Score: 0

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

Published: December 10, 2025 | arXiv ID: 2512.10102v1

By: Neelima Prasad , Jarek Reynolds , Neel Karsanbhai and more

Potential Business Impact:

Tracks all parts of objects and their links.

Business Areas:
Image Recognition Data and Analytics, Software

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

Page Count
16 pages

Category
Computer Science:
CV and Pattern Recognition