Dataset-driven new set of video quality evaluations towards reference-free video quality evaluations
Bibliographic record
Abstract
The popularity of network video service, which leads to the specification of the network video service quality is becoming more and more urgent, and human is the ultimate watch users of network video, Evaluation of human observers on the video’s perception of the situation is becoming more important, depending on the source video network video know nothing, you will need to refer to the participation of video quality evaluation algorithm. However, when the quality evaluation is done by human rating, it is time-consuming and laborious, so the computer is required to make an objective evaluation of the video. In the objective evaluation, the excellent performance of convolutional neural network based on deep learning in feature extraction contributes to the rapid development of the research field of video quality evaluation. However, the development of deep learning algorithms requires appropriate data sets for training and testing. The existing data sets are relatively small in scale and not comprehensive in terms of video content types and distortion types. Therefore, it is necessary to provide a new data set to evaluate the quality of video without reference, expand the scale of the data set, expand the content and distortion type of the video. At the same time, considering the new development of network video services, the video resolution is positioned as high definition, and the original video sampling ratio is 4:2:2. The dataset is freely available to relevant researchers for scientific research.
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 | 0.004 | 0.015 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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".