# TAO-Amodal: A Benchmark for Tracking Any Object Amodally Source: [TAO-Amodal: A Benchmark for Tracking Any Object Amodally]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:32:50.348Z Authors: Cheng-Yen Hsieh, Kaihua Chen, Achal Dave, Tarasha Khurana, Deva Ramanan Published: 2023-12-19T18:58:40.000Z ## Abstract Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear understanding of heavily occluded objects is essential. However, modern detection and tracking algorithms often overlook this critical capability, perhaps due to the prevalence of \\textit{modal} annotations in most benchmarks. To address the scarcity of amodal benchmarks, we introduce TAO-Amodal, featuring 833 diverse categories in thousands of video sequences. Our dataset includes \\textit{amodal} and modal bounding boxes for visible and partially or fully occluded objects, including those that are partially out of the camera frame. We investigate the current lay of the land in both amodal tracking and detection by benchmarking state-of-the-art modal trackers and amodal segmentation methods. We find that existing methods, even when adapted for amodal tracking, struggle to detect and track objects under heavy occlusion. To mitigate this, we explore simple finetuning schemes that can increase the amodal tracking and detection metrics of occluded objects by 2.1\\% and 3.3\\%. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Amodal Bounding Box Detection on TAO-Amodal custom 100-clip 1.0](): Amodal Bounding Box Detection; TAO-Amodal custom 100-clip 1.0; AP@25: 41.7. ## Original sources and implementation [Original paper]() [PDF]()