{
  "$schema": "/api/schemas/documents.schema.json",
  "apiVersion": "1.0.0",
  "generatedAt": "2026-07-14T19:46:21.019Z",
  "sourcePath": "src/main/data/docs",
  "docId": "10.5594-JMI.2025-NSNH7881",
  "document": {
    "abbrevTitle": "SMPTE Motion Imaging Jour.",
    "abbrevTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "abstract": "In the realm of video encoding, achieving the optimal balance between encoding efficiency and computational complexity remains a formidable challenge. This paper introduces a groundbreaking framework that utilizes a Large Multimodal Model (LMM) to revolutionize the per-title video encoding optimization process. By harnessing the predictive capabilities of LMMs, our framework estimates the encoding complexity of video content with unprecedented accuracy, enabling the dynamic selection of encoding configurations tailored to each video's unique characteristics. The proposed framework marks a significant departure from traditional per-title encoding methods, which often rely on expensive and time-consuming sampling in the rate-distortion space. Through a comprehensive set of experiments, we demonstrate that our LMM-based approach significantly reduces the computational complexity required for sampling-based per-title video encoding by an astounding 13 times and maintains the same level of bitrate saving. These findings pave the way for more efficient and adaptive video encoding strategies and highlight the potential of multimodal models in enhancing multimedia processing tasks. The implications of this research extend beyond the immediate improvements in encoding efficiency, offering a glimpse into the future of multimedia content distribution and consumption in an increasingly video-centric digital landscape.",
    "abstract$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "authors": [
      {
        "name": "Zhengfang Duanmu"
      },
      {
        "name": "Mingzhe Jiang"
      }
    ],
    "authors$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "contentType": "orig-research",
    "contentType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "copyright": {
      "holder": "SMPTE",
      "holder$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      },
      "year": "2025",
      "year$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "copyright$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docId": "10.5594-JMI.2025-NSNH7881",
    "docId$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docLabel": "MIJ 2025, Volume 134, Number 4 (pp. 46 to 52)",
    "docLabel$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docTitle": "Large Multimodal Model-Based Video Encoding Optimization",
    "docTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docType": "Journal Article",
    "docType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "doi": "10.5594/JMI.2025/NSNH7881",
    "doi$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "href": "https://doi.org/10.5594/JMI.2025/NSNH7881",
    "href$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "issn": {
      "electronic": "2160-2492",
      "electronic$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      },
      "print": "1545-0279",
      "print$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "issn$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "journalAcronym": "MIJ",
    "journalAcronym$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "journalTitle": "SMPTE Motion Imaging Journal",
    "journalTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "keywords": [
      "Video Encoding Optimization",
      "Large Language Models (LLMs)",
      "Per-Title Encoding",
      "Rate-Distortion Analysis"
    ],
    "keywords$meta": {
      "confidence": "high",
      "note": "Long-tail keyword cleanup (keywordLongTailApply.js): prose/contentless terms dropped, acronym casing + typos fixed, duplicate variants folded; all surviving terms indexed in controlledKeywords.",
      "source": "resolved",
      "updated": "2026-07-14T16:29:38.680Z"
    },
    "number": "4",
    "number$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "pages": "46–52",
    "pages$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "publicationDate": "2025-07-01",
    "publicationDate$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "publisher": "SMPTE",
    "publisher$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "status": {
      "active": true,
      "active$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "volume": "134",
    "volume$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    }
  }
}