Deep video code for efficient face video retrieval

作者：

Highlights：

• Propose a deep video code (DVC) framework to represent video face as binary codes.

• Propose two video modeling schemes to effectively aggregate information from video frames.

• A novel bounded triplet loss is elaborately designed for discriminative hash learning.

• Demonstrate superior performance of DVC for both video to video and image to video retrieval tasks on three challenging datasets.

摘要

•Propose a deep video code (DVC) framework to represent video face as binary codes.•Propose two video modeling schemes to effectively aggregate information from video frames.•A novel bounded triplet loss is elaborately designed for discriminative hash learning.•Demonstrate superior performance of DVC for both video to video and image to video retrieval tasks on three challenging datasets.

论文关键词：Face video retrieval,Temporal feature pooling,Bounded triplet loss,Deep video code,Hash learning

论文评审过程：Received 5 November 2019, Revised 3 November 2020, Accepted 8 November 2020, Available online 12 November 2020, Version of Record 19 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107754