AI Video Retrieval: A Semantic Search & Timestamp Alignment System
Bibliographic record
Abstract
Traditional video search systems depend on keywords and manual tagging, limiting their ability to retrieve video segments that semantically match user queries. While recent studies explore image captioning and audio-based retrieval, real-time, scalable frameworks with multimodal indexing remain limited. This paper presents an AI Video Retrieval (AIVR) system that overcomes these challenges using deep learning models—Whisper-Timestamped for speech transcription, Blip for frame captioning, and Sentence Transformers for embedding generation. Integrated through Django and indexed with TXTAI, the system supports real-time video uploads, transcribes audio, captions sampled frames, and structures multimodal data in JSON for efficient semantic search. It retrieves accurate video segments based on natural language queries and demonstrates improved retrieval relevance, timestamp precision, and usability over traditional methods. The framework is extendable with OCR, object detection, and action recognition, and has practical applications in education, media, and surveillance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".