Poster & Demo Sessions at the University of Florence

The 7th AI4Media Plenary Meeting was held at the University of Florence, Italy on January 31st and February 1st 2023.

During the event, the AI researchers working in WPs 3, 4,5 and 6 presented their most recent research results through posters and demos, while the media industry partners demonstrated live the demonstrators developed for the seven AI4Media use cases.

A debate space was also provided for the partners to exchange ideas and get to know each other’s work.

Some of the AI techniques and demos presented at the event are presented in short videos available on the project’s YouTube channel. Here’s the list of techniques and applications s presented in these videos:

• XAI-SUM: Explaining Video Summarization Based on the Focus of Attention – Vasileios Mezaris (CERTH)
• Unsupervised Domain Adaptation for Video Violence Detection in the Wild – Luca Ciampi (CNR)
• Truly Media presentation – Danae Tsabouraki (ATC)
• Tracing reuse across a large scale AV archive using Partial Audio Matching – Philo van Kemenade (NISV)
• Super-resolution benchmarking and detection – Adrián Tormos (BSC)
• Statistical characterization of local news – Victor Bros (Idiap Research Institute)
• SRAUnet – Super Resolution Atrous Unet for super resolution and restoration of analog videos – Lorenzo Berlincioni (UNIFI)
• SMACE: A New Method for the Interpretability of Composite Decision Systems – Gianluigi Lopardo (UCA)
• Public opinion monitoring through collective semantic analysis of tweets – Ioannis Pitas (AUTH)
• Open-ended Evolution for Minecraft Building Generation – Matthew Barthet (UM)
• modl.ai Platform and Exploratory Bot Presentation – Christoffer Holmgård (MODL)
• Model Compression through Knowledge Distillation to enable DeepFake Detection on the Edge – Akis Papadopoulos (CERTH)
• Joint-Based Action Progress Prediction – Davide Pucci (UNIFI)
• ImageCLEF2023 Benchmarking campaign – Ana-Maria Drăgulinescu (UPB)
• Frame analysis of No-vax news in Europe with GPT-3 – David Alonso del Barrio (Idiap Research Institute)
• Ephemerality metrics for estimating healthiness of online discussions – Dmitry Gnatyshak (BSC)
• Deepfake Detector Attack and Defence Analysis – Kieran Fraser (IBM)
• Deep Piano Synthesizer – Rémi Mignot (IRCAM)
• Concept Discovery in Activation Spaces with Singular Value Decomposition – Mara Graziani (Hes-so Valais)
• CL2R: Compatible Lifelong Learning Representations – Niccolò Biondi (UNIFI)
• Audio Analysis for Speech Synthesis and Manipulation Detection – Luca Cuccovillo (FhG-IDMT)
• ALADIN: Image-Text Matching and Retrieval in VISIONE – Lucia Vadicamo, Paolo Bolettieri (CNR)
• AdvisIL – A Class-Incremental Learning Advisor – Adrian Popescu (CEA)
• Music co creation between AI and humans – Artur Garcia (BSC)

Authors: Candela Bravo & Joana Martinheira (LOBA)