A multi-embedding neural model for incident video retrieval

作者：

Highlights：

• A state-of-the-art approach for video retrieval on several datasets.

• An encoder-decoder for learning the spatial and temporal characteristics of videos.

• Multi-resolution embedding of incident videos for similarity comparison.

摘要

•A state-of-the-art approach for video retrieval on several datasets.•An encoder-decoder for learning the spatial and temporal characteristics of videos.•Multi-resolution embedding of incident videos for similarity comparison.

论文关键词：Artificial intelligence,Computer vision,Deep metric learning,Incident video retrieval

论文评审过程：Received 25 September 2021, Revised 9 May 2022, Accepted 20 May 2022, Available online 24 May 2022, Version of Record 26 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108807