Jianjun Gao

Jianjun Gao

Auto-generated profile, based on publicly available information

Jianjun Gao

School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
9 August 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DPDuc Tri Phan
Duc Tri Phan
JGJianjun Gao
Jianjun Gao
YLYe Lu
Ye Lu
KYKim-Hui Yap
Kim-Hui Yap
KGKratika Garg
Kratika Garg
BHBoon Siew Han
Boon Siew Han
Automated crowd counting has emerged as a vision-based measurement method for crowd analysis and management. However, current methods based on density maps still suffer from challenges related to background noise and blurring effects. To address the limitations, this work proposes a deep neural network, named Joint Density Estimation and Object Detection (DEO-Net), specifically designed to generate high-quality density estimation maps. DEO-Net bridges the gap between detection and density estimation-based methods in crowd counting. The key contributions of this research are as follows: 1) DEO-Net incorporates object detection for more accurate crowd localization. 2) The network training is optimized with an Independent Structural Similarity Index (I-SSIM) and curriculum losses to better learn local structural information and recognize local maxima. 3) The experimental results demonstrate the state-of-the-art (SOA) performance of the proposed DEO-Net with Mean Absolute Error (MAE) values of 54.2, 6.2, 83.1 and 57.3 on the ShangHaiTechA, ShanghaiTechB, UCF QNRF, and JHU-CROWD++ public datasets, respectively.

12 May 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
JGJianjun Gao
Jianjun Gao
YWYi Wang
Yi Wang
KYKim-Hui Yap
Kim-Hui Yap
KGKratika Garg
Kratika Garg
BHBoon Siew Han
Boon Siew Han
Multiple pedestrian tracking is crucial for enhancing safety and efficiency in intelligent transport and autonomous driving systems by predicting movements and enabling adaptive decision-making in dynamic environments. It optimizes traffic flow, facilitates human interaction, and ensures compliance with regulations. However, it faces the challenge of tracking pedestrians in the presence of occlusion. Existing methods overlook effects caused by abnormal detections during partial occlusion. Subsequently, these abnormal detections can lead to inaccurate motion estimation, unreliable appearance features, and unfair association. To address these issues, we propose an adaptive occlusion-aware multiple pedestrian tracker, OccluTrack, to mitigate the effects caused by partial occlusion. Specifically, we first introduce a plug-and-play abnormal motion suppression mechanism into the Kalman Filter to adaptively detect and suppress outlier motions caused by partial occlusion. Second, we develop a pose-guided re-identification (Re-ID) module to extract discriminative part features for partially occluded pedestrians. Last, we develop a new occlusion-aware association method towards fair Intersection over Union (IoU) and appearance embedding distance measurement for occluded pedestrians. Extensive evaluation results demonstrate that our method outperforms state-of-the-art methods on MOTChallenge and DanceTrack datasets. Particularly, the performance improvements on IDF1 and ID Switches, as well as visualized results, demonstrate the effectiveness of our method in multiple pedestrian tracking.

6 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
WLWenyang Liu
Wenyang Liu
CCChen Cai
Chen Cai
JGJianjun Gao
Jianjun Gao
KWKejun Wu
Kejun Wu
YWYi Wang
Yi Wang
LCLap-Pui Chau
Lap-Pui Chau
Although the lightweight Vision Transformer has significantly advanced image super-resolution (SR), it faces the inherent challenge of a limited receptive field due to the window-based self-attention modeling. The quadratic computational complexity relative to window size restricts its ability to use a large window size for expanding the receptive field while maintaining low computational costs. To address this challenge, we propose PromptSR, a novel prompt-empowered lightweight image SR method. The core component is the proposed cascade prompting block (CPB), which enhances global information access and local refinement via three cascaded prompting layers: a global anchor prompting layer (GAPL) and two local prompting layers (LPLs). The GAPL leverages downscaled features as anchors to construct low-dimensional anchor prompts (APs) through cross-scale attention, significantly reducing computational costs. These APs, with enhanced global perception, are then used to provide global prompts, efficiently facilitating long-range token connections. The two LPLs subsequently combine category-based self-attention and window-based self-attention to refine the representation in a coarse-to-fine manner. They leverage attention maps from the GAPL as additional global prompts, enabling them to perceive features globally at different granularities for adaptive local refinement. In this way, the proposed CPB effectively combines global priors and local details, significantly enlarging the receptive field while maintaining the low computational costs of our PromptSR. The experimental results demonstrate the superiority of our method, which outperforms state-of-the-art lightweight SR methods in quantitative, qualitative, and complexity evaluations. Our code will be released at https://github.com/wenyang001/PromptSR.

2 May 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
JGJianjun Gao
Jianjun Gao
CCChen Cai
Chen Cai
RWRuoyu Wang
Ruoyu Wang
WLWenyang Liu
Wenyang Liu
KYKim-Hui Yap
Kim-Hui Yap
BHBoon Siew Han
Boon Siew Han


1 June 2017
Verified
Conference Paper
Closed access
JGJianjun Gao
Jianjun Gao
XXXinbo Xu
Xinbo Xu
FSFulin Su
Fulin Su
Synthetic aperture radar(SAR) imaging for ground moving targets has important applications both in military and civil areas. Range cell migration (RCM) occurs after range compression and needs to be corrected before azimuth processing. Due to the difficulty of range cell migration correction (RCMC) in SAR, a corresponding correction method based on envelope correlation method (ECM) is proposed. the phenomenon of RCM is introduced for SAR imaging of stationary and moving targets in strip-map mode, then, RCM results are deduced, next, RCMC algorithm based on ECM are elaborated and illustrated, Finally, simulation results are given and analyzed, which validates feasibility and effectiveness of the ECM algorithm, the ECM only requires basic cross-correlation operation and has equivalent precision.