Geneva, Switzerland – 21st November 2024. MPAI – Moving Picture, Audio and Data Coding by Artificial Intelligence – the international, non-profit, and unaffiliated organisation developing AI-based data coding standards – has concluded its 49th General Assembly (MPAI-49) by approving for publication:
1. Call for Technologies: Up-sampling Filter for Video applications (MPAI-UFV)
2. Technical Specification: Neural Network Traceability (MPAI-NNT) V1.0
3. Technical Specification: Human and Machine Communication (MPAI-HMC) V2.0
4. New versions of four standards with added Conformance Testing
Call for Technologies: Up-sampling Filter for Video applications (MPAI-UFV) invites any party able and wishing to contribute to the development of the planned MPAI-UFV Technical Specification to submit a response. MPAI-UFV is expected to leverage AI to provide higher video quality when upsampling a video from Standard Definition to HDTV and from HDTV to 4K.
Technical Specification: Neural Network Traceability (MPAI-NNT) V1.0 specifies methods to evaluate the ability to trace back to its source a neural network that has been modified, the computational cost of injecting, extracting, detecting, decoding, or matching data from a neural network, and the impact on the performance of a neural network with inserted traceability data and its inference.
Technical Specification: Human and Machine Communication (MPAI-HMC) V2.0 enables advanced forms of communication between humans in a real space or represented in a Virtual Space, and Machines represented as humanoids in a Virtual Space or rendered as humanoids in a real space. This new version leverages MPAI-CAE V2.3, MPAI MMC V2.3, MPAI-OSD V1.2, MPAI-PAF V1.3 and Technical Specification: Data Types, Formats, and Attributes (MPAI-TFA) V1.2 – just published as an MPAI standard.
The Call and the standards will be presented online according to the schedule reported below.
• Call for technologies: Upsampling Filter for Video application (UFV) 2024/11/27T14 to attend register at http://tiny.cc/oqdwzz
• New Standard: Neural Network Traceability (NNT) 2024/12/10T15 to attend register at http://tiny.cc/wqdwzz
• Revised Standard: Human and Machine Communication (HMC) 2024/12/09T16 to attend register at http://tiny.cc/pqdwzz
MPAI is continuing its work plan that involving the following activities:
1. AI Framework (MPAI-AIF https://mpai.community/standards/mpai-aif/): reference software, conformance testing, and application are-as.
2. AI for Health (MPAI-AIH https://mpai.community/standards/mpai-aih/): reference model and technologies for a system enabling clients to improve models processing health data and federated learning to share the training.
3. Context-based Audio Enhancement (CAE-DC https://mpai.community/standards/mpai-cae/): new projects.
4. Connected Autonomous Vehicle (MPAI-CAV https://mpai.community/standards/mpai-cav/): Functional Requirements of CAV architecture
5. Compression and Understanding of Industrial Data (MPAI-CUI https://mpai.community/standards/mpai-cui/): preparation for extension of existing standard.
6. End-to-End Video Coding (MPAI-EEV https://mpai.community/standards/mpai-eev/): video coding using AI-based End-to-End Video coding.
7.AI-Enhanced Video Coding (MPAI-EVC https://mpai.community/standards/mpai-evc/). video coding with AI tools added to existing tools.8. Governance of the MPAI Ecosystem (MPAI-GME https://mpai.community/standards/mpai-gme/): working on version 2.0 of the Specification.
9. Human and Machine Communication (MPAI-HMC https://mpai.community/standards/mpai-hmc/): model and technologies enabling a human or a machine to communicate with a machine or a human in a different cultural environment.
10.Multimodal Conversation (MPAI-MMC https://mpai.community/standards/mpai-mmc/): reference software, drafting conformance testing, and new areas.
11. MPAI Metaverse Model (MPAI-MMM https://mpai.community/standards/mpai-mmm/): reference software and metaverse technologies requiring standards.
12.Neural Network Watermarking (MPAI-NNW https://mpai.community/standards/mpai-nnw/): reference software for enhanced applications.
13.Object and Scene Description (MPAI-OSD https://mpai.community/standards/mpai-osd/): finalising V1.2 and developing reference software, conformance testing and new areas for digital humans.
14. Portable Avatar Format (MPAI-PAF https://mpai.community/standards/mpai-ara/): reference software, conformance testing and new areas.
15. AI Module Profiles (MPAI-PRF https://mpai.community/standards/mpai-prf/): to specify which features an AI Module supports.
16.Server-based Predictive Multiplayer Gaming (MPAI-SPG https://mpai.community/standards/mpai-spg/): technical report on mitigation of data loss and cheating.
17.Data Types, Formats, and Attributes (MPAI-TFA https://mpai.community/standards/mpai-tfa/): extending he standard to data types used by other MPAI standards.
18.XR Venues (MPAI-XRV https://mpai.community/standards/mpai-xrv/): preparation for the development of the standard.
Legal entities and representatives of academic departments supporting the MPAI mission and able to contribute to the development of standards for the efficient use of data can become MPAI members (https://mpai.community/2022/11/02/seven-good-reasons-to-join-mpai/)
Please visit the MPAI website (https://mpai.community), contact the MPAI secretariat (secretariat@mpai.community) for specific information, subscribe to the MPAI Newsletter and follow MPAI on social media:
– LinkedIn (https://www.linkedin.com/groups/13949076/).
– X (https://twitter.com/mpaicommunity).
– Facebook (https://www.facebook.com/mpaicommunity).
– Instagram (https://www.instagram.com/mpaicommunity/).
– Youtube (https://www.youtube.com/@MPAIstandards).
– Blueskay (https://bsky.app/profile/mpaicommunity.bsky.social)
MPAI, c/o Me Olivier Brunisholz
5 Cours des Bastions
CH-1205 Geneva, Switzerland.
Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is an international non-profit organisation with the mission is to develop Artificial Intelligence (AI) enabled digital data compression specifications, with clear Intellectual Property Rights (IPR) licensing frameworks,
1. Of Moving Picture, Audio and Data Coding, especially using new technologies such as Artificial Intelligence, and
2. That facilitate integration of Moving Picture, Audio and Data coding components into systems.
This release was published on openPR.
