Designing Multimodal Video Search by Examples (MVSE) user interfaces: UX requirements elicitation and insights from semi-structured interviews
Bibliographic record
Abstract
In order to search for content from large video archives, it is typically undertaken via keyword queries using predefined metadata such as title and other tags. However, it is difficult to use keywords to search for specific moments in a video. Video search by examples is a desirable approach for this scenario as it allows users to search for content using one or more examples without having to specify a keyword. However, video search by examples is notoriously challenging, and performance is poor. To improve search performance, multiple modalities may be considered – image, sound, voice and text, multiple search cues could be used to identify more relevant content. This is multimodal video search by examples (MVSE), where users can search for content using multiple modalities. In this paper, typical end users - BBC archivists, programme support staff - are interviewed to identify how their search needs can be addressed with the technical capabilities of a MVSE tool. Such a search tool will be useful for organisations such as the BBC who maintain large collections of video archives and want to provide a search tool for their own staff as well as for the public. It will also be useful for companies such as Youtube who host videos from the public and want to enable video search by examples. The study’s objectives explored in this paper were to inform the design and development of the UX workflows to gain a broader understanding of what opportunities and issues may arise from the proposed prototype tool. Results from the thematic analysis was highlighted 4 main themes: Opportunities, Time constraints, Activities, and Pain points. Further analysis highlighted key areas that should be considered for an MVSE-based system, such as scene recognition, face recognition, speed issues, and integration..
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 | 0.027 | 0.044 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".