A Formal Study of Shot Boundary Detection Approaches—Comparative Analysis

Nankani, Hanisha; Mahrishi, Mehul; Morwal, Sudha; Hiran, Kamal Kant

doi:10.1007/978-981-16-1740-9_26

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 The public structure of a convolutional neural network with an example of inserting images containing an object (bird) and how the type of object in the object is determined. A convolutional neural network has two main parts: the first is a convolution/pooling mechanism that divides the image into features and analyses them, and the second is a fully connected layer that takes the convolution/pooling output and guesses the best tag to describe the image [60][61][62][63][64][65][66][67]. Figure 2 illustrates how deep learning is utilised to classify images of COVID-19 patients [68].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

The Distinction between R-CNN and Fast R-CNN in Image Analysis: A Performance Comparison

Mijwil

Aggarwal

Doshi

et al. 2022

AJAS

View full text Add to dashboard Cite

Deep learning techniques have become vital in many fields in the modern era because they are excellent at analysing and predicting real big data to act in different situations. Although it is marvellous in many aspects, it is prone to misinterpretation of data, so teams of experienced specialists cannot be dispensed with in following up on the execution stages of data analysis. Convolutional Neural Network is one of the most significant deep learning techniques. It is widely employed in visual image analysis. In this article, R-CNN and Fast R-CNN are summarised and compared and are the best in image analysis. This article concluded that the most suitable performance is for Fast R-CNN in testing and training.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

The Distinction between R-CNN and Fast R-CNN in Image Analysis: A Performance Comparison

Mijwil

Aggarwal

Doshi

et al. 2022

AJAS

View full text Add to dashboard Cite

show abstract

“…For example, if a student is at risk, a teacher may intervene or provide feedback and instructional content to help them improve. Machine learning, data visualisation, learning sciences, and semantics all play a role in its development (M. Dadhich et al, 2022;Nankani et al, 2022). Competency learning powered by AI can, for example, help institutions anticipate the skills their students will need in the future.…”

Section: Learning Analyticsmentioning

confidence: 99%

The Impact of AI on Teaching and Learning in Higher Education Technology

2022

JHETP

View full text Add to dashboard Cite

Thanks to AI, students may now study whenever and wherever they like. Personalized feedback on assignments, quizzes, and other assessments can be generated using AI algorithms and utilised as a teaching tool to help students succeed. This study examined the impact of artificial intelligence in higher education teaching and learning. This study focuses on the impact of new technologies on student learning and educational institutions. With the rapid adoption of new technologies in higher education, as well as recent technological advancements, it is possible to forecast the future of higher education in a world where artificial intelligence is ubiquitous. Administration, student support, teaching, and learning can all benefit from the use of these technologies; we identify some challenges that higher education institutions and students may face, and we consider potential research directions.

show abstract