{
  "schema_version": "0.6.0",
  "paper_id": "ai-video-retrieval-semantic-search-timestamp-alignment",
  "page_url": "https://threadslab.org/research-publications/papers/ai-video-retrieval-semantic-search-timestamp-alignment/",
  "title": "AI Video Retrieval: A Semantic Search & Timestamp Alignment System",
  "title_variants": [],
  "authors": [
    "Hridoy Rahman",
    "Naser Ezzati-Jivan",
    "Blessing Ogbuokiri"
  ],
  "author_details": [
    {
      "name": "Hridoy Rahman",
      "orcid": null,
      "profile_url": "https://ieeexplore.ieee.org/author/366631566188381"
    },
    {
      "name": "Naser Ezzati-Jivan",
      "orcid": "https://orcid.org/0000-0003-1435-6297",
      "profile_url": "https://ieeexplore.ieee.org/author/37071999400"
    },
    {
      "name": "Blessing Ogbuokiri",
      "orcid": null,
      "profile_url": "https://ieeexplore.ieee.org/author/37088214110"
    }
  ],
  "publication": {
    "year": 2025,
    "venue": "2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)",
    "type": "conference paper",
    "publication_date": "2025-08-07",
    "online_date": null,
    "print_date": "2025-08-07",
    "volume": null,
    "issue": null,
    "pages": "1-6",
    "article_number": null,
    "publisher": "IEEE",
    "issn": [],
    "isbn": [],
    "crossref_type": "proceedings-article"
  },
  "publication_type": "conference paper",
  "status": "published_metadata_record",
  "canonical_source_url": "https://doi.org/10.1109/ACDSA65407.2025.11166430",
  "source_record_id": "ai-video-retrieval-a-semantic-search-timestamp-alignment-system-b0d72f7cf3",
  "identifiers": {
    "doi": "10.1109/ACDSA65407.2025.11166430"
  },
  "abstract": null,
  "abstract_source": "OpenAlex abstract metadata and IEEE record reviewed; abstract not reproduced because reuse permission for the publisher version was not established.",
  "abstract_available": false,
  "scholar_eligibility": {
    "eligible": false,
    "basis": "not-eligible",
    "note": "The page is a discovery record; it does not claim Google Scholar article-host eligibility."
  },
  "description": "The paper implements a timestamp-aware multimodal video-retrieval pipeline that joins speech transcription, sampled-frame captioning, text embeddings, and approximate-nearest-neighbor search.",
  "evidence_level": "full-text-reviewed",
  "evidence": {
    "source_basis": "full-text-reviewed",
    "coverage": "material paper sections",
    "summary_origin": "AI-assisted catalog editorial summary",
    "review_status": "catalog-reviewed; paper-author approval pending",
    "verified_on": "2026-08-26",
    "sources": [
      {
        "note": "Local PDF reviewed, including implementation, evaluation, and limitations sections"
      },
      {
        "note": "IEEE Xplore record: https://ieeexplore.ieee.org/document/11166430/"
      },
      {
        "note": "DOI metadata: https://doi.org/10.1109/ACDSA65407.2025.11166430"
      }
    ]
  },
  "summary": {
    "core_contribution": "The paper implements a timestamp-aware multimodal video-retrieval pipeline that joins speech transcription, sampled-frame captioning, text embeddings, and approximate-nearest-neighbor search.",
    "problem": "Keyword search and manual video tags do not reliably retrieve semantically related moments. A practical system must connect a natural-language query to the relevant time interval while indexing both spoken content and visual context at usable cost.",
    "method": "The implementation extracts and segments audio with PyDub 0.25.1, samples frames with OpenCV 4.11.0.86 at the stated 10% probability, and obtains segment/word timing with Whisper-Timestamped. BLIP captioning through Transformers 4.45.2 converts sampled frames to text. The system embeds transcripts and captions with all-MiniLM-L6-v2, indexes them with TXTAI 7.4.0 and HNSW-backed similarity search, and returns matches whose cosine/SIMILAR score is at least 0.30. Django 5.1.5 provides the application layer and JSON stores the timestamped metadata.",
    "findings": "The paper evaluates 100 pre-indexed videos with 30 Brock graduate and undergraduate participants. The reported indexing time is approximately 30–40 seconds for a 6–8 minute video, and the interface returns audio, visual, or multimodal matches with timestamps. The usability study reports generally positive relevance, timestamp usefulness, clarity, and recommendation responses; the paper also reports faster retrieval as the indexed collection grows.",
    "limitations": "The evaluation uses a small user study and a limited video collection rather than a standard retrieval benchmark with annotated temporal ground truth. The system covers speech and sampled visual captions but not OCR, explicit object detection, action recognition, or a broad comparison against retrieval baselines. The paper's implementation section and documentation also contain a TXTAI version discrepancy that should be preserved as a reproducibility caveat.",
    "future_work": "Add OCR, object and action features, richer multimodal fusion, standard temporal-retrieval metrics, larger and more diverse video corpora, and systematic latency/quality comparisons against dense-video-retrieval baselines."
  },
  "tags": [
    "multimodal-ai",
    "machine-learning",
    "benchmark-datasets"
  ],
  "keywords": [
    "video retrieval",
    "semantic search",
    "timestamp alignment",
    "AI video search",
    "ACDSA 2025"
  ],
  "versions": [
    {
      "id": "published-version",
      "label": "Published version",
      "relation": "version-of-record",
      "title": "AI Video Retrieval: A Semantic Search & Timestamp Alignment System",
      "url": "https://doi.org/10.1109/ACDSA65407.2025.11166430",
      "pdf_url": null,
      "status": "published",
      "canonical_for_citation": true
    },
    {
      "id": "ieee-record",
      "label": "IEEE record",
      "relation": "source-record",
      "title": "AI Video Retrieval: A Semantic Search & Timestamp Alignment System",
      "url": "https://ieeexplore.ieee.org/document/11166430/",
      "pdf_url": null,
      "status": "public_source_record",
      "canonical_for_citation": false
    }
  ],
  "access": {
    "status": "published_metadata_record",
    "note": "IEEE, Crossref, and J-GLOBAL verify the identity and DOI. The publisher PDF was not available through normal access; technical details are pending full-text review.",
    "license": null
  },
  "resources": {
    "code": null,
    "data": null,
    "slides": null,
    "demo": null
  },
  "citation_guidance": {
    "when_to_cite": "Cite this paper when your work performs timestamp-aware semantic retrieval over speech and visual video content.",
    "points": [
      "The Whisper-Timestamped plus BLIP multimodal indexing pipeline.",
      "Timestamped audio/visual sub-indexes with embedding similarity and HNSW retrieval.",
      "The 30-participant, 100-video usability evaluation and reported 0.30 similarity threshold.",
      "Future multimodal extensions such as OCR, object detection, and action recognition."
    ],
    "canonical_version_id": "published-version"
  },
  "provenance": {
    "metadata_verified_on": "2026-08-26",
    "metadata_source": [
      "Local PDF reviewed, including implementation, evaluation, and limitations sections",
      "IEEE Xplore record: https://ieeexplore.ieee.org/document/11166430/",
      "DOI metadata: https://doi.org/10.1109/ACDSA65407.2025.11166430"
    ],
    "summary_written_by": "AI-assisted",
    "summary_verified_by": "full-text-grounded catalog review; author approval pending",
    "linked_preprint_record": null,
    "author_order_note": null
  },
  "batch": {
    "phase": 2,
    "batch_label": "expanded forty-paper release",
    "status": "included_in_expanded_catalog",
    "selected_at": "2026-08-28"
  }
}