about Gpt-3 and Transformed-based language models. You can read the article here.

Interview at Smart City on Radio24 · 09/11/2019

I have been interviewed by Maurizio Melis on Radio24. You can hear the podcast of the interview here.

LAMV is being used at Facebook to detect harmful content · 08/05/2019

Our solution for matching and detecting copied videos, published in CVPR 2018, is now being used in production scale at Facebook to detect harmful content.

See the official announcement on the Facebook newsroom website, and the Github repository with the source code.

Universal Captioner: Inducing Content-Style Separation in Vision-and-Language Model Training
M. Cornia, L. Baraldi, G. Fiameni, R. Cucchiara

PDF  

Towards Sustainable Video Modeling: Progressive Architecture Shrinkage for Action Recognition
M. Tomei, L. Baraldi, G. Fiameni, S. Bronzin, R. Cucchiara

Tell Me What To Describe: Fully-Attentive Iterative Networks for Region-Controlled Image and Video Captioning
M. Cornia, L. Baraldi, R. Cucchiara

Multimodal attention networks for low-level vision-and-language navigation
F. Landi, M. Cornia, L. Baraldi, M. Corsini, R. Cucchiara
Computer Vision and Image Understanding

PDF  Code 

From Show to Tell: A Survey on Image Captioning
M. Stefanini, M. Cornia, L. Baraldi, S. Cascianelli, G. Fiameni, R. Cucchiara
IEEE TPAMI

PDF  Project 

Video action detection by learning graph-based spatio-temporal interactions
Matteo Tomei, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, Rita Cucchiara
Computer Vision and Image Understanding

PDF  Code 

SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability
Marcella Cornia, LORENZO BARALDI, Rita Cucchiara
International Conference on Robotics and Automation

PDF 

Meshed-Memory Transformer for Image Captioning
MARCELLA CORNIA, MATTEO STEFANINI, LORENZO BARALDI, Rita CUCCHIARA
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition

PDF  Code 

Explore and Explain: Self-supervised Navigation and Recounting
Roberto Bigazzi, Federico Landi, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara
Proceedings of the 25th International Conference on Pattern Recognition

PDF 

Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters
Federico Landi, Lorenzo Baraldi, Massimiliano Corsini, Rita Cucchiara
BMVC 2019

PDF  Code 

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
CVPR 2019

PDF  Code 

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation
Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
CVPR 2019

PDF  Code 

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara
IEEE TRANSACTIONS ON IMAGE PROCESSING

PDF  Code 

LAMV: Learning to align and match videos with kernelized temporal layers
Lorenzo Baraldi, Matthijs Douze, Rita Cucchiara, Hervé Jégou
CVPR 2018

PDF  Code 

Hierarchical Boundary-Aware Neural Encoder for Video Captioning
Lorenzo Baraldi, Costantino Grana, Rita Cucchiara
CVPR 2017

PDF