Umang Mathur - Academia.edu (original) (raw)
Uploads
Papers by Umang Mathur
International journal of computer applications, Nov 17, 2015
E-Learning platforms are increasingly used in universities, colleges and companies seeking effect... more E-Learning platforms are increasingly used in universities, colleges and companies seeking effective and continuous training of their employees without constraint of time and space. The effectiveness of such a learning system depends mainly on the degree of information assimilated by the learner at the end of training. In this project, the focus is on the implementation of a system for measuring competence for computer sciences. This system uses the model of item response theory. The results provided by this system are presented to the student, as a dashboard. They will allow the teacher or tutor to have the necessary elements to monitor their learning by identifying the causes blocking and checking its achievements. The emphasis of this project is to enable the learner to understand and simultaneously implement the concepts that have been designed by the content author or teacher. It is primarily geared towards enabling students to use an interactive E-Learning system that uses an algorithm based approach to assess skill levels. This system can also help to improve the recruitment process of companies using it in the selection process of candidates for jobs.
Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, 2020
Video accessibility is crucial for blind and visually impaired individuals for education, employm... more Video accessibility is crucial for blind and visually impaired individuals for education, employment, and entertainment purposes. However, professional video descriptions are costly and time-consuming. Volunteer-created video descriptions could be a promising alternative, however, they can vary in quality and can be intimidating for novice describers. We developed a Human-in-the-Loop Machine Learning (HILML) approach to video description by automating video text generation and scene segmentation while allowing humans to edit the output. Our HILML system was significantly faster and easier to use for first-time video describers compared to a human-only control condition with no machine learning assistance. The quality of the video descriptions and understanding of the topic created by the HILML system compared to the human-only condition were rated as being significantly higher by blind and visually impaired users.
Proceedings of the 2020 ACM Designing Interactive Systems Conference, 2020
Video accessibility is crucial for blind and visually impaired individuals for education, employm... more Video accessibility is crucial for blind and visually impaired individuals for education, employment, and entertainment purposes. However, professional video descriptions are costly and time-consuming. Volunteer-created video descriptions could be a promising alternative, however, they can vary in quality and can be intimidating for novice describers. We developed a Human-in-the-Loop Machine Learning (HILML) approach to video description by automating video text generation and scene segmentation and allowing humans to edit the output. The HILML approach facilitates human-machine collaboration to produce high quality video descriptions while keeping a low barrier to entry for volunteer describers. Our HILML system was signifcantly faster and easier to use for frst-time video describers compared to a human-only control condition with no machine learning assistance. The quality of the video descriptions and understanding of the topic created by the HILML system compared to the human-only condition were rated as being signifcantly higher by blind and visually impaired users.
International journal of computer applications, Nov 17, 2015
E-Learning platforms are increasingly used in universities, colleges and companies seeking effect... more E-Learning platforms are increasingly used in universities, colleges and companies seeking effective and continuous training of their employees without constraint of time and space. The effectiveness of such a learning system depends mainly on the degree of information assimilated by the learner at the end of training. In this project, the focus is on the implementation of a system for measuring competence for computer sciences. This system uses the model of item response theory. The results provided by this system are presented to the student, as a dashboard. They will allow the teacher or tutor to have the necessary elements to monitor their learning by identifying the causes blocking and checking its achievements. The emphasis of this project is to enable the learner to understand and simultaneously implement the concepts that have been designed by the content author or teacher. It is primarily geared towards enabling students to use an interactive E-Learning system that uses an algorithm based approach to assess skill levels. This system can also help to improve the recruitment process of companies using it in the selection process of candidates for jobs.
Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, 2020
Video accessibility is crucial for blind and visually impaired individuals for education, employm... more Video accessibility is crucial for blind and visually impaired individuals for education, employment, and entertainment purposes. However, professional video descriptions are costly and time-consuming. Volunteer-created video descriptions could be a promising alternative, however, they can vary in quality and can be intimidating for novice describers. We developed a Human-in-the-Loop Machine Learning (HILML) approach to video description by automating video text generation and scene segmentation while allowing humans to edit the output. Our HILML system was significantly faster and easier to use for first-time video describers compared to a human-only control condition with no machine learning assistance. The quality of the video descriptions and understanding of the topic created by the HILML system compared to the human-only condition were rated as being significantly higher by blind and visually impaired users.
Proceedings of the 2020 ACM Designing Interactive Systems Conference, 2020
Video accessibility is crucial for blind and visually impaired individuals for education, employm... more Video accessibility is crucial for blind and visually impaired individuals for education, employment, and entertainment purposes. However, professional video descriptions are costly and time-consuming. Volunteer-created video descriptions could be a promising alternative, however, they can vary in quality and can be intimidating for novice describers. We developed a Human-in-the-Loop Machine Learning (HILML) approach to video description by automating video text generation and scene segmentation and allowing humans to edit the output. The HILML approach facilitates human-machine collaboration to produce high quality video descriptions while keeping a low barrier to entry for volunteer describers. Our HILML system was signifcantly faster and easier to use for frst-time video describers compared to a human-only control condition with no machine learning assistance. The quality of the video descriptions and understanding of the topic created by the HILML system compared to the human-only condition were rated as being signifcantly higher by blind and visually impaired users.