-
3 MEDIALAB papers @ ECCV
We will present 3 papers (2 at the main conference and a workshop one) at the European Conference on Computer Vision (ECCV) : “HoloADMM: High-Quality Holographic Complex Field Recovery” (in collaboration with Sony Europe) and “Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation” (in collaboration with the Xidian University) at the…
-
Hybrid Extended reAliTy
MEDIA Lab is participating to a new three-year EU project, Hybrid Extended reAliTy (HEAT). HEAT aims at integrating immersive media technologies such as point cloud/holographic imaging, multi-sensorial media, Social VR in a multi-user, feedback-enabled communication system to provide the construction of compelling context-aware and embodied experiences for innovative hybrid XR applications.
-
Paper accepted on PAMI
We are happy to announce that the paper “Learning with Style: Continual Semantic Segmentation Across Tasks and Domains” from Marco Toldo, Umberto Michieli and Pietro Zanuttigh has been accepted for publication on the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
-
Paper accepted at ICML 2024
We are happy to announce that the paper “ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data” from Carmen Martin-Turrero, Maxence Bouvier, Manuel Breitenstein, Pietro Zanuttigh and Vincent Parret has been accepted for publication at the International Conference on Machine Learning (ICML). The work is a result of the long-term collaboration we…
-
2 Papers at ACM MMSys 2024
We presented 2 papers at the ACM Multimedia Systems Conference. : “A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation” (research track) and “Questset: A VR Dataset for Network and Quality of Experience Studies” (software and dataset track) The first work has been possible thanks to a collaboration between the…
-
Best demo award @ GTTI MMSP 2024
During the GTTI-SPS Thematic Meeting on Multimedia Signal Processing the demo presented by Sara Baldoni (University of Padova) and Anna Ferrarotti (Roma Tre University) won the Best Demo Award. The 2024 edition of the GTTI-SPS Thematic Meeting on Multimedia Signal Processing, organized by the University of Trento, was held in Andalo (TN) on January 22 and…
-
HePIC dataset released
HePIC dataset released with the publication of our ICIP paper in collaboration with ICEA Dept. @Unipd! We are thrilled to announce that our Heritage Pointcloud Instance Collection (HePIC) dataset has been published! It consists of a dataset of Heritage Buildings Point clouds labeled at Semantic and Instance Level, acquired via Terrestrial Laser Scanner by our…
-
Short course “Elementary, my dear human!”
We are happy to announce that on Monday September 4 @ 14:00 in room Ke we are going to host a talk by prof. Anderson Rocha from Universidade Estadual de Campinas, Brasil titled Artificial Intelligence and Digital Forensics: a much-needed alliance Abstract: In this talk, we will discuss a panoramic view of digital forensics in…
-
Paper on NeRF-based 3D reconstruction accepted at BMVC 2023
We are happy to announce that the paper “Exploiting Multiple Priors for Neural 3D Indoor Reconstruction” has been accepted as oral presentation at the 34th British Machine Vision Conference (BMVC) held in Aberdeen, Scotland. This work has been possible thanks to a collaboration between the M3Dia Lab and the Sony Europe R&D department. Congratulations to…
-
SYNDRONE Dataset Released
The SYNDRONE dataset has been released! It is a multimodal synthetic dataset containing images and 3D data taken at multiple flying heights. It has both object-level and pixel-level annotations. It contains 72k labeled samples that allow for effective training of deep learning architectures. Download the dataset here
