Video Hunter at VBS 2017

详细信息    查看全文

• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10133
• 期：1
• 页码：493-498
• 丛书名：MultiMedia Modeling
• ISBN：978-3-319-51814-5
• 卷排序：10133

文摘

After almost three years of development, the Video Hunter tool (formerly the Signature-Based Video Browser) has become a complex tool combining different query modalities, multi-sketches, visualizations and browsing techniques. In this paper, we present additional improvements of the tool focusing on keyword search. More specifically, we present a method relying on an external image search engine and a method relying on ImageNet labels. We also present a keyframe caching method employed by our tool.