Saliency-Associated Object Tracking

TL;DR

This paper introduces a saliency-based object tracking method that focuses on discriminative local parts of the target, improving robustness against appearance variations by modeling saliency associations.

Contribution

It proposes a novel saliency mining and association framework for tracking discriminative local parts, enhancing tracking accuracy over holistic and uniform patch-based methods.

Findings

Outperforms state-of-the-art trackers on five diverse datasets.

Effective in handling targets with appearance variations.

Improves tracking robustness by focusing on salient local parts.

Abstract

Most existing trackers based on deep learning perform tracking in a holistic strategy, which aims to learn deep representations of the whole target for localizing the target. It is arduous for such methods to track targets with various appearance variations. To address this limitation, another type of methods adopts a part-based tracking strategy which divides the target into equal patches and tracks all these patches in parallel. The target state is inferred by summarizing the tracking results of these patches. A potential limitation of such trackers is that not all patches are equally informative for tracking. Some patches that are not discriminative may have adverse effects. In this paper, we propose to track the salient local parts of the target that are discriminative for tracking. In particular, we propose a fine-grained saliency mining module to capture the local saliencies. Further, we design a saliency-association modeling module to associate the captured saliencies together to learn effective correlation representations between the exemplar and the search image for state estimation. Extensive experiments on five diverse datasets demonstrate that the proposed method performs favorably against state-of-the-art trackers.