Lecture Vdeo Indexing Using Boosted Margin Maximizing Neural Networks

Ma, Di; Zhang, Xi; Ouyang, Xu; Agam, Gady

doi:10.1109/icmla.2017.0-155

Cited by 7 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several works have been proposed in previous years dealing with lecture video related issues, such as lecture video indexing, retrieval, recommendation and segmentation. In [11] an automated lecture video indexing system is proposed. Boosted deep convolution neural networks are used to correlate lecture slide images with candidate video frames.…”

Section: Related Workmentioning

confidence: 99%

Temporal Lecture Video Fragmentation Using Word Embeddings

Galanopoulos

Mezaris

2018

MultiMedia Modeling

View full text Add to dashboard Cite

In this work the problem of temporal video lecture fragmentation in meaningful parts is addressed. The visual content of lecture video can not be effectively used for this task due to its extremely homogeneous content. A new method for lecture video fragmentation in which only automatically generated speech transcripts of a video are exploited, is proposed. Contrary to previously proposed works that employ visual, audio and textual features and use time-consuming supervised methods which require annotated training data, we present a method that analyses the transcripts' text with the help of word embeddings that are generated from pre-trained state-of-the-art neural networks. Furthermore, we address a major problem of video lecture fragmentation research, which is the lack of large-scale datasets for evaluation, by presenting a new artificially-generated dataset of synthetic video lecture transcripts that we make publicly available. Experimental comparisons document the merit of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporal Lecture Video Fragmentation Using Word Embeddings

Galanopoulos

Mezaris

2018

MultiMedia Modeling

View full text Add to dashboard Cite

show abstract

“…This approach involves training a Support Vector Machine (SVM) on lecture videos to detect changes in events, such as "speaker writing on the blackboard" or "slide presentation," from which fragment boundaries are extracted. In another work by [21], an innovative solution is introduced that employs boosted margin maximizing neural networks to efficiently index educational videos. Through the utilization of neural networks and boosted margin maximization, this method exhibits promise in accurately identifying and organizing crucial segments within lecture videos, thereby enhancing content retrieval and accessibility.…”

Section: Video Segmentation Based On Audio/image/text Algorithmsmentioning

confidence: 99%

Semantic Segmentation of Educational Videos for Micro Learning Objects in Adaptive E-Learning

Halawa,

Gamalel-Din,

Nasr

2023

Journal of Al-Azhar University Engineering Sector

View full text Add to dashboard Cite

E-Learning is gaining prominence, especially in lifelong learning, primarily through lecture videos. However, these videos often encompass multiple topics or serve various instructional roles within a single subject. In adaptive e-Learning, the smaller and granular the units, the more versatile presentations and personalized lectures are composed. Such units are known as Micro Learning Objects (MLOs). Consequently, the necessity emerges to segment these lecture videos into multiple MLOs, each fulfilling a distinct instructional role in a lecture. This article presents an automatic model leveraging advanced language models to segment lecture videos semantically into Micro Learning Objects (MLOs). Additionally, a new wellsegmented dataset of educational videos (YT-EV) was introduced, in which the video is segmented according to a pre-defined timestamped agenda. The model is trained on general text datasets to understand LO segments and subsequently fine-tuned using transfer learning on video datasets to achieve better segmentation results. The experimental results showed an F1-score of value 0.657, which is considered promising and emphasizes the significance of text transcript-based video segmentation for enhancing adaptive e-Learning.

show abstract

“…For instance, in [9], Ma and Agam proposed an approach to segment video into various scenes by identifying the transition of frames by the analysis of color histogram of lecture video's frames. In [10], Ma et al, proposed an automatic lecture video indexing framework that compares lecture slide images with candidate video frames using Boosted deep neural networks. In [11], a supervised technique is proposed that uses visual features and transcripts to detect changes in occurrences, such as "speaker writing on the blackboard" or "slide presentation."…”

Section: Related Workmentioning

confidence: 99%