Content selection criteria for news multi-video summarization based on human strategies

Barbieri, Tamires Tessarolli de Souza; Goularte, Rudinei

doi:10.1007/s00799-020-00281-9

Cited by 5 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This show can consider other summation models as depicted in the study [4], wherein approaches like Motion based way of thinking, Event based procedure, Color based point of view, Audio-visual based framework, Trajectory assessment, Gesture based, Clustering, shot confirmation approach and Mosaic based construction is portrayed. These designs can be applied for different video news format as displayed in the study [5], wherein human methods for unprecedented of video are portrayed. These methodologies consider partition data; and oblige it with PC vision to review best models for news design.…”

Section: Literature Review Deep Learning-based Video Summarizationmentioning

confidence: 99%

Gated Recurrent Units and Recurrent Neural Network Based Multimodal Approach for Automatic Video Summarization

Kaur¹,

Aljrees²,

Kumar³

et al. 2023

View full text Add to dashboard Cite

A typical video record aggregation system requires the concurrent performance of a large number of image processing tasks, including but not limited to image acquisition, pre-processing, segmentation, feature extraction, verification, and description. These tasks must be executed with utmost precision to ensure smooth system performance. Among these tasks, feature extraction and selection are the most critical. Feature extraction involves converting the large-scale image data into smaller mathematical vectors, and this process requires great skill. Various feature extraction models are available, including wavelet, cosine, Fourier, histogram-based, and edge-based models. The key objective of any feature extraction model is to represent the image data with minimal attributes and no loss of information. In this study, we propose a novel feature-variance model that detects differences in video features and generates feature-reduced video frames. These frames are then fed into a GRU-based RNN model, which classifies them as either keyframes or non-keyframes. Keyframes are then extracted to create a summarized video, while non-keyframes are reduced. Various key-frame extraction models are also discussed in this section, followed by a detailed analysis of the proposed summarization model and its results. Finally, we present some interesting observations about the proposed model and suggest ways to improve it.

show abstract

Section: Literature Review Deep Learning-based Video Summarizationmentioning

confidence: 99%

Gated Recurrent Units and Recurrent Neural Network Based Multimodal Approach for Automatic Video Summarization

Kaur¹,

Aljrees²,

Kumar³

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In order to save reading time and maintain key information, abstractive summarizers are crucial [ 16 ]. The abstractive method of video summarizing picks out the most important frames from the video and uses pre-trained network architectures to analyze the contents of it [ 17 ]. But processing of such data with high dimensional features are challenging.…”

Section: Introductionmentioning

confidence: 99%