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

• URL: http://arxiv.org/abs/2603.13679v1
• Date: Sat, 14 Mar 2026 01:04:58 GMT
• Title: Toward Scalable Co-located Practical Learning: Assisting with Computer Vision and Multimodal Analytics
• Abstract summary: This study examined whether a single ceiling-mounted camera could be used to capture fine-grained learning behaviours in co-located practical learning.<n>In undergraduate nursing simulations, teachers first identified seven observable behaviour categories, which were then used to train a YOLO-based detector.<n>Video data were collected from 52 sessions, and analyses focused on Scenario A because it produced greater behavioural variation than Scenario B.<n>The study shows that a single-camera computer vision approach can support the analysis of teamwork and task engagement in face-to-face practical learning without relying on wearable sensors.
• Score: 13.632792983535822
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study examined whether a single ceiling-mounted camera could be used to capture fine-grained learning behaviours in co-located practical learning. In undergraduate nursing simulations, teachers first identified seven observable behaviour categories, which were then used to train a YOLO-based detector. Video data were collected from 52 sessions, and analyses focused on Scenario A because it produced greater behavioural variation than Scenario B. Annotation reliability was high (F1=0.933). On the held-out test set, the model achieved a precision of 0.789, a recall of 0.784, and an mAP@0.5 of 0.827. When only behaviour frequencies were compared, no robust differences were found between high- and low-performing groups. However, when behaviour labels were analysed together with spatial context, clear differences emerged in both task and collaboration performance. Higher-performing teams showed more patient interaction in the primary work area, whereas lower-performing teams showed more phone-related activity and more activity in secondary areas. These findings suggest that behavioural data are more informative when interpreted together with where they occur. Overall, the study shows that a single-camera computer vision approach can support the analysis of teamwork and task engagement in face-to-face practical learning without relying on wearable sensors.

Related papers

• Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success? [0.12314765641075437]
  We examine alignment in cybersecurity simulations using multimodal traces from 23 teams (76 students) across five exercise sessions.<n> Alignment, defined as the discrepancy between required and enacted Bloom levels, predicts success, whereas the Bloom category alone does not predict success once discrepancy is considered.
  arXiv  Detail & Related papers  (2026-03-30T15:14:56Z)
• Uncovering Memorization Effect in the Presence of Spurious Correlations [19.824897288786303]
  This paper systematically shows the existence of spurious features in a small set of neurons within the network.<n>We show that spurious memorization, concentrated within a small subset of neurons, plays a key role in driving imbalanced group performance.
  arXiv  Detail & Related papers  (2025-01-01T21:45:00Z)
• Self-Supervised Approach to Addressing Zero-Shot Learning Problem [7.125631269067275]
  A common pretext task is the measure of similarity and dissimilarity between pairs of images. In this study, we explored the performance of a Siamese neural network using contrastive loss. Our results show a 61% F1-score on zero-shot instances, a performance showing 11% improvement on samples of classes that share intersections with the training set.
  arXiv  Detail & Related papers  (2022-01-05T00:08:36Z)
• ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection [102.9428507180728]
  A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially on rare classes.
  arXiv  Detail & Related papers  (2021-09-09T06:02:50Z)
• Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss [72.62029620566925]
  Recent works in self-supervised learning have advanced the state-of-the-art by relying on the contrastive learning paradigm. Our work analyzes contrastive learning without assuming conditional independence of positive pairs. We propose a loss that performs spectral decomposition on the population augmentation graph and can be succinctly written as a contrastive learning objective.
  arXiv  Detail & Related papers  (2021-06-08T07:41:02Z)
• Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
  dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
  arXiv  Detail & Related papers  (2021-04-14T14:20:22Z)
• Learning task-agnostic representation via toddler-inspired learning [19.478820330574628]
  We derive inspiration from a highly intentional learning system via action: the toddler. Inspired by the toddler's learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation. Experimental results show that such obtained representation was expandable to various vision tasks.
  arXiv  Detail & Related papers  (2021-01-27T06:26:56Z)
• Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination [68.83098015578874]
  We integrate between-instance similarity into contrastive learning, not directly by instance grouping, but by cross-level discrimination. CLD effectively brings unsupervised learning closer to natural data and real-world applications. New state-of-the-art on self-supervision, semi-supervision, and transfer learning benchmarks, and beats MoCo v2 and SimCLR on every reported performance.
  arXiv  Detail & Related papers  (2020-08-09T21:13:13Z)
• Detecting Human-Object Interactions with Action Co-occurrence Priors [108.31956827512376]
  A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially in rare classes.
  arXiv  Detail & Related papers  (2020-07-17T02:47:45Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.