Self-Supervised Learning to Detect Key Frames in Videos

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 23; p. 6941
• Main Authors: Yan, Xiang, Gilani, Syed Zulqarnain, Feng, Mingtao, Zhang, Liang, Qin, Hanlin, Mian, Ajmal
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 04.12.2020; MDPI
• Subjects: Annotations; convolutional networks; Datasets; Discriminant analysis; Human subjects; key frames; Labeling; Machine learning; Methods; Neural networks; self-supervised learning; two-stream ConvNets; self-supervised learning; two-stream ConvNets; key frames; convolutional networks

Detecting key frames in videos is a common problem in many applications such as video classification, action recognition and video summarization. These tasks can be performed more efficiently using only a handful of key frames rather than the full video. Existing key frame detection approaches are m...