Video Summarization with LSTM and Deep Attention Models
| Autor: | Eugenia Koblents, Luis Lebron Casas |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Similarity (geometry)
Computational complexity theory business.industry Computer science Deep learning Digital forensics Frame (networking) 020207 software engineering 02 engineering and technology Attention model Machine learning computer.software_genre Automatic summarization 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Relevance (information retrieval) Artificial intelligence business computer |
| Zdroj: | MultiMedia Modeling-25th International Conference, MMM 2019, Thessaloniki, Greece, January 8–11, 2019, Proceedings, Part II MultiMedia Modeling ISBN: 9783030057152 MMM (2) Lecture Notes in Computer Science Lecture Notes in Computer Science-MultiMedia Modeling |
| ISSN: | 0302-9743 1611-3349 |
| DOI: | 10.1007/978-3-030-05716-9_6 |
| Popis: | In this paper we propose two video summarization models based on the recently proposed vsLSTM and dppLSTM deep networks, which allow to model frame relevance and similarity. The proposed deep learning architectures additionally incorporate an attention mechanism to model user interest. In this paper the proposed models are compared to the original ones in terms of prediction accuracy and computational complexity. The proposed vsLSTM+Att method with an attention model outperforms the original methods when evaluated on common public datasets. Additionally, results obtained on a real video dataset containing terrorist-related content are provided to highlight the challenges faced in real-life applications. The proposed method yields outstanding results in this complex scenario, when compared to the original methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|