[Case Study] Transfer Learning with Inflated 3D CNN for Word-Level Recognition for Azerbaijani Sign Language Dataset
Bibliographic record
Abstract
Sign language is a non-verbal form of communication primarily used by the Deaf and Hard of Hearing (DHH).Sign language recognition (SLR) is the automatic recognition of sign language that treats each sign as a class.In related work, significant progress has been made using deep learning techniques.Large amounts of data are typically required to train deep learning models effectively.In the academic community working on SLR, different well-tuned models provide benchmarking on different sign language datasets, and many sign languages still lack corresponding datasets, making it challenging to train models for these languages.Transfer learning is a technique that utilizes a related task with abundant available data to solve a target task with insufficient data.Transfer learning has been successfully applied in computer vision and SLR.This study investigates how effectively transfer learning can be applied to isolated SLR using an inflated 3D convolutional neural network as a deep learning architecture.Transfer learning is implemented by pre-training a network and subsequently fine-tuning it on a small Azerbaijani Sign Language Dataset.This approach is promising because it leverages the knowledge gained from a related task with more abundant data to enhance the model's performance on the target SLR 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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 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".