Feature flow: In-network feature flow estimation for video object detection

作者：

Highlights：

• A type of shallow modules are proposed to directly predict the feature flow for feature alignment in a single network.

• Self-supervision learning is introduced to further improve the quality of the predicted feature flow.

• A new state-of-the-art performance is shown by comparing with other methods, while a fast inference speed is maintained.

摘要

•A type of shallow modules are proposed to directly predict the feature flow for feature alignment in a single network.•Self-supervision learning is introduced to further improve the quality of the predicted feature flow.•A new state-of-the-art performance is shown by comparing with other methods, while a fast inference speed is maintained.

论文关键词：Video object detection,Feature flow,Object detection,Video analysis,Deep convolutional neural network (DCNN)

论文评审过程：Received 28 January 2021, Revised 10 September 2021, Accepted 11 September 2021, Available online 20 September 2021, Version of Record 23 September 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108323