Ge Cao

Mr. Ge Cao

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
20 August 2021 in IEEE Access
Verified
Journal Article
Open access
QTQing Tang
Qing Tang
GCGe Cao
Ge Cao
KJKang-Hyun Jo
Kang-Hyun Jo
Traffic sign detection is a critical task in the visual system of the Advanced Driver Assistance System (ADAS) and the Automated Driving System (ADS). Although the general object detection has achieved promising results by using Feature Pyramid Network (FPN) in recent years, we still observed that FPN cannot obtain satisfactory results in traffic sign detection because the size and class distribution of traffic signs are extremely unbalanced. To overcome this problem, a novel Plug-and-Play neck network Integrated Feature Pyramid Network with Feature Aggregation (IFA-FPN) is proposed in this paper based on the statistical characteristics of traffic signs. First, a lightweight operation is introduced to fully utilize the model and improve the inference speed of the model. Second, an Integrated Operation (IO) is introduced to solve the imbalance problem of Region-of-Interests (RoIs) in pyramid levels. Third, we introduce a Feature Aggregation (FA) structure to strengthen the feature representation capacity of feature maps, thereby enhancing the network robustness against the size discrepancy of traffic signs. The experiments are performed on three mainstream datasets, i.e., the German Traffic Sign Detection Benchmark (GTSDB), Swedish Traffic Sign Dataset (STSD), and Tsinghua-Tencent 100k dataset (TT100k). The experimental results demonstrate the superiority of the proposed IFA-FPN in the traffic sign detection tasks. Specifically, when the proposed IFA-FPN is applied to the Cascade RCNN, it achieves 80.3% mAP in GTSDB which surpasses FPN by 9.9%, 65.2% in mAP in STSD which surpasses FPN by 3.5%, and 93.6% in mAP in TT100k which surpasses FPN by 1.6%.

29 July 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YSYu Shen
Yu Shen
GCGe Cao
Ge Cao
HDHuanyu Dong
Huanyu Dong
BDBo Dong
Bo Dong
CLC.-M. Lee
C.-M. Lee
With the increasing severity of urban noise pollution, its detrimental impact on public health has garnered growing attention. However, accurate identification and classification of noise sources in complex urban acoustic environments remain major technical challenges for achieving refined noise management. To address this issue, this study presents two key contributions. First, we construct a new urban noise classification dataset, namely the urban noise 15-category dataset (UN15), which consists of 1620 audio clips from 15 representative categories, including traffic, construction, crowd activity, and commercial noise, recorded from diverse real-world urban scenes. Second, we propose a novel deep neural network architecture based on a residual network and integrated with a time–frequency attention mechanism, referred to as residual network with temporal–frequency attention (ResNet-TF). Extensive experiments conducted on the UN15 dataset demonstrate that ResNet-TF outperforms several mainstream baseline models in both classification accuracy and robustness. These results not only verify the effectiveness of the proposed attention mechanism but also establish the UN15 dataset as a valuable benchmark for future research in urban noise classification.

10 December 2021 in IEEE Access
Verified
Journal Article
Open access
QTQing Tang
Qing Tang
GCGe Cao
Ge Cao
KJKang-Hyun Jo
Kang-Hyun Jo
Person re-identification (re-ID) is the task of finding the matched person in a non-overlapping and multi-camera system. Because annotating images across multiple cameras is difficult and time-consuming, this paper focuses on fully unsupervised learning person re-ID that can learn person re-ID on unlabeled data. The unsupervised re-ID needs to self-generate pseudo labels to make training possible. Unlike human-annotated true labels, the pseudo labels contain noise labels which substantially hinder the network’s capability on feature learning. In order to refine the predicted pseudo labels, we introduce a novel unsupervised re-ID method named Multiple pseudo Labels Joint Training (MLJT) in this paper. Different from the existing works, the MLJT predicts multiple pseudo labels for each image by mining potential similarities in multiple ways. Based on invariance constraints among multiple pseudo labels, the MLJT is jointly optimized under the supervision of multiple pseudo labels to ease the impact of noises in the single pseudo label. The proposed MLJT predicts three types of pseudo labels for one input image. The first one is the clustering-based pseudo label. The second one is adaptive similarity measurement-based pseudo label. The third one is pseudo sub-labels which are predicted by mining channel-based self-similarities. The proposed MLJT has been extensively evaluated on two mainstream and public person re-ID datasets and outdoor real-world videos. Experiments demonstrate the effectiveness of the proposed multiple pseudo labels joint training strategy and the practicality of the proposed MLJT in real-world unsupervised person re-ID applications. The testing demo can be found at https://drive.google.com/drive/folders/1RvNaEiy6tF18_RcgTNcjE7jJ6eGy8sZL?usp=sharing .

18 April 2025 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
XVXuan-Thuy Vo
Xuan-Thuy Vo
DNDuy-Linh Nguyen
Duy-Linh Nguyen
APAdri Priadana
Adri Priadana
GCGe Cao
Ge Cao
JCJehwan Choi
Jehwan Choi
KJKang-Hyun Jo
Kang-Hyun Jo
Although local self-attentions exhibit translation equivariance and locality similar to convolution, the model has limited receptive fields and weak modeling ability. The main reason is that self-attention is computed within nonoverlapped windows. To overcome this issue, common methods need further operations to communicate the information across windows, such as window shifting, and sliding. These operations are memory unfriendly, not well supported, and optimized by modern deep-learning frameworks. Alternatively, this article exchanges information across nonoverlapped windows via efficiently mixing abstract tokens (MAT). The MAT block includes the following steps. First, the image tokens are partitioned into windows and each window is merged with an abstract token. Second, in each window, interactions of image tokens and the abstract token to image tokens are performed. Third, because the abstract token learns abstract information from each corresponding window, mixing all abstract tokens via transformer encoder helps to exchange information between local windows and result in global context modeling. Fourth, the global information of the mixed tokens is propagated back to the image tokens through transformer decoder. The MAT block is efficient and easy to implement, only containing matrix multiplications. In addition, this article also proposes a bilinear patch embedding that samples relevant regions of the input tokens based on learned offsets. Extensive experiments are conducted and evaluated with various tasks such as image classification, object detection, and segmentation. As a result, our method achieves promising performances across tasks. For example, MAT-2 accomplishes 79.0% top-1 accuracy on ImageNet-1 K with 0.7 GFLOPs and outperforms the baseline Swin-0.7 G by 4.6% while reducing 15.2 ms on CPU and 0.53 ms on GPU devices. The MAT-4 surpasses Swin-T by 1.8% mIoU with only 70% GFLOPs.

30 June 2025 in IEEE Access
Verified
Journal Article
Open access
GCGe Cao
Ge Cao
QTQing Tang
Qing Tang
XVXuan-Thuy Vo
Xuan-Thuy Vo
APAdri Priadana
Adri Priadana
TTTien-Dat Tran
Tien-Dat Tran
KJKang-Hyun Jo
Kang-Hyun Jo
Person Re-identification (Re-ID) aims at accurately querying pedestrians across multiple non-overlapping cameras system, playing an essential role in computer vision applications. While CNN-based methods leverage feature aggregation and attention mechanisms to achieve competitive performance, their limitations in capturing long-range dependencies have motivated the research of transformer-based architectures, which excel in the evolution of person Re-ID research. Despite leveraging pretrained vision-language models to facilitate visual encoder training, current methods suffer from fragmented optimization procedures, complexity increasing, and inadequate semantic guidance from textual prompts. To address these limitations, we propose an end-to-end method named Text-Guided Fusion Transformer (TGFT). TGFT applies the fixed but semantically enriched texts to guide visual training with a novel Gated Cross Attention (GCA) fusion module. The GCA module adaptively modulates the integration of textual information and visual features, effectively enhancing cross-modal feature alignment and semantic consistency. Without significantly increasing computational complexity or parameter count, TGFT achieves superior performance, demonstrating strong effectiveness and scalability on multiple major Re-ID benchmarks.

12 May 2025 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
APAdri Priadana
Adri Priadana
DNDuy-Linh Nguyen
Duy-Linh Nguyen
XVXuan-Thuy Vo
Xuan-Thuy Vo
MPMuhamad Dwisnanto Putro
Muhamad Dwisnanto Putro
GCGe Cao
Ge Cao
KJKang-Hyun Jo
Kang-Hyun Jo
Smart factories require secure and sustainable worker authentication for safe operations. Biometric continuous authentication based on facial recognition is one of the most convenient mechanisms. This method applies a face recognition task to verify the captured face as an authorized user. However, existing methods that employ large networks for high-accuracy face recognition incur high computational costs and slow down the process, rendering them unsuitable for continuous operation. This work proposes an efficient and rapid face recognizer with high accuracy. It offers a faster face residual network, containing efficient FasterFace blocks and efficient channel spatial attention for improved feature extraction. As a result, the proposed network achieves 97.08% based on average accuracy, outperforming the other networks on five benchmark datasets. It performs faster at 19.91 frames per second in real time on CPU-based hardware when integrated with a face detector, showcasing its capacity to support real-time biometric continuous authentication for smart factory workers.