{"total":25,"rows":[{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2104.10122","title":"Improving state-of-the-art in Detecting Student Engagement with Resnet and TCN Hybrid Network","created":"2021-04-20","cited_by_count":22,"area":null},{"id":"2106.10882","title":"Affect-driven Ordinal Engagement Measurement from Video","created":"2021-06-21","cited_by_count":11,"area":null},{"id":"2304.05292","title":"MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos","created":"2023-04-11","cited_by_count":11,"area":null},{"id":"2404.15310","title":"Automated Assessment of Encouragement and Warmth in Classrooms Leveraging Multimodal Emotional Features and ChatGPT","created":"2024-04-01","cited_by_count":7,"area":null},{"id":"2211.06870","title":"Detecting Disengagement in Virtual Learning as an Anomaly using Temporal Convolutional Network Autoencoder","created":"2022-11-13","cited_by_count":6,"area":null},{"id":"2301.06730","title":"Bag of States: A Non-sequential Approach to Video-based Engagement Measurement","created":"2023-01-17","cited_by_count":5,"area":null},{"id":"2304.00377","title":"Beyond One-Size-Fits-All: A Survey of Personalized Affective Computing in Human-Agent Interaction","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2403.08824","title":"Computational Analysis of Stress, Depression and Engagement in Mental Health: A Survey","created":"2024-03-09","cited_by_count":4,"area":null},{"id":"2408.14491","title":"Multimodal Methods for Analyzing Learning and Training Environments: A Systematic Literature Review","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2312.09066","title":"CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2307.09420","title":"Measuring Student Behavioral Engagement using Histogram of Actions","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2504.19271","title":"Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detection","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2505.07552","title":"Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.07902","title":"Multimodal Assessment of Classroom Discourse Quality: A Text-Centered Attention-Based Multi-Task Learning Approach","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2209.08614","title":"Deep Adaptation of Adult-Child Facial Expressions by Fusing Landmark Features","created":"2022-09-18","cited_by_count":1,"area":null},{"id":"2308.15119","title":"AI-Based Facial Emotion Recognition Solutions for Education: A Study of Teacher-User and Other Categories","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2408.06874","title":"Leveraging Language Models for Emotion and Behavior Analysis in Education","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2208.04548","title":"Inconsistencies in the Definition and Annotation of Student Engagement in Virtual Learning Datasets: A Critical Review","created":"2022-08-09","cited_by_count":0,"area":null},{"id":"2312.05797","title":"Multimodality in Online Education: A Comparative Study","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2409.16126","title":"VisioPhysioENet: Visual Physiological Engagement Detection Network","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2512.20059","title":"DS-HGCN: A Dual-Stream Hypergraph Convolutional Network for Predicting Student Engagement via Social Contagion","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2602.09904","title":"Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.13679","title":"Toward Scalable Co-located Practical Learning: Assisting with Computer Vision and Multimodal Analytics","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.16806","title":"Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}