paper-with-me

홈 › Papers

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

2025-12-10 · Neelima Prasad, Jarek Reynolds, Neel Karsanbhai, Tanusree Sharma, Lotus Zhang, Abigale Stangl, Yang Wang, Leah Findlater, Danna Gurari arxiv

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/

📄 PDF Abstract BibTeX arXiv:2512.10102

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITS

2026-07-09 · Roba H. Farouk, Catherine M. Elias arxiv

Large-scale and diverse datasets are needed to train AI models to take real-time decisions for autonomous vehicles (AVs), an intelligent transportation system (ITS) application. Pedestrian intention and trajectory predic…

Trajectory PredictionAutonomous VehiclesFace Swapping

Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks

2025-12-20 · Yucheng Fan, Jiawei Chen, Yu Tian, Zhaoxia Yin arxiv

As vision-language models (VLMs) become widely adopted, VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attributes from images shared on social media…

Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search

2025-09-25 · Shuo Huang, Xingliang Yuan, Gholamreza Haffari, Lizhen Qu arxiv

The increasing adoption of large language models (LLMs) in cloud-based services has raised significant privacy concerns, as user inputs may inadvertently expose sensitive information. Existing text anonymization and de-i…

Design of Stochastic Quantizers for Privacy Preservation

2024-03-05 · Le Liu, Yu Kawano, Ming Cao

In this paper, we examine the role of stochastic quantizers for privacy preservation. We first employ a static stochastic quantizer and investigate its corresponding privacy-preserving properties. Specifically, we demons…

Privacy PreservingQuantization

Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning

2026-01-25 · Shudi Weng, Ming Xiao, Mikael Skoglund arxiv

Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication …

Federated Learning