{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prediction-and-localization-of-student","title":"Prediction and Localization of Student Engagement in the Wild","arxiv_id":"1804.00858","date":"2018-04-03","proceeding":null,"authors":["Amanjot Kaur","Aamir Mustafa","Love Mehta","Abhinav Dhall"],"abstract":"In this paper, we introduce a new dataset for student engagement detection\nand localization. Digital revolution has transformed the traditional teaching\nprocedure and a result analysis of the student engagement in an e-learning\nenvironment would facilitate effective task accomplishment and learning. Well\nknown social cues of engagement/disengagement can be inferred from facial\nexpressions, body movements and gaze pattern. In this paper, student's response\nto various stimuli videos are recorded and important cues are extracted to\nestimate variations in engagement level. In this paper, we study the\nassociation of a subject's behavioral cues with his/her engagement level, as\nannotated by labelers. We then localize engaging/non-engaging parts in the\nstimuli videos using a deep multiple instance learning based framework, which\ncan give useful insight into designing Massive Open Online Courses (MOOCs)\nvideo material. Recognizing the lack of any publicly available dataset in the\ndomain of user engagement, a new `in the wild' dataset is created to study the\nsubject engagement problem. The dataset contains 195 videos captured from 78\nsubjects which is about 16.5 hours of recording. We present detailed baseline\nresults using different classifiers ranging from traditional machine learning\nto deep learning based approaches. The subject independent analysis is\nperformed so that it can be generalized to new users. The problem of engagement\nprediction is modeled as a weakly supervised learning problem. The dataset is\nmanually annotated by different labelers for four levels of engagement\nindependently and the correlation studies between annotated and predicted\nlabels of videos by different classifiers is reported. This dataset creation is\nan effort to facilitate research in various e-learning environments such as\nintelligent tutoring systems, MOOCs, and others.","url_abs":"http://arxiv.org/abs/1804.00858v4","url_pdf":"http://arxiv.org/pdf/1804.00858v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prediction-and-localization-of-student","repo_url":"https://github.com/CopurOnur/ED-MTT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.00858","atlas_url":"https://app.syntology.ai/?focus=1804.00858","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}