Interp-SUM: Unsupervised Video Summarization with Piecewise Linear Interpolation
| Autor: | Myung-Duk Hong, Ui-Nyoung Yoon, Geun-Sik Jo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
reinforcement learning
Exploit Computer science Video Recording TP1-1185 02 engineering and technology unsupervised learning Biochemistry Article Analytical Chemistry video summarization Image Interpretation Computer-Assisted 0202 electrical engineering electronic engineering information engineering Humans Reinforcement learning Electrical and Electronic Engineering Instrumentation business.industry Chemical technology Frame (networking) piecewise linear interpolation 020206 networking & telecommunications Piecewise linear interpolation Pattern recognition Function (mathematics) Automatic summarization Atomic and Molecular Physics and Optics Unsupervised learning 020201 artificial intelligence & image processing Artificial intelligence business Algorithms Interpolation |
| Zdroj: | Sensors Volume 21 Issue 13 Sensors (Basel, Switzerland) Sensors, Vol 21, Iss 4562, p 4562 (2021) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s21134562 |
| Popis: | This paper addresses the problem of unsupervised video summarization. Video summarization helps people browse large-scale videos easily with a summary from the selected frames of the video. In this paper, we propose an unsupervised video summarization method with piecewise linear interpolation (Interp-SUM). Our method aims to improve summarization performance and generate a natural sequence of keyframes with predicting importance scores of each frame utilizing the interpolation method. To train the video summarization network, we exploit a reinforcement learning-based framework with an explicit reward function. We employ the objective function of the exploring under-appreciated reward method for training efficiently. In addition, we present a modified reconstruction loss to promote the representativeness of the summary. We evaluate the proposed method on two datasets, SumMe and TVSum. The experimental result showed that Interp-SUM generates the most natural sequence of summary frames than any other the state-of-the-art methods. In addition, Interp-SUM still showed comparable performance with the state-of-art research on unsupervised video summarization methods, which is shown and analyzed in the experiments of this paper. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |