Visual content summarisation for instructional videos using AdaBoost and SIFT

khattabi, Zaynab El; Tabii, Youness; Benkaddour, Abdelhamid

doi:10.1504/ijkesdp.2019.10025587

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tools, tasks and technologies: The main tools, pipelines, frameworks, and methods that have been proposed for supporting VBL were related to information extraction, integration of interactive features, recommendation systems, classification and prediction, video navigation, and summarization (see Section 5.1 Figure 5). Information extraction focused mainly on retrieving text [49,49,50,72,72,115,115,115,123,123,124,138,138,262,262,276,276], metadata [61,64,77,109,111,176], and key information from videos such as key video segments and key topics [32,76,128,148,152,195]. Some approaches used deep learning for information extraction [32,49,115,148], but also other (shallow) machine learning methods based on hand-crafted features were still present [32,152,195].…”

Section: Discussionmentioning

confidence: 99%

“…Information extraction focused mainly on retrieving text [49,49,50,72,72,115,115,115,123,123,124,138,138,262,262,276,276], metadata [61,64,77,109,111,176], and key information from videos such as key video segments and key topics [32,76,128,148,152,195]. Some approaches used deep learning for information extraction [32,49,115,148], but also other (shallow) machine learning methods based on hand-crafted features were still present [32,152,195]. Knowledge bases [77,109,176] and natural language [61,64,111] processing methods were also utilized.…”

Section: Discussionmentioning

confidence: 99%

“…Extraction of text: We found seven proposals that extracted handwritten text [49,72,123,124,138,262] and two papers on extracting machine-printed text (e.g., from slide-based videos) [115,276]. Davila et al [49] retrieved handwriting using a convolutional neural network (CNN).…”

Section: Information Extraction Toolsmentioning

confidence: 99%

“…Davila et al [49] retrieved handwriting using a convolutional neural network (CNN). Kota et al [115] used multiscale histogram of gradients for feature representation and deep neural networks to extract handwriting. In another article, Kota et al [123] detected bounding boxes with handwriting and used clustering algorithms to group them, which could identify also content that was occluded by the instructor when she was standing in front of the whiteboard.…”

Section: Information Extraction Toolsmentioning

confidence: 99%

“…Zhong and Ma [276] extracted machine printed text using the maximally stable extremal regions method to detect candidate regions and clustering techniques were used to ensemble lines of text. Finally, Khattabi et al [115] detected parts of the video that contained text using an AdaBoost meta-classifier.…”

Section: Information Extraction Toolsmentioning

confidence: 99%

See 4 more Smart Citations

A Closer Look into Recent Video-based Learning Research: A Comprehensive Review of Video Characteristics, Tools, Technologies, and Learning Effectiveness

Navarrete¹,

Nehring²,

Schanze³

et al. 2023

Preprint

View full text Add to dashboard Cite

People increasingly use videos on the Web as a source for learning, be it for daily tasks or in formal as well as informal educational settings. To support this way of learning, researchers and developers are continuously developing tools, proposing guidelines, analyzing data, and conducting experiments. However, it is still not clear what characteristics a video should have to be an effective learning medium. In this paper, we present a comprehensive review of 257 articles on video-based learning from computer science databases for the period from 2016 to 2021 using the PRISMA guidelines. One of the aims of the review is to identify the video characteristics that have been explored by previous work. Based on our analysis, we suggest a taxonomy which organizes the video characteristics and contextual aspects into eight categories: (1) audio features, (2) visual features, (3) textual features, (4) instructor behavior, (5) learners' activities, (6) interactive features (quizzes, etc.), (7) production style, and (8) instructional design. Also, we identify four representative research directions: (1) proposals of tools to support video-based learning, (2) studies with controlled experiments, (3) data analysis studies, and (4) proposals of design guidelines for learning videos. We find that the most explored characteristics are textual features followed by visual features, learner's activities, and interactive features. Text of transcripts, video frames, and images (figures and illustrations) are most frequently used by tools that support learning through videos. The learner's activity is heavily explored through log files in data analysis studies, and interactive features have been frequently scrutinized in controlled experiments. We complement our review by contrasting research findings that investigate the impact of video characteristics on the learning effectiveness, report on tasks and technologies used to develop tools that support learning, and summarize trends in the development of design guidelines to produce learning videos.

show abstract