From local to global key-frame extraction based on important scenes using SVD of centrist features

Bendraou, Youssef; Essannouni, Fedwa; Mashaly, Ahmed S.

doi:10.1007/s11042-018-6274-0

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In KEGC (Keyframe Extraction via Graph Clustering) [62] was introduced a VS approach using graph clustering after local features were extracted from video frames using the LBP descriptor and points of interest using the SIFT algorithm. In CENTRIST VS [63] a VS method was proposed via singular value decomposition (SVD) of centrist features (census transform histogram), which is a visual descriptor for recognizing places or scene understanding. Final keyframes were selected by a k-means clustering on the extracted features.…”

Section: Video Summarization Methods Using the Ov Datasetmentioning

confidence: 99%

“…Every video is watched and evaluated by 5 humans who selected ground truth (GT) frames according to their subjective opinions. Since this dataset is publicly available and is consisted of videos along with their respective summarization GT, its popularity is quite large and thus, several VS methods select it to perform their experiments [58], [12], [42]- [63].…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

SalSum: Saliency-based Video Summarization using Generative Adversarial Networks

Pantazis,

Dimas,

Iakovidis

2020

Preprint

View full text Add to dashboard Cite

The huge amount of video data produced daily by camera-based systems, such as surveilance, medical and telecommunication systems, emerges the need for effective video summarization (VS) methods. These methods should be capable of creating an overview of the video content. In this paper, we propose a novel VS method based on a Generative Adversarial Network (GAN) model pre-trained with human eye fixations. The main contribution of the proposed method is that it can provide perceptually compatible video summaries by combining both perceived color and spatiotemporal visual attention cues in a unsupervised scheme. Several fusion approaches are considered for robustness under uncertainty, and personalization. The proposed method is evaluated in comparison to state-of-the-art VS approaches on the benchmark dataset VSUMM. The experimental results conclude that SalSum outperforms the state-of-the-art approaches by providing the highest f-measure score on the VSUMM benchmark.

show abstract

Section: Video Summarization Methods Using the Ov Datasetmentioning

confidence: 99%