Robust handwriting extraction and lecture video summarization

Lee, Greg C.; Yeh, Fu-Hao; Chen, Ying‐Ju; Chang, Tao-Ku

doi:10.1007/s11042-016-3353-y

Cited by 19 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

“…Regarding tasks and technologies, we identified some low-level tasks performed as basic steps, of which, many rely on deep learning approaches. For example, for textual video elements, several studies employed optical character recognition [14,21,29,32,49,50,54,64,67,102,109,114,123,138,152,160,161,179,195,255,261,262,265,273,276], keyword extraction [14,40,43,61,92,105,106,109,112,121,128,131,161,206,255,264,271], generic natural language processing methods (e.g., [29,127,128,194,243]), or utilized word embeddings (e.g., [54,…”

Section: Audio Featuresmentioning

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%

“…The handwriting was then extracted by enclosing it in bounding boxes and binarizing it. Lee et al [138] detected changes in the the handwriting pixels and extracted them using an adaptive threshold and time-series denoising techniques. Davila and Zanibbi [50] extracted handwritten formulas using a random forest classifier trained on handwritten symbols.…”

Section: Information Extraction Toolsmentioning

confidence: 99%

See 3 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

Section: Discussionmentioning

confidence: 99%

Section: Audio Featuresmentioning

confidence: 99%

Section: Information Extraction Toolsmentioning

confidence: 99%

Section: Information Extraction Toolsmentioning

confidence: 99%

See 2 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

show abstract

“…Já [Yousaf et al 2015] identifica atividades do instrutor usando recursos de reconhecimento de face e estimativa de pose do professor. Enquanto que outros artigos focam na extrac ¸ão do conteúdo escrito na lousa, [Lee et al 2017] identifica e melhora a qualidade do frame que melhor representa o conteúdo, [Davila and Zanibbi 2018] reconhece fórmulas matemáticas presentes na lousa, [Kota et al 2021, Urala Kota et al 2018 e [Davila et al 2021] buscaram resumir o conteúdo escrito na lousa por meio da identificac ¸ão de conteúdos e frames chaves. Já [Ciurez et al 2019] apresentou um método para classificar os vídeos em diferentes estilos de aprendizagem, com técnicas para calcular a quantidade de texto e imagem de diferentes frames do vídeo.…”

Section: Trabalhos Relacionadosunclassified

Classificação Automática de Estilos de Videoaulas

Aquino

Barrére²,

Souza³

2022

Anais Do XXXIII Simpósio Brasileiro De Informática Na Educação (SBIE 2022)

View full text Add to dashboard Cite

Muito tem sido feito para investigar os efeitos dos estilos das videoaulas no envolvimento do aluno e no resultado de aprendizagem. Porém, poucos estudos buscaram classificar automaticamente esses estilos. Assim, o estudo atual utilizou características visuais dos estilos das videoaulas (presença de pessoas e textos) e diferentes classificadores para a avaliação do método de classificação proposto. Essa classificação automática poderá ser utilizada por sistemas de recomendação para sugestão de estilos mais aderentes a preferências dos alunos e ao resultado de aprendizagem pretendido. Os experimentos realizados mostraram que o método de classificação utilizado é adequado ao problema, atingindo valores de até 92% de acurácia.

show abstract

Multimodal Corpus Analysis of Autoblog 2020: Lecture Videos in Machine Learning

Hernandez

Yang

2021

Speech and Computer

View full text Add to dashboard Cite

Robust handwriting extraction and lecture video summarization

Cited by 19 publications

References 17 publications

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

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

Classificação Automática de Estilos de Videoaulas

Multimodal Corpus Analysis of Autoblog 2020: Lecture Videos in Machine Learning

Contact Info

Product

Resources

About