Study on the Relevance of Jiangnan Garden Design Elements and Aesthetic Context Based on Visual Recognition
Bibliographic record
Abstract
Jiangnan gardens have become a valuable cultural heritage of China with its elegant garden style.The article proposes a binocular visual recognition system by analyzing the composition of the garden spatial elements and performing feature fusion based on scene-driven coefficients.Ablation experiments are conducted on each part of the constructed data enhancement framework for generating the design of the Jiangnan garden plan, which is applied to generate a set of high-quality datasets and apply the data to image segmentation for generating the design of the Jiangnan garden.The algorithm training is carried out by applying the generated design plan dataset.On this basis, the data from the actual Jiangnan garden research and the spatially quantized feature data are used to do the correlation analysis between the design elements and the aesthetic mood.The data enhancement framework constructed in this paper improves the IOU of ST elements to 0.537, and the average intersection and merger ratio MIOU is 0.389.It shows that the data evaluation framework based on visual recognition is suitable for the study of plan generation of Jiangnan gardens.The correlation coefficients of connection value, spatial control value, average depth value, and integration degree regarding aesthetic context with the data of Jiangnan garden design elements are 0.173, 0.301, -0.278, and 0.325, respectively, which indicate that there is a significant correlation between all of them.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".