Bibliographic record
Abstract
Nowadays, access to information requires to manage effectively multimedia databases, and among challenges offered to scientific community since last decades, multimedia retrieval techniques (particularly images retrieval) are became an active research direction. Introduced to overcome the main drawbacks encountered by text-based images retrieval, which are the subjective and manual annotation of images, content based images retrieval (CBIR) systems index images according to low-level visual features such as color, texture, shape to retrieve similar images. However, despite the progress achieved in the content based image retrieval, in particular with the relevance feedback approach where the user refine the search via the specification of relevant or not relevant items, the current CBIR systems still have a major difficulty that it has yet to overcome: how to negotiate the "semantic gap"? This problem comes from the mismatch between their capabilities and the needs of users. In this paper, we address the problem of how relate lowlevel features to high level to bring out semantic concepts from images. Our aim is to combine contentbased and metadata-based approaches for image retrieval from a user perspective to yield better results and overcome to the lacks of these techniques when they are taken separately. To represent the semantic content of images, we propose a model which takes account of the interaction between the user and the metadata. In particular, we model the semantic user' preference by analyzing its answers through the Relevance Feedback process. Furthermore, we introduce a new machine learning technique that modify the weights (i.e. relative importance) of metadata representing the semantic content of images.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| 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".