AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee

TL;DR

This paper introduces AAA, an adaptive online tracker aggregation method with a theoretical guarantee that it performs comparably to the best individual tracker, achieving state-of-the-art results across diverse datasets.

Contribution

It proposes a novel adaptive aggregation approach for online trackers with proven performance guarantees, addressing variability in target appearance.

Findings

Achieves state-of-the-art tracking performance on benchmark datasets.

Provides theoretical guarantees of performance relative to the best tracker.

Effectively handles large variations in target appearance.

Abstract

For visual object tracking, it is difficult to realize an almighty online tracker due to the huge variations of target appearance depending on an image sequence. This paper proposes an online tracking method that adaptively aggregates arbitrary multiple online trackers. The performance of the proposed method is theoretically guaranteed to be comparable to that of the best tracker for any image sequence, although the best expert is unknown during tracking. The experimental study on the large variations of benchmark datasets and aggregated trackers demonstrates that the proposed method can achieve state-of-the-art performance. The code is available at https://github.com/songheony/AAA-journal.