Jie Hua — accepted AI-conference papers

2026

GLoMOT: Efficient Online GNN-based Low-Frame-Rate Multi-Object Tracker

Yaxuan Hu, Jie Hua, Gang Wu, Yuhong Yang, Atsushi Suzuki, Zhongyuan Wang

AAAI 2026technical

Low-frame-rate (LFR) Multi-Object Tracking (MOT) is crucial for efficient tracking on edge devices, as it significantly reduces computational and storage demands. However, existing trackers struggle in LFR settings due to large temporal gaps, extreme appearance changes, and motion non-linearity. Whi

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smoke Detection

Yuhan Jiang, Zhongyuan Wang, Jie Hua, Jinbi Liang, Zengmin Xu

ICASSP 2025accepted

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10,724 images covering three common scen…

Cited by 0 Source ↗Scholar ↗