Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026 Open access

Read full text
Authors: Neelima Prasad, Jarek Reynolds, Neel Karsanbhai, Tanusree Sharma, Lotus Zhang, Abigale J. Stangl, Yang Wang, Leah Findlater, Danna Gurari
DOI: 10.1109/wacv61042.2026.00575
Cited by: 0
References: 64

Abstract

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/

Fields of Study & Subjects

Domain Adaptation and Few-Shot Learning Face recognition and analysis Video Surveillance and Tracking Methods

Publication details

Journal / source
2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Publisher
IEEE
Pages
5945–5955
Publication date
6 March 2026