Hybrid-Based Compressed Domain Video Fingerprinting Technique
Bibliographic record
Abstract
Video fingerprinting is a newer research area. It is also called “content-based video copy detection” or “content-based video identification” in literature. The goal is to locate videos with segments substantially identical to segments of a query video while tolerating common artifacts in video processing. Its value as a tool to curb piracy and legally monetize contents becomes more and more apparent in recent years with the wide spread of Internet videos through user generated content (UGC) sites like YouTube. Its practical applications to a certain extent overlap with those of digital watermarking, which requires adding artificial information into the contents. Fingerprints are compact content-based signature that summarizes a video signal or another media signal. Several video fingerprinting methods have been proposed for identifying video, in which fingerprints are extracted by analyzing video in both spatial and temporal dimension. However, these conventional methods have one resemblance, in which video decompression is still required for extracting the fingerprint from a compressed video. In practical, faster computational time can be achieved if fingerprint is extracted directly from the compressed domain. So far, too fewer methods are known to propose video fingerprinting in compressed domain. This paper presents a video fingerprinting technique that works directly in the compressed domain. Experimental results show that the proposed fingerprint is highly robust against most signal processing transformations.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".