Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.05852 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911735274799104 |
|---|---|
| author | Hamid, Kaiser Akbar, Khandakar Ashrafi Li, Peihang Liang, Nade |
| author_facet | Hamid, Kaiser Akbar, Khandakar Ashrafi Li, Peihang Liang, Nade |
| contents | Driver gaze is commonly modeled as a spatial heatmap, but heatmaps alone are difficult for humans to interpret because they do not explain which road object or region is being monitored or why an attention shift may matter. This study examines whether minimal human-grounded supervision can steer a vision--language model toward interpretable descriptions of driver attention shifts. Using selected high-change gaze moments from the Berkeley DeepDrive-Attention dataset, we compare zero-shot, one-shot, and LoRA fine-tuned VLM conditions against human-refined reference descriptions and expert ratings. Results show that fine-tuning with 80 expert-refined attention examples improves ROUGE-L, METEOR, Entity Alignment F1, and Human Alignment Score relative to unsteered VLM outputs. The findings suggest that language-based descriptions can complement gaze heatmaps by making driver attention more accessible for human-factors analysis, driver-monitoring review, and situation-awareness support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interpretable Modeling of Driver Attention Shifts with a Vision--Language Model Hamid, Kaiser Akbar, Khandakar Ashrafi Li, Peihang Liang, Nade Computer Vision and Pattern Recognition I.5.4 Driver gaze is commonly modeled as a spatial heatmap, but heatmaps alone are difficult for humans to interpret because they do not explain which road object or region is being monitored or why an attention shift may matter. This study examines whether minimal human-grounded supervision can steer a vision--language model toward interpretable descriptions of driver attention shifts. Using selected high-change gaze moments from the Berkeley DeepDrive-Attention dataset, we compare zero-shot, one-shot, and LoRA fine-tuned VLM conditions against human-refined reference descriptions and expert ratings. Results show that fine-tuning with 80 expert-refined attention examples improves ROUGE-L, METEOR, Entity Alignment F1, and Human Alignment Score relative to unsteered VLM outputs. The findings suggest that language-based descriptions can complement gaze heatmaps by making driver attention more accessible for human-factors analysis, driver-monitoring review, and situation-awareness support. |
| title | Interpretable Modeling of Driver Attention Shifts with a Vision--Language Model |
| topic | Computer Vision and Pattern Recognition I.5.4 |
| url | https://arxiv.org/abs/2508.05852 |