Video-4-Video: using video for searching, classifying and summarising video
Bibliographic record
Abstract
YouTube has meant that we are now becoming accustomed to searching for video clips, and finding them, for both work and leisure pursuits. But YouTube, like the Internet Archive, OpenVideo and almost everything other video library, doesn't use video to find video, it uses metadata, usually based on user generated content (UGC). But what if we don't know what we're looking for and the metadata doesn't help, or we have poor metadata or no UGC, can we use the video to find video ? Can we automatically derive semantic concepts directly from video which we can use for retrieval or summarisation ? Many dozens of research groups throughout the world work on the problems associated with content-based video search, content-based detection of semantic concepts, shot boundary detection, content-based summarisation and content-based event detection. In this presentation we give a summary of the achievements of almost a decade of research by the TRECVid community, including a report on performance of groups in different TRECVid tasks. We present the modus operandi of the annual TRECVid benchmarking, the problems associated with running an annual evaluation for nearly 100 research groups every year and an overview of the most successful approaches to each task.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.007 |
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".