Video summarization using deep learning techniques: a detailed analysis and investigation

Saini, Parul; Kumar, Krishan; Kashid, Shamal; Saini, Ashray; Negi, Atul

doi:10.1007/s10462-023-10444-0

Cited by 21 publications

(9 citation statements)

References 140 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods leverage deep learning (DL) algorithms and learn from a vast amount of video data to achieve pixel-level, frame-level, or video-level discrimination of abnormal behaviors. Saini et al [23] proposed that existing DL-based video summarization algorithms can be broadly categorized into three groups: unsupervised, weakly supervised, and supervised. Abnormal behavior detection techniques are widely employed within each of these three categories.…”

Section: Abnormal Behavior Detectionmentioning

confidence: 99%

“…These methods require only a limited amount of labeled data during training, reducing the need for manual intervention. This approach is particularly useful when models rely on expensive annotated data or have time constraints for manual annotation [23]. In paper [28], it shows that currently in the weakly supervised direction, the AUC of the UCF-Crime dataset using MGFN and I3D-RGB methods is the best, which reaches 86.98%.…”

Section: Weakly Supervisedmentioning

confidence: 99%

See 1 more Smart Citation

Advances in abnormal human activity detection based on video surveillance

wang,

Leung,

Khor

et al. 2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

Section: Abnormal Behavior Detectionmentioning

confidence: 99%

Section: Weakly Supervisedmentioning

confidence: 99%

Advances in abnormal human activity detection based on video surveillance

wang,

Leung,

Khor

et al. 2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

“…As an important research direction in this field, video summarization has been widely applied in various application scenarios including news, documentaries, surveillance, education, medicine and more. Its main goal is to extract representative frames or shots by analyzing and processing videos and form a short and compact summary video, retaining the key information of the original video as much as possible, so that users can quickly browse and obtain the core information of the video [1][2][3]. According to the type of the generated summaries, video summarization can be generally divided into two types: static video summarization and dynamic video summarization [4].…”

Section: Introductionmentioning

confidence: 99%

Video Summarization Generation Network Based on Dynamic Graph Contrastive Learning and Feature Fusion

Zhang,

Wu,

et al. 2024

Electronics

View full text Add to dashboard Cite

Video summarization aims to analyze the structure and content of videos and extract key segments to construct summarization that can accurately summarize the main content, allowing users to quickly access the core information without browsing the full video. However, existing methods have difficulties in capturing long-term dependencies when dealing with long videos. On the other hand, there is a large amount of noise in graph structures, which may lead to the influence of redundant information and is not conducive to the effective learning of video features. To solve the above problems, we propose a video summarization generation network based on dynamic graph contrastive learning and feature fusion, which mainly consists of three modules: feature extraction, video encoder, and feature fusion. Firstly, we compute the shot features and construct a dynamic graph by using the shot features as nodes of the graph and the similarity between the shot features as the weights of the edges. In the video encoder, we extract the temporal and structural features in the video using stacked L-G Blocks, where the L-G Block consists of a bidirectional long short-term memory network and a graph convolutional network. Then, the shallow-level features are obtained after processing by L-G Blocks. In order to remove the redundant information in the graph, graph contrastive learning is used to obtain the optimized deep-level features. Finally, to fully exploit the feature information of the video, a feature fusion gate using the gating mechanism is designed to fully fuse the shallow-level features with the deep-level features. Extensive experiments are conducted on two benchmark datasets, TVSum and SumMe, and the experimental results show that our proposed method outperforms most of the current state-of-the-art video summarization methods.

show abstract

“…Video summarization is broadly divided into static and dynamic summary (Saini et al, 2023). Dynamic summaries also referred to as video skim, are produced by video segments that analyse the audio and visual content of the video.…”

Section: Introductionmentioning

confidence: 99%

Auto encoder with mode‐based learning for keyframe extraction in video summarization

Shambharkar,

Goel

2023

Expert Systems

View full text Add to dashboard Cite

The exponential increase in video consumption has created new difficulties for browsing and navigating through video more effectively and efficiently. Researchers are interested in video summarization because it offers a brief but instructive video version that helps users and systems save time and effort when looking for and comprehending relevant content. Key frame extraction is a method of video summarization that only chooses the most important frames from a given video. In this article, a novel supervised learning method ‘TC‐CLSTM Auto Encoder with Mode‐based Learning’ using temporal and spatial features is proposed for automatically choosing keyframes or important sub‐shots from videos. The method was able to achieve an average F‐score of 84.35 on TVSum dataset. Extensive tests on benchmark data sets show that the suggested methodology outperforms state‐of‐the‐art methods.

show abstract

Video summarization using deep learning techniques: a detailed analysis and investigation

Cited by 21 publications

References 140 publications

Advances in abnormal human activity detection based on video surveillance

Advances in abnormal human activity detection based on video surveillance

Video Summarization Generation Network Based on Dynamic Graph Contrastive Learning and Feature Fusion

Auto encoder with mode‐based learning for keyframe extraction in video summarization

Contact Info

Product

Resources

About