Tracking through Containers and Occluders in the Wild

TL;DR

This paper introduces TCOW, a benchmark and model for tracking objects through heavy occlusion and containment in cluttered environments, highlighting current model limitations in understanding object permanence.

Contribution

The paper presents a new benchmark and dataset for tracking through occlusion and containment, along with an evaluation of transformer-based models on this challenging task.

Findings

Transformer models perform variably under occlusion conditions.

Significant performance gap remains in understanding object permanence.

The dataset supports both supervised learning and structured evaluation.

Abstract

Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce $\textbf{TCOW}$, a new benchmark and model for visual tracking through heavy occlusion and containment. We set up a task where the goal is to, given a video sequence, segment both the projected extent of the target object, as well as the surrounding container or occluder whenever one exists. To study this task, we create a mixture of synthetic and annotated real datasets to support both supervised learning and structured evaluation of model performance under various forms of task variation, such as moving or nested containment. We evaluate two recent transformer-based video models and find that while they can be surprisingly capable of tracking targets under certain settings of task variation, there remains a considerable performance gap before we can claim a tracking model to have acquired a true notion of object permanence.