Beyond ranking loss : deep holographic networks for multi-label video search

• Main Authors: Chen, Zhuo, Lin, Jie, Wang, Zhe, Chandrasekhar, Vijay, Lin, Weisi
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Video Retrieval; Correlation
• Online Access: https://hdl.handle.net/10356/144186
• Institution: Nanyang Technological University

In this paper, we propose Deep Holographic Networks (DHN) to learn similarity metrics of videos for multi-label video search. DHN introduces a holographic composition layer to explicitly encode similarity metrics at intermediate layer of the network, instead of conventional deep metric learning appr...