VANDALs in Tel Aviv for ECCV22

At the end of October, the VANDAL lab flew to Tel Aviv for attending the European Conference on Computer Vision (ECCV) 2022: a wonderful occasion to connect with brilliant researchers from all over the world!

Discover the presented articles:

  •  Improving Generalization in Federated Learning by Seeking Flat Minima. Debora Caldarola*, Barbara Caputo, Marco Ciccone*. Read the paper here.
  • Semantic Novelty Detection via Relational Reasoning. Francesco Cappio Borlino, Silvia Bucci, Tatiana Tommasi. Read the paper here.

VANDALs @ CVPR 2022

Discover the new articles published by the VANDAL group to CVPR (Conference on Computer Vision and Pattern Recognition) 2022:

  • Deep Visual Geo-localization Benchmark. Oral.
    Gabriele Berton, Riccardo Mereu, Gabriele Trivigno, Carlo Masone, Gabriela Csurka, Torsten Sattler, Barbara Caputo.
  • E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition. Chiara Plizzari*, Mirco Planamente*, Gabriele Goletto, Marco Cannici, Emanuele Gusso, Matteo Matteucci, Barbara Caputo. Read the paper.
  • Incremental Learning in Semantic Segmentation from Image Labels.
    Fabio Cermelli*, Dario Fontanel*, Antonio Tavera*, Marco Ciccone, Barbara Caputo. Read the paper.
  • Rethinking Visual Geo-localization for Large-Scale Applications.
    Gabriele Berton, Carlo Masone, Barbara Caputo.

Congratulations everyone!

VANDALs in the organization of I-RIM 2021

This year the third Italian Conference on Robotics and Intelligent Machines (IRIM) has been organized by the VANDAL group of the Politecnico di Torino, together with the Campus Biomedico in Rome. Moreover, Professor Barbara Caputo was the General Chair of the Conference, together with Professor Eugenio Guglielmelli.

A successful event, with more than 150 on site attendees and more than 400 connected with us remotely. We hosted well renowned International and Italian speakers, interesting discussions on the future directions of Italian research in Robotics and Artificial Intelligence, and lots of scientific presentations. Many research labs also brought their groundbreaking research outcomes in an amazing exposition organized together with Maker Faire.

VANDALs on the podium of the EPIC KITCHENS Challenge

EPIC-KITCHENS [1] is the largest-scale egocentric dataset collected by 32 participants in their native kitchen environments, and densely annotated with actions and object interactions (125 verb classes and 331 noun classes).

The dataset is aligned with six challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition.

The unsupervised domain adaptation challenge tests how models can cope with similar data collected 2 years later on the task of action recognition. The goal is thus to assign a (verb, noun) label to a trimmed segment, following the Unsupervised Domain Adaptation paradigm: a labelled source domain is used for training, and the model needs to adapt to an unlabelled target domain. Videos recorded in 2018 (EPIC-KITCHENS-55) constitute the source domain, while videos recorded two years later (EPIC-KITCHENS-100’s extension) constitute the unlabelled target domain.

Our PhD students Mirco Planamente and Chiara Plizzari achieved the 3rd place position [3] in the third edition of the challenge, presented at the Eighth International Workshop on Egocentric Perception Interaction and Computing. They re-purposed the Relative Norm Alignment loss [2], a multi-modal loss recently proposed to deal with the Domain Generalization setting for action recognition, to operate between different backbone architectures in order to enhance their collaboration. Indeed, they achieved top performance on all verb, noun and action category.‚Äč

[1] Damen, Dima, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti et al. “Scaling egocentric vision: The epic-kitchens dataset.” In Proceedings of the European Conference on Computer Vision (ECCV), pp. 720-736. 2018.

[2] Planamente, Mirco, Chiara Plizzari, Emanuele Alberti, and Barbara Caputo. “Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition”, WACV 2021.

[3] Plizzari, Chiara, Mirco Planamente, Emanuele Alberti, and Barbara Caputo. “PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition.” arXiv preprint arXiv:2107.00337 (2021).

Data, AI e Robotica @ PoliTO

Research, technology transfer and support to companies on the fundamental issues of Big Data, Artificial Intelligence, robotics and the digital revolution

As part of the AI-Hub @ Politecnico di Torino, our lab took part in the workshop “Dati, AI e Robotica @ PoliTO”.

The workshop illustrated the initiatives and skills of the Centers of the Politecnico di Torino in the context of the digital revolution, with successful stories of business – university collaboration on the topics of Industry 4.0, AI for vision, Robotics, Business Intelligence, Internet Analytics, Smart Cities and more.

The event was organized by Politecnico di Torino in collaboration with SmartData@PoliTO, AI-H@PoliTO, Pic4SeR, LINKS Fundation, incubatore I3P, Torino Wireless and Piattaforma Digital Revolution.

For more info on the AI-Hub read here.

VANDALs contribute to ECCV 2024 organization

The European Conference on Computer Vision (ECCV) is one of the three top conferences in Computer Vision, alongside the International Conference on Computer Vision (ICCV) and the Conference on Computer Vision and Pattern Recognition (CVPR). It is held every two years, alternating with ICCV. Its proceedings are published by Springer Science+Business Media.

The VANDAL Lab will be involved in the organization of ECCV 2024.