Zhongyu Jiang

Zhongyu Jiang

Auto-generated profile, based on publicly available information

Zhongyu Jiang

University of Washington

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 February 2021 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
Yizhou WangYizhou Wang
Yizhou Wang
ZJZhongyu Jiang
Zhongyu Jiang
YLYudong Li
Yudong Li
JHJenq-Neng Hwang
Jenq-Neng Hwang
GXGuanbin Xing
Guanbin Xing
HLHui Liu
Hui Liu
Various autonomous or assisted driving strategies have been facilitated through the accurate and reliable perception of the environment around a vehicle. Among the commonly used sensors, radar has usually been considered as a robust and cost-effective solution even in adverse driving scenarios, e.g., weak/strong lighting or bad weather. Instead of considering fusing the unreliable information from all available sensors, perception from pure radar data becomes a valuable alternative that is worth exploring. In this paper, we propose a deep radar object detection network, named RODNet, which is cross-supervised by a camera-radar fused algorithm without laborious annotation efforts, to effectively detect objects from the radio frequency (RF) images in real-time. First, the raw signals captured by millimeter-wave radars are transformed to RF images in range-azimuth coordinates. Second, our proposed RODNet takes a snippet of RF images as the input to predict the likelihood of objects in the radar field of view (FoV). Two customized modules are also added to handle multi-chirp information and object relative motion. The proposed RODNet is cross-supervised by a novel 3D localization of detected objects using a camera-radar fusion (CRF) strategy in the training stage. Due to no existing public dataset available for our task, we create a new dataset, named CRUW, 1 1The dataset and code are available at https://www.cruwdataset.org/. which contains synchronized RGB and RF image sequences in various driving scenarios. With intensive experiments, our proposed cross-supervised RODNet achieves 86% average precision and 88% average recall of object detection performance, which shows the robustness in various driving conditions.

14 November 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
RGRenshu Gu
Renshu Gu
GWGaoang Wang
Gaoang Wang
ZJZhongyu Jiang
Zhongyu Jiang
JHJenq-Neng Hwang
Jenq-Neng Hwang
Despite the increasing need of analyzing human poses on the street and in the wild, multi-person 3D pose estimation using monocular static or moving camera in real-world scenarios remains a challenge, either requiring large-scale training data or high computation complexity due to the high degrees of freedom in 3D human poses. We propose a novel scheme to effectively track and hierarchically estimate 3D human poses in natural videos in an efficient fashion. Without the need of using labelled 3D training data, we formulate torso estimation as a Perspective-N-Point (PNP) problem, and limb pose estimation as an optimization problem, and hierarchically structure the high dimensional poses to efficiently address the challenge. Experiments show good performance and high efficiency of multi-person 3D pose estimation on real-world videos, including street scenarios and various human daily activities from fixed and moving cameras, resulting in great new opportunities to understand and predict human behaviors.

21 November 2024
Verified
Book Chapter
Closed access
PDF file
YHYuan-Hao Ho
Yuan-Hao Ho
JCJen-Hao Cheng
Jen-Hao Cheng
SKSheng Yao Kuan
Sheng Yao Kuan
ZJZhongyu Jiang
Zhongyu Jiang
WCWenhao Chai
Wenhao Chai
JHJenq-Neng Hwang
Jenq-Neng Hwang

28 March 2025
Verified
Book Chapter
Closed access
PDF file
JSJiacheng Sun
Jiacheng Sun
HHHsiang-Wei Huang
Hsiang-Wei Huang
CYCheng-Yen Yang
Cheng-Yen Yang
ZJZhongyu Jiang
Zhongyu Jiang
JHJenq-Neng Hwang
Jenq-Neng Hwang

3 November 2024
Verified
Book Chapter
Closed access
PDF file
ZZZhenyu Zhang
Zhenyu Zhang
WCWenhao Chai
Wenhao Chai
ZJZhongyu Jiang
Zhongyu Jiang
TYTian Ye
Tian Ye
MSMingli Song
Mingli Song
GWGaoang Wang
Gaoang Wang

13 January 2026 in IEEE Transactions on Image Processing
Verified
Journal Article
Open access
CYCheng-Yeng Yang
Cheng-Yeng Yang
HHHsiang-Wei Huang
Hsiang-Wei Huang
WCWenhao Chai
Wenhao Chai
ZJZhongyu Jiang
Zhongyu Jiang
JHJenq-Neng Hwang
Jenq-Neng Hwang
The Segment Anything Model 2 (SAM 2) has demonstrated exceptional performance in object segmentation tasks but encounters challenges in visual object tracking, particularly in handling crowded scenes with fast-moving or self-occluding objects. Additionally, its fixed-window memory mechanism indiscriminately retains past frames, leading to error accumulation. This issue results in incorrect memory retention during occlusions, causing the model to condition future predictions on unreliable features and leading to identity switches or drift in crowded scenes. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 that integrates temporal motion cues with a novel motion-aware memory selection strategy. SAMURAI effectively predicts object motion and refines mask selection, achieving robust and precise tracking without requiring retraining or fine-tuning. It demonstrates strong training-free performance across multiple VOT benchmark datasets, underscoring its generalization capability. SAMURAI achieves state-of-the-art performance on LaSOText, GOT-10k, and TrackingNet, while also delivering competitive results on LaSOT, VOT2020-ST, VOT2022-ST, and VOS benchmarks such as SA-V. These results highlight SAMURAI’s robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments with an optimized memory selection mechanism. Code and results are available at https://github.com/yangchris11/samurai.