# Toward Scalable Co-located Practical Learning: Assisting with Computer Vision and Multimodal Analytics

arXiv: https://arxiv.org/abs/2603.13679 · HTML: https://mlsanity.com/paper/2603.13679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 77 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer](https://mlsanity.com/paper/2407.17140/) (2024)
- [Multimodal Engagement Analysis from Facial Videos in the Classroom](https://mlsanity.com/paper/2101.04215/) (2021)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [Lessons Learnt from a Multimodal Learning Analytics Deployment In-the-wild](https://mlsanity.com/paper/2303.09099/) (2023)
- [EPARS: Early Prediction of At-risk Students with Online and Offline Learning Behaviors](https://mlsanity.com/paper/2006.03857/) (2020)
- [Heterogenous Network Analytics of Small Group Teamwork: Using Multimodal Data to Uncover Individual Behavioral Engagement Strategies](https://mlsanity.com/paper/2312.08786/) (2023)
- [Striving for Authentic and Sustained Technology Use In the Classroom: Lessons Learned from a Longitudinal Evaluation of a Sensor-based Science Education Platform](https://mlsanity.com/paper/2304.03450/) (2023)

## Abstract (arXiv)

Co-located practical learning leaves evidence in visible actions around patients, task resources and room zones, but these traces are often recovered through live observation or retrospective video review. Fixed wide-angle video could reduce sensing burden, yet a debriefing pipeline must do more than detect behaviours: it must maintain detection after small camera-position shifts, relate the detector-derived behaviour trace to instructor-labelled outcomes and preserve room-zone context. This study evaluates a fixed-camera pipeline in repeated nursing simulation. Using a harmonised six-code taxonomy, we tested YOLO26 target-only training and two-stage source-to-target adaptation across two same-room side-view data sources. We then converted detections from 51 instructor-labelled sessions into one-second behaviour and behaviour-zone traces for rate, ordered-network, transition-network and sequence analyses. Two-stage adaptation improved mean mAP50 from 0.815 to 0.848 for the 2021 target view and from 0.690 to 0.855 for the smaller 2022 target view; with a balanced target quota of (N = 22), the 2022 model reached 0.850 mAP50. In the detector-derived behaviour trace analyses, higher phone use characterised low task-performance sessions. Zone labels changed the interpretation of patient interaction: primary patient-care-zone interaction was stronger in higher-performance sessions, while secondary-zone interaction was stronger in lower-performance sessions. Ordered and transition network models showed that ordered room-zone relations contributed beyond behaviour frequency, with the strongest task-performance classifier using zoned and co-presence features. The resulting trace is most appropriate for searchable simulation debriefing, where instructors inspect detected moments rather than receive automated assessment scores.