Toward an Application of Content-Based Video Indexing to Computer- Assisted Descriptive Video
Bibliographic record
Abstract
This paper presents the status of a project targeting the development of content-based video indexing tools, to assist a human in the generation of descriptive video for the hard of seeing people. We describe three main elements: (1) the video content that is pertinent for computer-assisted descriptive video, (2) the system dataflow, based on a light plug-in architecture of an open-source video processing software and (3) the first version of the plug-ins developed to date. Plugs-ins that are under development include shot transition detection, key-frames identification, keyface detection, key-text spotting, visual motion mapping, face recognition, facial characterization, story segmentation, gait/gesture characterization, keyplace recognition, key-object spotting and image categorization. Some of these tools are adapted from our previous works on video surveillance, audiovisual speech recognition and content-based video indexing of documentary films. We do not focus on the algorithmic details in this paper neither on the global performance since the integration is done yet. We rather concentrate on discussing application issues of automatic descriptive video usability aspects.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".