AI-Based Media Coding Standards

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Mot. Imag. J
Volume: 131, No. 4, pp. 10–20
Abstract: Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is the first standards organization to develop data coding standards that have artificial intelligence (AI) as their core technology. MPAI believes that universally accessible standards for AI-based data coding can have the same positive effects on AI as standards had on digital media. Elementary components of MPAI standards–AI modules (AIMs)–expose standard interfaces for operation in a standard AI framework (AIF). As their performance may depend on the technologies used, MPAI expects that competing developers providing AIMs will promote horizontal markets of AI solutions that build on and further promote AI innovation. Finally, the MPAI framework licences (FWLs) provide guidelines to intellectual property right (IPR) holders facilitating the availability of compatible licenses to standard users.
Publication Date: 2022-05-01
DOI: 10.5594/JMI.2022.3160793
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/JMI.2022.3160793
Author(s): Andrea Basso
bio
Andrea Basso received a PhD degree, and is an advisor at the Progress Tech Transfer fund, a chief technology officer at MITO Technology, Milan, Italy, a senior expert World Intellectual Property Organization/European Commission, and a director at Synesthesia, Turin, Italy. While at Bell and AT&T Labs, Murray Hill, NJ, he contributed to the Internet Engineering Task Force (IETF) and the International Organization for Standardization/Motion Picture Experts Group (ISO/MPEG), and the International Multimedia Telecommunications Consortium (IMTC). He has authored or coauthored over 60 articles and holds 174 patents.
Paolo Ribeca
bio
Paolo Ribeca is a physicist by education but for 15 years he has specialized in the analysis of high- throughput sequencing data, being particularly interested in the development of algorithms and workflows for alignment, de novo assembly, and compression. He is delighted whenever he can apply those techniques and answer complex biological questions.
Marina Bosi
bio
Marina Bosi, a pioneer in the development of digital audio coding, is a founding director of the Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Organization, Geneva, Switzerland, and the chair of MPAI-Context-Based Audio Enhancement (MPAI-CAE). A fellow and past president of the Audio Engineering Society, Bosi was chief technology officer of MPEG LA, LLC, Denver, CO, vice president-technology at DTS, Inc., Los Angeles, CA, and was a member of the research team that created Dolby Digital at Dolby Laboratories, San Francisco, CA, where she also led the MPEG-2 AAC development.
Niccolò Pretto
bio
Niccolò Pretto is a senior postdoctoral research fellow with the Department of Information Engineering, University of Padova, Padua, Italy. His research is primarily focused on sound and music computing, applying computer science to the preservation and access to historical audio documents and cultural heritage.
Gérard Chollet
bio
Gérard Chollet studied linguistics, electrical engineering, and computer science at the University of California at Santa Barbara, Santa Barbara, CA, where he was granted a PhD in computer science and linguistics. In 1983, he joined a newly created Centre national de la recherche scientifique (CNRS) Research Unit at ENST (now Institut Polytechnique de Paris), Palaiseau, France. He supervised more than 40 doctoral theses. CNRS granted him an emeritus status in 2012. He is currently consulting for Intelligent Voice Ltd., London, U.K., Speech Morphing Inc., San Jose, CA, and Zaion.ai, Paris, France. His main publications are available at http://scholar.google.co.uk/citations?user=NakTCiYAAAAJ&hl=en
Michelangelo Guarise
bio
Michelangelo Guarise is a founder of Volumio, Florence, Italy, the market leader of hi-fi music playback ecosystem. He has been involved in physical computing and user experience research, now focusing on AI and machine learning (ML) on the field applications for high-performance and adaptive music playback systems.
Miran Choi
bio
Miran Choi is a principal researcher at the Electronics and Telecommunication Research Institute (ETRI), Daejeon, South Korea. Her research topics are natural language processing and human computer interaction (HCI). She is participating in standardization activities in ITU-T, International Organization for Standardization (ISO), and MPAI, where she develops standards on language-related technology and user interface.
Leonardo Chiariglione
bio
Leonardo Chiariglione received a MS from the Polytechnic of Turin, Turin, Italy, and a PhD from the University of Tokyo, Tokyo, Japan. He founded and chaired the Moving Picture Experts Group (MPEG) for 32 years, and proposed and chairs the Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI), for AI-enabled data coding standards.
Roberto Iacoviello
bio
Roberto Iacoviello is a lead research engineer. He graduated from the Politecnico di Torino, Turin, Italy. Since 2007, he has been working at Rai Research and Development, Turin. His current research focuses on artificial intelligence applied to video compression, and augmented reality in broadcast television. He leads the Video Evaluation Group at the European Broadcasting Union (EBU) and actively participates in MPEG and MPAI meetings.
Franesco Banterle
bio
Franesco Banterle is a researcher with the Visual Computing Laboratory at Consiglio Nazionale delle Richerch- (CNR)-Institute of Information Science and Technologies (ISTI), Pisa, Italy. He received a PhD in engineering from the University of Warwick, Coventry, U.K., in 2009. He developed Inverse Tone Mapping, which bridges classic imaging and high-dynamic range (HDR) imaging. His main research fields are HDR imaging and deep learning.
Alessandro Artusi
bio
Alessandro Artusi received a PhD in computer science from the Vienna University of Technology, Vienna, Austria, in 2004. He is the team leader of the DeepCamera Group at CYENS Nicosia, Cyprus. His research interests include image/video processing, computer graphics, computer vision, and color science, with a particular focus to deploy the next generation of imaging/video pipeline.
Francesco Gissi
bio
Francesco Gissi received an MSc in computer engineering. He is currently pursuing a PhD in information technology for engineering with the University of Sannio, Benevento, Italy. He is currently working as a data architectures, AI and advanced analytics engineer at Kebula, Naples, Italy. His principal research interests are application of AI models and approaches on video analytics tasks, audio-video compression pipelines via content-based analysis with deep learning techniques, and advanced learning algorithms.
Attilio Fiandrotti
bio
Attilio Fiandrotti received a PhD in computer science from the Politecnico di Torino, Turin, Italy, in 2010. He is currently an assistant professor at the Dipartimento di Informatica, Università di Torino, Turin, and holds a position as maıtre de confèrènces with the Multimedia Group, LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France. His current research interests focus mainly on deep learning techniques for image and video analysis, compression, and synthesis and the distribution of multimedia contents over wireless packet networks.
Giovanni Ballocca
bio
Giovanni Ballocca received a master’s in physics from the Università di Torino, Turin, Italy. He is a project manager with Sisvel Technology, None Torinese, IT, focusing on research and development projects on compression and distribution of multimedia content. He is also an expert in the field of intellectual property right (IPR) management and licensing in the consumer electronics field.
Marco Mazzaglia
bio
Marco Mazzaglia is a video game evangelist for Synesthesia, Italy. Since 2008, he has worked on more than 30 original titles and conversions on last-generation game consoles and for the B2B world. He is an adjunct professor of game design and gamification for the Polytechnic of Turin, Turin, Italy, at the master’s degree courses for cinema and media engineering and computer engineering.
Scott Moskowitz
bio
Scott Moskowitz graduated cum laude from the Wharton School of the University of Pennsylvania, Philadelphia, Pennsylvania. He holds more than 110 patents in digital watermarks, product license keys, address space layout randomization (ASLR), and so on. He presented his acclaimed “Cuba” photograph series at Leica Store Miami. He is a senior member of Institute of Electrical and Electronics Engineers (IEEE), Assoication for Computing Machinery (ACM), and Society of Photographic Instrumentation Engineers (SPIE). He is fluent in Japanese.
Keyword(s): Artificial Intelligence, Audio Enhancement, IP License, Standards, Video Compression
Copyright: © 2022 SMPTE

Bibliographic Reference(s)

L. Chiariglione et al., “AI-Based Media Coding and Beyond,” Proc. Intl. Broadcast. Convention (IBC’21), Dec. 2021. EXTERNAL
MPAI Community, “Artificial Intelligence Framework (MPAI-AIF) V1. Accessed: Apr. 7, 2022. [Online]. Available: https://bit.ly/3EV1HaY EXTERNAL
Anwar et al., “Densely Residual Laplacian Super-Resolution,” IEEE Trans. Pattern Analysis Machine Intelligence, 44(3):1192–1204, 2020, doi: 10.1109/TPAMI.2020.3021088. EXTERNAL
M. Bosi et al., “Sound and Music Computing Using AI: Designing a Standard,” Proc. 18th Sound Music Comput. Conf. (SMC’21), Jun. 2021. EXTERNAL
MPAI Community, “AI-Enhanced Video Coding (MPAI-EVC). Accessed: Apr. 7, 2022. [Online]. Available: https://bit.ly/3tNjtId EXTERNAL
N. Pretto et al., “A Workflow and Novel Digital Filters for Compensating Speed and Equalization Errors on Digitized Audio Open-Reel Tapes,” Proc. Audio Mostly (AM’21), pp. 224– 231, Sep. 2021. EXTERNAL
MPAI Community, “Multi-Modal Conversation (MPAI-MMC) V1.1. Accessed: Apr. 7, 2022. [Online]. Available: https://bit.ly/3DH7Sit EXTERNAL
MPAI Community, “Context-Based Audio Enhancement (MPAI-CAE) V1.2. Accessed: Apr. 7, 2022. [Online]. Available: https://bit.ly/3KrxS3d EXTERNAL
N. Pretto et al., “Computing Methodologies Supporting the Preservation of Electro-Acoustic Music From Analog Magnetic Tape,” Computer Music J., 42(4):59–74, Jun. 2019. EXTERNAL
A. Artusi et al., “Towards Pervasive and Trustworthy Artificial Intelligence: How Standards Can Put a Great Technology at the Service of Humankind,” Amazon Publishing: Geneva, Switzerland, 2021. EXTERNAL
MPAI Community, “Server-Based Predictive Multiplayer Gaming (MPAI-SPG). Accessed: Apr. 7, 2022. [Online]. Available: https://bit.ly/3I6yKcd EXTERNAL
L. Wang et al., “Enhancing HEVC Spatial Prediction by Context-Based Learning,” Proc. IEEE Intl. Conf. Acoust., Speech, Signal Process. (ICASSP’19), pp. 4035–4039, May 2019, doi: 10.1109/ICASSP.2019.8683624. EXTERNAL
T. Dumas et al., “Context-Adaptive Neural Network-Based Prediction for Image Compression,” IEEE Trans. Image Processing, 29:679–693, 2019, doi: 10.1109/TIP.2019.2934565. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2022.3160793.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Andrea Basso, Paolo Ribeca, Marina Bosi, Niccolò Pretto, Gérard Chollet, Michelangelo Guarise, Miran Choi, Leonardo Chiariglione, Roberto Iacoviello, Franesco Banterle, Alessandro Artusi, Francesco Gissi, Attilio Fiandrotti, Giovanni Ballocca, Marco Mazzaglia, and Scott Moskowitz; AI-Based Media Coding Standards, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 4, May 2022); SMPTE, 2022. Available at https://doi.org/10.5594/JMI.2022.3160793

Snippet:

Andrea Basso, Paolo Ribeca, Marina Bosi, Niccolò Pretto, Gérard Chollet, Michelangelo Guarise, Miran Choi, Leonardo Chiariglione, Roberto Iacoviello, Franesco Banterle, Alessandro Artusi, Francesco Gissi, Attilio Fiandrotti, Giovanni Ballocca, Marco Mazzaglia, and Scott Moskowitz; AI-Based Media Coding Standards, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 4, May 2022); SMPTE, 2022. Available at https://doi.org/10.5594/JMI.2022.3160793

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Andrea Basso, Paolo Ribeca, Marina Bosi, Niccolò Pretto, Gérard Chollet, Michelangelo Guarise, Miran Choi, Leonardo Chiariglione, Roberto Iacoviello, Franesco Banterle, Alessandro Artusi, Francesco Gissi, Attilio Fiandrotti, Giovanni Ballocca, Marco Mazzaglia, and Scott Moskowitz; <cite>AI-Based Media Coding Standards</cite>, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 4, May 2022); SMPTE, 2022. Available at <a href="https://doi.org/10.5594/JMI.2022.3160793" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2022.3160793</a></span>

SMPTE's HTML Pub

Preview:

Andrea Basso, Paolo Ribeca, Marina Bosi, Niccolò Pretto, Gérard Chollet, Michelangelo Guarise, Miran Choi, Leonardo Chiariglione, Roberto Iacoviello, Franesco Banterle, Alessandro Artusi, Francesco Gissi, Attilio Fiandrotti, Giovanni Ballocca, Marco Mazzaglia, and Scott Moskowitz; AI-Based Media Coding Standards, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 4, May 2022); SMPTE, 2022
doi: 10.5594/JMI.2022.3160793
url: https://doi.org/10.5594/JMI.2022.3160793

Snippet:

<li>
Andrea Basso, Paolo Ribeca, Marina Bosi, Niccolò Pretto, Gérard Chollet, Michelangelo Guarise, Miran Choi, Leonardo Chiariglione, Roberto Iacoviello, Franesco Banterle, Alessandro Artusi, Francesco Gissi, Attilio Fiandrotti, Giovanni Ballocca, Marco Mazzaglia, and Scott Moskowitz; <cite id="bib-10-5594-jmi-2022-3160793">AI-Based Media Coding Standards</cite>, SMPTE Motion Imaging Journal ( Volume: 131, Issue: 4, May 2022); SMPTE, 2022
<span class="doi">10.5594/JMI.2022.3160793</span>
</li>