SAFER – Smart Assistant For Enhanced Remote Digital Tower

The project aims to research and develop multimodal AI techniques and approaches for video-centric object detection and tracking in remote digital tower (RDT) scenarios. Innovation of smart assistive technology for RDT’s vison system is the central goal of this project.

Contact

Team Possegger Horst Possegger

possegger@tugraz.at

+43 316 873 - 5033

Profile

Project Consortium

Frequentis AG (Consortium Lead)
Austrian Institute of Technology
Graz University of Technology

Project Duration

2022 - 2025

Dissemination

Press release by Frequentis
Kirillova et al. Into the Fog: Evaluating Robustness of Multiple Object Tracking, BMVC, 2024
Mirza et al. Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs, ECCV, 2024
Mirza et al. LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections, NeurIPS, 2023
Lin et al. MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge, ICCV, 2023
Mirza et al. MATE: Masked Autoencoders are Online 3D Test-Time Learner, ICCV, 2023
Mirza et al. ActMAD: Activation Matching to Align Distributions for Test-Time-Training, CVPR, 2023
Leitner et al. Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions, IV, 2023

Project Funding

This project received funding from the Take Off programme under the project SAFER (894164). Take Off is a research, technology and innovation funding programme of the Republic of Austria, Federal Ministry for Climate Action, Environment, Energy, Mobility, Innovation and Technology. The Austrian Research Promotion Agency (FFG) has been authorised for the programme management.