Spatio-Temporal Matching for Siamese Visual Tracking

TL;DR

This paper introduces a novel spatio-temporal matching approach for Siamese visual tracking that leverages 4-D information, including space and time, to improve robustness and accuracy over traditional methods.

Contribution

It proposes a space-variant channel-guided correlation and an aberrance repressed module to enhance 4-D matching in object tracking, along with a new anchor-free framework.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively suppresses aberrances in interframe responses.

Enhances robustness and accuracy in challenging scenarios.

Abstract

Similarity matching is a core operation in Siamese trackers. Most Siamese trackers carry out similarity learning via cross correlation that originates from the image matching field. However, unlike 2-D image matching, the matching network in object tracking requires 4-D information (height, width, channel and time). Cross correlation neglects the information from channel and time dimensions, and thus produces ambiguous matching. This paper proposes a spatio-temporal matching process to thoroughly explore the capability of 4-D matching in space (height, width and channel) and time. In spatial matching, we introduce a space-variant channel-guided correlation (SVC-Corr) to recalibrate channel-wise feature responses for each spatial location, which can guide the generation of the target-aware matching features. In temporal matching, we investigate the time-domain context relations of the target and the background and develop an aberrance repressed module (ARM). By restricting the abrupt alteration in the interframe response maps, our ARM can clearly suppress aberrances and thus enables more robust and accurate object tracking. Furthermore, a novel anchor-free tracking framework is presented to accommodate these innovations. Experiments on challenging benchmarks including OTB100, VOT2018, VOT2020, GOT-10k, and LaSOT demonstrate the state-of-the-art performance of the proposed method.