Invitation to contribute proposals of AI-based coding standards
MPAI – Moving Picture, Audio and Data Coding by Artificial Intelligence is an international not-for-profit organisation with the mission to develop AI enabled digital data compression standards with clear IPR licensing frameworks.
MPAI invites you to contribute proposals of AI-based data coding standards.
The MPAI Statutes define two classes of membership: Principal Members with the right to vote and Associate Members with the right to participate in the development of MPAI technical specifications. However, MPAI encourages non-members to propose new MPAI standards and participate in meetings dealing with proposals of new standards and their functional requirements.
MPAI has already collected and documented several use cases proposed by members and non-members in the MPAI Use Cases document, now at version 2.0. Combinations of some of the use cases proposed has led MPAI to initiate the development of several standards:
Artificial Intelligence Framework (MPAI-AIF) enables creation and automation of mixed Artificial Intelligence – Machine Learning – Data Processing workflows for the application areas currently considered by the MPAI work plan.
Artificial Intelligence for Health data (MPAI-AIH) is an MPAI project addressing the secure collection, AI-based processing and secure access to Health data.
Avatar Representation and Animation (MPAI-ARA) specifies the technologies enabling the implementation of the Avatar-Based Videoconference Use Case specified in the Avatar-Based Videoconference Use Case.
Context-based Audio Enhancement (MPAI-CAE) improves the user experience for several audio-related applications including entertainment, communication, teleconferencing, gaming, post-production, restoration etc. in a variety of contexts such as in the home, in the car, on-the-go, in the studio etc. using context information to act on the input audio content using AI.
Connected Autonomous Vehicles (MPAI-CAV) is a Use Case addressing the Connected Autonomous Vehicle (CAV).
Compression and understanding of industrial data (MPAI-CUI) aims to enable AI-based filtering and extraction of key information to predict company performance by applying Artificial Intelligence to governance, financial and risk data.
There is consensus in the video coding research community that the so-called End-to-End (E2E) video coding (MPAI-EEV) schemes can yield significantly higher performance than those target, e.g., by MPAI-EVC. AI-based End-to-End Video Coding intends to address this promising area.
AI-Enhanced Video Coding (MPAI-EVC) is a video compression standard that substantially enhances the performance of a traditional video codec by improving or replacing traditional tools with AI-based tools. Two approaches – Horizontal Hybrid and Vertical Hybrid – are envisaged.
Integrative Genomic/Sensor Analysis (MPAI-GSA) uses AI to understand and compress the result of high-throughput experiments combining genomic/proteomic and other data, e.g., from video, motion, location, weather, medical sensors.
Mixed-Reality Collaborative (MPAI-MCS) Spaces is a project riding on the opportunities offered by emerging technologies enabling developers to deliver mixed-reality collaborative space (MCS) applications where biomedical, scientific, and industrial sensor streams and recordings are to be viewed. MCS systems use AI to achieve immersive presence, spatial maps (e.g., Lidar scans, inside-out tracking) rendering, and multiuser synchronisation etc.
Multi-modal conversation (MPAI-MMC) aims to enable human-machine conversation that emulates human-human conversation in completeness and intensity by using AI.
MPAI Metaverse Model (MPAI-MMM) is an MPAI p;roject targeting a series of Technical Reports and Specifications promoting Metaverse Interoperability.
Neural Network Watermarking (MPAI-NNW) is a standard whose purpose is to enable watermarking technology providers to qualify their products by providing the means to measure, for a given size of the watermarking payload.
Visual object and scene description (MPAI-OSD) is a collection of Use Cases sharing the goal of describe visual object and locate them in the space. Scene description includes the usual description of objects and their attributes in a scene and the semantic description of the objects.
Server-based Predictive Multiplayer Gaming (MPAI-SPG) aims to minimise the audio-visual and gameplay discontinuities caused by high latency or packet losses during an online real-time game. In case information from a client is missing, the data collected from the clients involved in a particular game are fed to an AI-based system that predicts the moves of the client whose data are missing. The same technologies provide a response to the need to detect who amongst the players is cheating.
XR Venues (MPAI-XRV) is an MPAI project addressing a multiplicity of use cases enabled by AR/VR/MR (XR) and enhanced by Artificial Intelligence technologies. The word venue is used as a synonym to Environment, and can be both real and virtual.
MPAI invites all interested parties to submit proposals of practical use cases that benefit from the capability of AI technologies to compress digital data and/or to bring out information embedded in the data. Any company, organisation or individual, irrespective of its membership in MPAI, is entitled to submit a written contribution proposing use cases and participate in MPAI meetings until their Functional Requirements are finalised. Participation in subsequent stages of standard development requires MPAI membership.
Contributions, drafted using the template below should be sent to the MPAI secretariat: firstname.lastname@example.org.
Title: Concise title of use case
Proponent: Proponent’s name and affiliation
Description: Explains and delimits the scope of the use case
Comments: General comment on why and how AI can support the use case
Examples: Illustrate how the use case can cover different contexts, especially if the use case has a broad coverage
Requirements: Preliminary requirements to clarify the use case (full requirements identification is part of the subsequent Functional Requirements stage)
Object of standard: Provides general identification of what is normative in the proposed use case if a standard will be developed
Benefits: Advantages offered by the standard over existing solutions and new opportunities offered to industry and/or end users
Bottlenecks: Technical issues that may limit use of the standard or whose passing over will facilitate use of the standard
Social aspects: Cases where using the standard may have social impacts (optional)
Success criteria: Proposed measures of the standard’s success. These should include outcomes (short term) and impact (longer term).