The IPTC Video Metadata Working Group is happy to announce that version 1.7 of its flagship standard, Video Metadata Hub, has now been released.

The new version has four new properties which allow users and tools to embed metadata about AI prompt information that was used to generate the image, if applicable.

The new properties in detail are:

• AI System Used (text string, single-valued, optional)
  The AI engine and/or the model name used to generate this media.
  Note: For example, ChatGPT DALL-E, Google Gemini, ChatGPT
• AI System Version Used (text string, single-valued, optional)
  The version of the AI system used to generate this media, if known.
• AI Prompt Information (text string, single-valued, optional)
  The information that was given to the generative AI service as “prompt(s)” in order to generate this media.
  Note: This may include negative [excludes] and positive [includes] statements in the prompt.
• AI Prompt Writer Name (text string, single-valued, optional)
  Name of the person who wrote the prompt used for generating this media.
  Note: this person should not be considered as the media creator.

Please note that users should not expect that the contents of the “AI Prompt Information” property could be given directly to an AI system to generate the same video; there are many reasons why generated media files differ even for the same input information. The Working Group decided to add “AI Prompt Information” as a generic property that creators could use to describe the process that was used to prompt an AI system to create the content.

The official IPTC Video Metadata Hub recommendation files and user documentation have all been updated for the new version:

• IPTC Video Metadata Hub 1.7 properties table
• IPTC Video Metadata Hub 1.7 full mappings table
• IPTC Video Metadata Hub 1.7 user guide
• IPTC Video Metadata Hub generator – A tool that can help developers to understand how Video Metadata Hub works and to generate example files
• IPTC Video Metadata Hub 1.7 JSON Schema

The Video Metadata Working Group welcomes feedback. Please post to the IPTC Video Metadata public discussion group or use the IPTC Contact Us form.

The IPTC Video Metadata Working Group has released version 1.6 of its Video Metadata Hub standard, including terms for rights usage, language, and content created by Generative AI models.

The specification for Video Metadata Hub is separated into two parts: IPTC Video Metadata Hub properties and IPTC Video Metadata Hub mappings showing how to apply these core properties in many existing video standards.

There is also a JSON Schema representation of Video Metadata Hub, which is used by some large media companies in manageing their video content. The 1.6 version of the JSON schema reflects the latest changes.

The Video Metadata Hub User Guide and Video Metadata Hub Generator tool have also been updated to include the changes in version 1.6.

Please feel free to discuss the new version of Video Metadata Hub on the public iptc-videometadata discussion group, or contact IPTC via the Contact us form.

Following the IPTC’s recent announcement that Rights holders can exclude images from generative AI with IPTC Photo Metadata Standard 2023.1 , the IPTC Video Metadata Working Group  is very happy to announce that the same capability now exists for video, through IPTC Video Metadata Hub version 1.5.

The “Data Mining” property has been added to this new version of IPTC Video Metadata Hub, which was approved by the IPTC Standards Committee on October 4th, 2023. Because it uses the same XMP identifier as the Photo Metadata Standard property, the existing support in the latest versions of ExifTool will also work for video files.

Therefore, adding metadata to a video file that says it should be excluded from Generative AI indexing is as simple as running this command in a terminal window:

exiftool -XMP-plus:DataMining="Prohibited for Generative AI/ML training" example-video.mp4

(Please note that this will only work in ExifTool version 12.67 and above, i.e. any version of ExifTool released after September 19, 2023)

The possible values of the Data Mining property are listed below:

A corresponding new property “Other Constraints” has also been added to Video Metadata Hub v1.5. This property allows plain-text human-readable constraints to be placed on the video when using the “Prohibited, see plus:OtherConstraints” value of the Data Mining property.

The Video Metadata Hub User Guide and Video Metadata Hub Generator have also been updated to include the new Data Mining property added in version 1.5.

We look forward to seeing video tools (and particularly crawling engines for generative AI training systems) implement the new properties.

Please feel free to discuss the new version of Video Metadata Hub on the public iptc-videometadata discussion group, or contact IPTC via the Contact us form.

The IPTC is proud to announce that after intense work by most of its Working Groups, we have published version 1.0 of our guidelines document: Expressing Trust and Credibility Information in IPTC Standards.

The culmination of a large amount of work over the past several years across many of IPTC’s Working Groups, the document represents a guide for news providers as to how to express signals of trust known as “Trust Indicators” into their content.

Trust Indicators are ways that news organisations can signal to their readers and viewers that they should be considered as trustworthy publishers of news content. For example, one Trust Indicator is a news outlet’s corrections policy. If the news outlet provides (and follows) a clear guideline regarding when and how it updates its news content.

The IPTC guideline does not define these trust indicators: they were taken from existing work by other groups, mainly the Journalism Trust Initiative (an initiative from Reporters Sans Frontières / Reporters Without Borders) and The Trust Project (a non-profit founded by Sally Lehrman of UC Santa Cruz).

The first part of the guideline document shows how trust indicators created by these standards can be embedded into IPTC-formatted news content, using IPTC’s NewsML-G2 and ninjs standards which are both widely used for storing and distributing news content.

The second part of the IPTC guidelines document describes how cryptographically verifiable metadata can be added to media content. This metadata may express trust indicators but also more traditional metadata such as copyright, licensing, description and accessibility information. This can be achieved using the C2PA specification, which implements the requirements of the news industry via Project Origin and of the wider creative industry via the Content Authenticity Initiative. The IPTC guidelines show how both IPTC Photo Metadata and IPTC Video Metadata Hub metadata can be included in a cryptographically signed “assertion” 

We expect these guidelines to evolve as trust and credibility standards and specifications change, particularly in light of recent developments in signalling content created by generative AI engines. We welcome feedback and will be happy to make changes and clarifications based on recommendations.

The IPTC sends its thanks to all IPTC Working Groups that were involved in creating the guidelines, and to all organisations who created the trust indicators and the frameworks upon which this work is based.

Feedback can be shared using the IPTC Contact Us form.

The IPTC NewsCodes Working Group has approved an addition to the Digital Source Type NewsCodes vocabulary.

The new term, “Composite with Trained Algorithmic Media“, is intended to handle situations where the “synthetic composite” term is not specific enough, for example a composite that is specifically made using an AI engine’s “inpainting” or “outpainting” operations.

The full Digital Source Type vocabulary can be accessed from https://cv.iptc.org/newscodes/digitalsourcetype. It can be downloaded in NewsML-G2 (XML), SKOS (RDF/XML, Turtle or JSON-LD) to be integrated into content management and digital asset management systems.

The new term can be used immediately with any tool or standard that supports IPTC’s Digital Source Type vocabulary, including the C2PA specification, the IPTC Photo Metadata Standard and IPTC Video Metadata Hub.

Information on the new term will soon be added to IPTC’s Guidance on using Digital Source Type in the IPTC Photo Metadata User Guide.

The IPTC Video Metadata Working Group is proud to announce the release of version 1.4 of the group’s standard, Video Metadata Hub.

See the updated properties table, updated mappings table and updated guidelines document.

All changes can be used immediately in Video Metadata Hub use cases, particularly in C2PA assertions (described in our recent post).

We are happy to announce that IPTC’s work with C2PA, the Coalition for Content Provenance and Authority, continues to bear fruit. The latest development is that C2PA assertions can now include properties from both the IPTC Photo Metadata Standard and our video metadata standard, IPTC Video Metadata Hub.

Version 1.2 of the C2PA Specification describes how metadata from either the photo or video standard can be added, using the XMP tag for each field in the JSON-LD markup for the assertion.

For IPTC Photo Metadata properties, the XMP tag name to be used is shown in the “XMP specs” row in the table describing each property in the Photo Metadata Standard specification. For Video Metadata Hub, the XMP tag can be found in the Video Metadata Hub properties table under the “XMP property” column.

We also show in the example assertion how the new accessibility properties can be added using the Alt Text (Accessibility) field which is available in Photo Metadata Standard and will soon be available in a new version of Video Metadata Hub.

The National Association of Broadcasters (NAB) Show wrapped up its first face-to-face event in three years last week in Las Vegas.  In spite of the name, this is an internationally attended trade conference and exhibition showcasing equipment, software and services for film and video production, management and distribution. There were 52,000 attendees, down from a typical 90-100k, with some reduction in booth density; overall the show was reminiscent of pre-COVID days.  A few members of IPTC met while there: Mark Milstein (vAIsual), Alison Sullivan (MGM Resorts), Phil Avner (Associated Press) and Pam Fisher (The Media Institute).  Kudos to Phil for working, showcasing ENPS on the AP stand, while others walked the exhibition stands.

NAB is a long-running event and several large vendors have large ‘anchor’ booths.  Some such as Panasonic and Adobe reduced their normal NAB booth size, while Blackmagic had their normal ‘city block’-sized presence, teeming with traffic.  In some ways the reduced booth density was ideal for visitors: plenty of tables and chairs populated the open areas making more meeting and refreshment space available.  The NAB exhibition is substantially more widely attended than the conference, and this year several theatres were provided on the show floor for sessions any ‘exhibits only’ attendee could watch.  Some content is now available here: https://nabshow.com/2022/videos-on-demand/

For the most part this was a show of ‘consolidation’ rather than ‘innovation’. For example, exhibitors were enjoying welcoming their partners and customers face-to-face rather than launching significant new products.  Codecs standardised during the past several years were finally reaching mainstream support, with AV1, VP9 and HEVC well-represented across vendors. SVT-AV1 (Scalable Vector Technology) was particularly prevalent, having been well optimised and made available to use license-free by the standard’s contributors. VVC (Versatile Video Coding), a more recent and more advanced standard, is still too computationally intensive for commercial use, though a small set made mention of it on their stands (e.g. Fraunhofer).

IP is now fairly ubiquitous within broadcast ecosystems.  To consolidate further, an IP Showcase booth illustrating support across standards bodies and professional organisations championed more sophisticated adoption. A pyramid graphic showing a cascade of ‘widely available’ to ‘rarely available’ sub-systems encouraged deeper adoption.

Super Resolution – raising the game for video upscaling

One of the show floor sessions – “Improving Video Quality with AI” – presented advances by iSIZE and Intel. The Intel technology may be particularly interesting to IPTC members, and concerns “Super Resolution.” Having followed the subject for over 20 years, for me this was a personal highlight of the show.

Super Resolution is a technique for creating higher resolution content from smaller originals.  For example, achieving a professional quality 1080p video from a 480p source, or scaling up a social media-sized image for feature use.

A few years ago a novel and highly effective new Super Resolution method was innovated (“RAISR”, see https://arxiv.org/abs/1606.01299); this represented a major discontinuity in the field, albeit with the usual mountain of investment and work needed to take the ‘R’ (research) to ‘D’ (development).

This is exactly what Intel have done, and the resulting toolsets will be made available at no cost at the company’s Open Visual Cloud repository at the end of May.

Intel invested four years in improving the AI/ML algorithms (having created a massive ground truth library for learning), optimising to CPUs for performance and parallelisation, and then engineering the ‘applied’ tools developers need for integration (e.g. Docker containers, FFmpeg and GStreamer plug-ins). Performance will now be commercially robust.

The visual results are astonishing, and could have a major impact on the commercial potential of photographic and film/video collections needing to reach much higher resolutions or even to repair ‘blurriness’.

Next year’s event is the centennial of the first NAB Show and takes place from April 15th-19th in Las Vegas.

– Pam Fisher – Lead, IPTC Video Metadata Working Group

The IPTC Video Metadata Working Group is happy to announce the 1.0 version of the  IPTC Video Metadata Hub User Guide.

The guide introduces IPTC’s Video Metadata Hub recommendation and explains how it can be used to solve metadata management problems in any organisation that processes video content, from news agencies to advertising agencies; libraries, galleries and museums; long-form video producers such as broadcasters and movie studios; and stock video services.

As well as explaining the details of each field in the IPTC Video Metadata Hub standard, it shows through a set of use cases how it can be used in a variety of common scenarios to store rights, descriptive and administrative metadata for video content.

Pam Fisher, group lead, and the IPTC’s Video Metadata Working Group welcome feedback on the document. If your organisation handles video content, please read it and let us know what you think and what can be explained better. Comments can be send via this site’s Contact Us form or to the public Video Metadata Hub discussion list at https://groups.io/g/iptc-videometadata.

The guide can be seen at https://iptc.org/std/videometadatahub/userguide/.

On July 1st 2020, IPTC was invited to participate in an online workshop held by the Arab States Broadcasting Union (ASBU).

In a joint presentation, Brendan Quinn (IPTC Managing Director) and Robert Schmidt-Nia (Chair of IPTC and consultant with DATAGROUP Consulting Services) spoke on behalf of IPTC and Jürgen Grupp (data architect with the German public broadcaster SWR) spoke on behalf of the European Broadcasting Union.

The invitation was extended to IPTC and EBU because ASBU is looking at creating a common framework for sharing content between ASBU member broadcasters.

Jürgen Grupp started with an overview of why metadata is important in broadcasting and media organisations, and introduced the EBU’s high-level architecture for media, the EBU Class Conceptual Data Model (CCDM). and the EBUCore metadata set. Jürgen then gave examples of how CCDM and EBUCore are implemented by some European broadcasters.

Next, Brendan Quinn introduced IPTC and the IPTC News Architecture, the underlying logical model behind all of IPTC’s standards. We then took a deep dive into some video-related NewsML-G2 constructs like partMeta (used to describe metadata for parts of a video such as the rights and descriptive metadata for multiple time-based shots within a single video file) and contentSet (used to link to multiple renditions of the same video in different formats, resolutions or quality levels).

Then Robert Schmidt-Nia described some real-world examples of implementation of NewsML-G2 and the IPTC News Architecture at broadcasters and news agencies in Europe, in particular touching on the real-world issues of whether to “push” content or to create a “content API” that customers can use to select and download the content that they would like.

A common theme throughout our presentations was that the representation of the data in XML, RDF, JSON or some other format is relatively easy to change, but the important decision is what logical model to use and how to agree on the meaning (semantics) of terms and vocabularies.

A robust question and answer period touched on wide-ranging issues from the choices between XML, RDF and JSON, extending standardised models and vocabularies, and what decisions should be made to decide how to proceed.

This was one of the first meetings of ASBU on this topic and we look forward to assisting them further on their journey to metadata-based content sharing between their members.