MVRLR: Multiple Perspectives Feature Representation Based on Low-rank Representation Learning for Short Video
Bibliographic record
Abstract
Abstract In recent years, with the rapid development of the Internet, multimedia information and its processing technology began to flourish. Today, smart terminals represented by smartphones are becoming more and more popular, and the era of mobile Internet has arrived. While changing the way multimedia information is composed and accessed, the Internet has also led to explosive growth in the amount of multimedia data. Short videos are often used as a social medium and spread on short video social platforms. Despite their limited length, short videos can always depict a relatively simple but complete story in a relatively short time. At the same time, they are always produced by non-professional users. We propose a short video feature presentation model MVRLR based on low-rank representation learning for multiple perspectives, which not only maximizes the complementarity and correlation among multiple perspectives, but also learns the subspace structure of lower dimensional eigenvalues through low-rank embedding; on this basis, we introduce a robust elastic regularization network to learn the potential label matrix to prevent the overfitting problem. Second, to further solve the high-dimensional and nonlinear problems of the data, the proposed model is extended to a multilinear form by constructing a new eigenmatrix through kernel functions to improve the model's ability to deal with high-dimensional nonlinear problems. We conduct several experiments to confirm that the model performs better than other baselines.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| 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".