Adaptive feature fusion for visual object tracking

作者：

Highlights：

• We propose an adaptive feature fusion mechanism to provide both semantic and discriminative feature representations by automatically fusing multi-level convolutional layers.

• We reformulate the update strategy. Through joint training the projection matrix layer and correlation layer, a more convincing target localization formulation can be achieved.

• We validate our method on several benchmarking datasets with state-of-the-art methods. The experimental results and corresponding analysis demonstrate the merit of the proposed tracker.

摘要

•We propose an adaptive feature fusion mechanism to provide both semantic and discriminative feature representations by automatically fusing multi-level convolutional layers.•We reformulate the update strategy. Through joint training the projection matrix layer and correlation layer, a more convincing target localization formulation can be achieved.•We validate our method on several benchmarking datasets with state-of-the-art methods. The experimental results and corresponding analysis demonstrate the merit of the proposed tracker.

论文关键词：Visual tracking,Deep neural network,Feature fusion,Online adaptation

论文评审过程：Received 30 December 2019, Revised 24 August 2020, Accepted 23 September 2020, Available online 21 October 2020, Version of Record 2 November 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107679