News

Glad to announce that our papers, "Semantically Conditioned Prompts for Visual Recognition under Missing Modality Scenarios" (with V. Pipoli, F. Bolelli, S. Sarto, M. Cornia, C. Grana, R. Cucchiara and E. Ficarra) and "Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries" (with R. Amoroso, G. Zhang, R. Koner, R. Cucchiara, V. Tresp) have been accepted at WACV 2025!

Our paper, "Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments", has been accepted to NeurIPS 2024, Datasets and Benchmarks track!

Today we are introducing LLaVA-MORE, a family of models that enhances LLaVA by integrating LLaMA 3.1 as the language model. Check out our Github repo!

Our paper, "Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization", has been accepted for oral presentation to BMVC 2024!

We have open research grant positions within the PRIN projects "MUCES - a Multimedia platform for Content Enrichment and Search in audiovisual archives" and "MUSMA: Multimedia Understanding meets Social Media Analysis". If you are interested, please get in touch!

Our proposal MINERVA, submitted to the DIGITAL-EUROHPC-JU-2023-AISC-03-01 call, and coordinated by CINECA, has been successfully approved!

Glad to announce that we have three papers accepted at ECCV 2024: "Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models", "Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities" and "BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues". 

Our paper, "The Revolution of Multimodal Large Language Models: A Survey", has been accepted to the ACL 2024 Findings!

Glad to announce that I will be organizing three workshops at ECCV 2024: "Computational Aspects of Deep Learning" (CADL) with NVIDIA, "TWYN: Trust What You learN. 1st Workshop on Trustworthiness in Computer Vision" with Leonardo SpA, and AI4DH "Artificial Intelligence for Digital Humanities" with UNIMC. Details soon to follow!

Our paper "Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation" (with L. Barsellotti, R. Amoroso, M. Cornia, R. Cucchiara) has been accepted at CVPR 2024! [project page, video, arxiv]

Our paper "Mapping High-level Semantic Regions in Indoor Environments without Object Recognition" (with R. Bigazzi, S. Kousik, R. Cucchiara and M. Pavone) has been accepted as oral to ICRA 2024!

I am co-organizing the second International Workshop on DeepFake Analysis and Detection, which will be held in conjunction with CVPR 2024. See the website (www.dfad.unimore.it) for more!

I have been appointed as Associate Editor for Pattern Recognition.

I will serve as Area Chair for ACM Multimedia 2024. The deadline for paper submission is 12th April 2024.

Our paper "Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets" (with M. Cornia, G. Fiameni, R. Cucchiara) has been accepted to IJCV!

Two papers accepted on semantic (and open-vocabulary) segmentation at WACV 2024. Thanks to R. Amoroso, L. Barsellotti, R. Cucchiara, M. Bernhard, Y. Kindermann, M. Schubert and V. Tresp!

Our PRIN 2022 project "MUCES - a MUltimedia platform for Content Enrichment and Search in audiovisual archives" (with F. Carrara) has been accepted!

We are glad to announce that our paper "With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning" has been accepted to ICCV 2023.

Our PRIN 2022 project "MUSMA: Multimedia Understanding meets Social Media Analysis" (with G. Serra and W. Quattrociocchi) has been accepted!

I am co-organizing the first International Workshop on DeepFake Analysis and Detection, which will be held in conjunction with ICCV 2023. See the website for more. Paper submission deadline is July, 17th AoE.

I will be delivering for the International AI Doctoral Academy (AIDA) the e-lecture:  “From Images to Text: New forms of Human-AI Interaction”, on May 16th, 2023 17:00 -18:00 CET. See details in: http://www.i-aida.org/ai-lectures/

You can join for free using the zoom link: link & Password: 148148

I will serve as Area Chair to the 30th ACM International Conference on Multimedia. The deadline for paper submission is 30th April 2023.

Our Modena Elllis Unit will is organizing a Summer School of the Ellis network this year, on September 18th to 25th, at Modena Technopole. See the website for more.

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.

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

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)!

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.

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.

I am co-organizing the first International Workshop on Artificial Intelligence for Digital Humanities, which will be held in conjunction with ICIAP 2021. See the website for more.

I will participate as Area Chair to the 29th ACM International Conference on Multimedia. The deadline for paper submission is 31st March 2022.

Our paper "Focus on Impact: Indoor Exploration with Intrinsic Motivation" has been accepted to ICRA 2022 and IEEE RA-L. Read it on ArXiv.

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!

I will serve as Associate Editor for ICPR 2022.

Happy to announce that I will be joining the ECCV 2022 organizing team as Communications Chair. 

📣 Update: the official website of ECCV 2022 is out, with deadlines.

We have a three-years Early-Stage Researcher/PhD position on the Integration of vision and language for human-robot interaction, inside the MSCA project PERSEO. See the call for information on salary and how to apply.

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

I will serve as Associate Editor for the specialty section in Pattern Recognition of Frontiers in Artificial Intelligence.

Our paper "Video action detection by learning graph-based spatio-temporal interactions" has been accepted to Computer Vision and Image Understanding! You can read the full article here.

Our submission "Learning to Select: A Fully Attentive Approach for Novel Object Captioning" has been accepted at ICMR 2021.

Our submission "More Efficient and Accurate Video Networks: A New Approach to Maximize the Accuracy/Computation Tradeoff" has been accepted for oral presentation at NVIDIA GTC 2021, which will take place online on April 12 -16. Watch the talk.

I will participate as Area Chair to the 29th ACM International Conference on Multimedia. The deadline for paper submission is Apr. 10, 2021.

Our paper "Video action detection by learning graph-based spatio-temporal interactions" has been accepted to Computer Vision and Image Understanding! You can read the full article here.

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.

Together with NVAITC, we are organizing the first Workshop on Computational Aspects of Deep Learning (CADL), which will be hosted at ICPR 2020. See the website for more.

ICPR invites researchers to present live demonstration of their research results and systems. Demos are intended as real, practical, and possibly interactive proofs of the presenters’ research ideas and scientific or engineering contributions. They should provide the audience the opportunity to discuss working systems, applications and prototypes based on leading edge research, and to discuss and interact in first person with the researchers presenting the demo. See the call.

We are presenting our work on image captioning at CVPR 2020. Take a look at the video presentation, read the paper and share code!

The Galleria Estense of Modena, in partnership with AImageLab, is organizing virtual tours that let visitors walk through the halls of the art gallery without leaving their homes. See the press releases on Gazzetta di Modena and Modena in Diretta.

I have been appointed as Associate Editor at Pattern Recognition Letters.

With a CIDEr-D of 1.321, our architecture for image captioning is first on COCO Captioning. See the leaderboard.

On September 27th I will give an invited talk at the "Modena Smart Life" festival, on Vision, Language and Embodied AI. See the program of the event for further details.

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

From September, 13th to 29th you can discover your doppelgänger in art with our interactive face similarity demo.
See the Gallerie Estensi website for more.

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.

See the abstract and program on the tutorial page.