{
  "$schema": "/api/schemas/documents.schema.json",
  "apiVersion": "1.1.0",
  "lastModified": "2026-10-07T20:50:36.411Z",
  "sourcePath": "src/main/data/docs",
  "docId": "10.5594-M001973",
  "document": {
    "abstract": "Recent advances in Machine Learning (ML) have produced a new form of semantic indexing that lets users enhance searches, as well as gain new insights into their media libraries. Unlike typical search systems that use extracted metadata, semantic indexing allows users to find relevant material without the need to tag the media with selections from a predefined taxonomy. With semantic search, users can simply enter unstructured text, and the system will find the best matching media clips. The paper extends the use of the same technology to gather analytics on the data which can then be further correlated to generate various insights. — This new form of media indexing can be performed with the CLIP model from OpenAI. The model encodes images and text into embeddings that can be searched to find the closest semantic similarity, enhanced with learned cultural knowledge. This type of indexing can be made practical using a database like Elasticsearch. The system has the benefit of finding media based on keywords, synonyms, and summaries. The same system can also be used for analytics and insights, such as clustering, shot detection, and creating a 2-dimensional map to display correlations. — The paper also presents extensions to the semantic search systems. Based on a study of multiple existing models, these extensions provide new capabilities - to handle many media types, using additional languages, search for spoken phrases in audio files, finding both verbatim and semantically similar phrases, extracting semantic information that leverages multiple video frames, and searching for ambient sounds.",
    "abstract$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "authors": [
      {
        "affiliation": "Engineering Fellow, Avid Technology",
        "name": "Rob Gonsalves"
      },
      {
        "affiliation": "Concordia University, Avid Technology",
        "name": "Zahra Montajabi"
      },
      {
        "affiliation": "V.P. Architecture, Avid Technology",
        "name": "Shailendra Mathur"
      },
      {
        "affiliation": "PhD, Concordia University",
        "name": "Nizar Bouguila"
      }
    ],
    "authors$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "contentType": "orig-research",
    "contentType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "copyright": {
      "holder": "Society of Motion Picture and Television Engineers, Inc.",
      "holder$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      },
      "year": "2022",
      "year$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "copyright$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docId": "10.5594-M001973",
    "docId$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docLabel": "SMPTE Meetings and Conferences ( October 2022)",
    "docLabel$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docTitle": "ML-Based Indexing of Media Libraries for Insights and Search",
    "docTitle$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docType": "Conference Paper",
    "docType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "doi": "10.5594/M001973",
    "doi$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "href": "https://doi.org/10.5594/M001973",
    "href$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "isbn": {
      "print": "978-1-61482-963-8",
      "print$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "isbn$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "keywords": [
      "Artificial Intelligence",
      "Machine Learning",
      "Media Search",
      "Semantic Search",
      "OpenAI CLIP",
      "Multilingual CLIP",
      "Wav2vec2",
      "CLIP4Clip",
      "Wav2CLIP",
      "Microsoft CLAP"
    ],
    "keywords$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "number": "10",
    "number$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "pages": "1–17",
    "pages$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publicationDate": "2022-10-24",
    "publicationDate$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publisher": "SMPTE",
    "publisher$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publisherLocation": {
      "city": "White Plains, NY",
      "city$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      },
      "country": "USA",
      "country$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "publisherLocation$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "references": {
      "bibliographic": [
        "orphan/10.5594-M001973/h:2dcf4005",
        "orphan/10.5594-M001973/h:994211f6",
        "orphan/10.5594-M001973/h:6a148a27",
        "orphan/10.5594-M001973/h:e230747b",
        "orphan/10.5594-M001973/h:4d469b50",
        "orphan/10.5594-M001973/h:21ee4484",
        "orphan/10.5594-M001973/h:48bb850d",
        "orphan/10.5594-M001973/h:10ad91b3",
        "orphan/10.5594-M001973/h:5a3cc712",
        "orphan/10.5594-M001973/h:dc94f0bb",
        "orphan/10.5594-M001973/h:e42d54c3",
        "orphan/10.5594-M001973/h:938332cc",
        "orphan/10.5594-M001973/h:80e6ac4f",
        "orphan/10.5594-M001973/h:e2beb505",
        "orphan/10.5594-M001973/h:7c636068",
        "orphan/10.5594-M001973/h:2ab89e98",
        "orphan/10.5594-M001973/h:85393f68",
        "orphan/10.5594-M001973/h:97360fd5",
        "orphan/10.5594-M001973/h:e0f67d66",
        "orphan/10.5594-M001973/h:104c14cc",
        "orphan/10.5594-M001973/h:b7602735",
        "orphan/10.5594-M001973/h:3219757e",
        "orphan/10.5594-M001973/h:226e536c",
        "orphan/10.5594-M001973/h:f858213d",
        "orphan/10.5594-M001973/h:5a9b02cc",
        "orphan/10.5594-M001973/h:d8ed6318"
      ],
      "bibliographic$meta": {
        "confidence": "medium",
        "note": "References parsed from the published PDF (Conference Repository/Conference Papers/2022/10012556/10012557/10012597.pdf). SMPTE's library delivery has no reference file or full text for this paper (src/main/reports/smpte-upstream/referenceFilesTruthTable.md). Cross-check: Crossref lists 26 reference(s) for this DOI; 26 parsed from the PDF.",
        "originalValue": [],
        "overridden": true,
        "source": "parsed",
        "updated": "2026-10-07T20:50:36.411Z",
        "version": "extractDocs.js@commit:d25f34130540"
      }
    },
    "status": {
      "active": true,
      "active$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "volume": "2022",
    "volume$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2022/10012556/10012557/10012597.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    }
  }
}