Large-Scale Content-Only Video Recommendation
Authors:
- Joonseok LeeJLJoonseok Lee
- Sami Abu-El-HaijaSASami Abu-El-Haija
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 987-995
Abstract
Traditional recommendation systems using collaborative filtering (CF) approaches work relatively well when the candidate videos are sufficiently popular With the increase of user-created videos, however, recommending fresh videos gets more and more important, but pure CF-based systems may not perform well in such cold-start situation. In this paper, we model recommendation as a video content-based similarity learning problem, and learn deep video embeddings trained to predict video relationships identified by a co-watch-based system but using only visual and audial content. The system does not depend on availability on video meta-data, and can generalize to both popular and tail content, including new video uploads. We demonstrate performance of the proposed method in large-scale datasets, both quantitatively and qualitatively.Keywords
This publication has 19 references indexed in Scilit:
- Delving Deep into Personal Photo and Video Search2017
- Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification2016
- Some Like It Hot — Visual Guidance for Preference Prediction2016
- An efficient and sparse approach for large scale human action recognition in videosMachine Vision and Applications, 2016
- Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Local collaborative ranking2014
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification2010
- Taxonomy-driven computation of product recommendations2004