Journal
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Volume -, Issue -, Pages 879-883Publisher
IEEE
DOI: 10.1109/icip.2019.8802944
Keywords
Video Search; Multi-label; Deep Metric Learning; Feature Composition
Categories
Funding
- Agency for Science, Technology and Research (A*STAR) under its Hardware-Software Co-optimisation for Deep Learning [A1892b0026]
- Singapore Ministry of Education Tier-2 Fund [MOE2016-T2-2-057(S)]
Ask authors/readers for more resources
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 approaches driven by ranking losses. The holographic composition layer is parameter-free and enables less memory footprint compared with state-of-the-art. Towards multi-label video search at large scale, we present a new video benchmark built upon the YouTube-8M dataset. Extensive evaluations on this dataset demonstrate that DHN performs better than traditional deep metric learning approaches as well as other compositional networks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available