Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03401 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913082270285824 |
|---|---|
| author | Platt, Nolan Nizamani, Sehrish Tural, Alp Tural, Elif Nizamani, Saad Katz, Andrew Lee, Yoonje Basit, Nada |
| author_facet | Platt, Nolan Nizamani, Sehrish Tural, Alp Tural, Elif Nizamani, Saad Katz, Andrew Lee, Yoonje Basit, Nada |
| contents | Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03401 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior Platt, Nolan Nizamani, Sehrish Tural, Alp Tural, Elif Nizamani, Saad Katz, Andrew Lee, Yoonje Basit, Nada Human-Computer Interaction Artificial Intelligence Computer Vision and Pattern Recognition H.5.2; I.2.7 Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts. |
| title | Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior |
| topic | Human-Computer Interaction Artificial Intelligence Computer Vision and Pattern Recognition H.5.2; I.2.7 |
| url | https://arxiv.org/abs/2604.03401 |