GMOT-40: A Benchmark for Generic Multiple Object Tracking

TL;DR

This paper introduces GMOT-40, the first public benchmark dataset for Generic Multiple Object Tracking, along with baseline algorithms and evaluation protocols to advance research in tracking unseen categories.

Contribution

The paper presents GMOT-40, a new dataset, evaluation protocols, and baseline algorithms for the under-explored task of generic multiple object tracking.

Findings

GMOT-40 contains 40 annotated sequences across 10 categories.

Baseline algorithms provide a starting point for GMOT research.

Evaluation results highlight challenges and future directions in GMOT.

Abstract

Multiple Object Tracking (MOT) has witnessed remarkable advances in recent years. However, existing studies dominantly request prior knowledge of the tracking target, and hence may not generalize well to unseen categories. In contrast, Generic Multiple Object Tracking (GMOT), which requires little prior information about the target, is largely under-explored. In this paper, we make contributions to boost the study of GMOT in three aspects. First, we construct the first public GMOT dataset, dubbed GMOT-40, which contains 40 carefully annotated sequences evenly distributed among 10 object categories. In addition, two tracking protocols are adopted to evaluate different characteristics of tracking algorithms. Second, by noting the lack of devoted tracking algorithms, we have designed a series of baseline GMOT algorithms. Third, we perform a thorough evaluation on GMOT-40, involving popular MOT algorithms (with necessary modifications) and the proposed baselines. We will release the GMOT-40 benchmark, the evaluation results, as well as the baseline algorithm to the public upon the publication of the paper.