CollectiveIntelligenceAdmin at 14:47, 1 September 2026

2026-09-01T14:47:54Z

New page

=== CORTEX2 Project ===
{| class='wikitable' style='margin:auto'
|-
! CORDIS Reference !! Start date !! End date !! Coordinator
|-
| https://cordis.europa.eu/project/id/101070192 || 01/09/2022 || 31/08/2025 || DFKI / Germany
|}
=== Project description ===
Video conferencing and mixed reality are both forms of communication but based on very different technologies. Video conferencing does not provide an in-person feel to meetings and has several other drawbacks. In contrast, mixed reality has emerged as a technology that can provide a genuine feeling of presence, and better collaboration tools. The EU-funded CORTEX² project will bridge the divide between widespread video conferencing tools and innovative XR-based solutions to democratise the adoption of next-generation eXtended Reality tele-cooperation by industrial sectors and SMEs. The initiative will use and extend the widespread Rainbow teleconferencing solution from Alcatel Lucent Enterprise to allow for fully interactive XR-based cooperation. This will be demonstrated in three pilots: industrial production, business meetings, and remote training respectively.

=== Project outputs ===
==== Publications ====
{| class="wikitable sortable"
! Domain !! Type of output !! Title !! DOI URL
|-
| Audio, Speech & NLP || Conference proceedings || Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras || https://doi.org/10.48550/arxiv.2207.06058
|-
| Audio, Speech & NLP || Conference proceedings || X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents || https://doi.org/10.48550/arxiv.2306.17674
|-
| Computer Vision, 3D Modeling & Rendering || Conference proceedings || Dynamic Cost Volumes with Scalable Transformer Architecture for Optical Flow || https://doi.org/10.5281/zenodo.8253051
|-
| Computer Vision, 3D Modeling & Rendering || Conference proceedings || Avatar quality: A study on presence and user preference || https://doi.org/10.1109/AIxVR59861.2024.00022
|-
| Education, Training & Serious Games || Peer reviewed articles || Exploring Avatar Utilization in Workplace and Educational Environments: A Study on User Acceptance, Preferences, and Technostress || https://doi.org/10.3390/APP15063290
|-
| Extended Reality (VR/AR/MR) & HCI || Conference proceedings || CORTEX2 – Extended Collaborative Telepresence for future work and education || https://doi.org/10.5281/ZENODO.8065220
|-
| Robotics, Manufacturing & Industry 4.0 || Conference proceedings || Ready Expert One: Universal 3D Workbench for Remote Industrial Training || https://doi.org/10.1145/3706370.3731701
|}

==== Technological assets ====
{| class="wikitable sortable"
! Title !! Type of Asset !! Link / DOI !! Description
|-
| Dynamic Cost Volumes with Scalable Transformer Architecture for Optical Flow || AI Model / Software || https://doi.org/10.5281/zenodo.8253051 || A neural network architecture and software framework for accurate optical flow estimation.
|-
| Uni-SLAM || AI Model / Software || https://cortex2.eu/2025/11/29/cortex2-publication-uni-slam-uncertainty-aware-neural-implicit-slam-for-real-time-dense-indoor-scene-reconstruction/ || An uncertainty-aware neural implicit SLAM model developed for real-time dense indoor scene reconstruction.
|-
| X-RiSAWOZ || Dataset || https://doi.org/10.48550/arxiv.2306.17674 || High-quality end-to-end multilingual dialogue datasets accompanied by few-shot agents.
|-
| FREDSum || Dataset || https://arxiv.org/abs/2312.04843 || A dialogue summarization corpus specifically designed around French political debates.
|}

CORTEX2 - Revision history

CollectiveIntelligenceAdmin at 14:47, 1 September 2026