JQJian Qu

Jian Qu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jian Qu has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CTPG-Net: A Cross-Modal Image-Text Matching Network for Traffic Police Gesture Understanding

    by Zhu Kang, Deng Yufeng, Wang Ning, Jian Qu

    In complex traffic environments, autonomous driving systems not only need to recognize traditional traffic signs and traffic lights, but also need to understand the semantics of traffic police gestures accurately. Accurate interpretation of traffic police gestures is crucial for ensuring road safety and improving traffic efficiency. However, most existing research treats traffic police gestures as a single classification task, primarily focusing on gesture category recognition and neglecting the fine-grained semantics behind these gestures, thereby failing to meet the semantic understanding requirements of intelligent transportation systems. To address this issue, we propose a cross-modal image-text semantic-matching framework for understanding traffic police gestures. We construct a cross-modal dataset of traffic police gestures (CTPG-Dataset), equipping each gesture image with a fine-grained textual semantic description. We also design a two-stream cross-modal matching network (CTPG-Net), which combines BERT and ResNet50, introduces a Top-K Hard Negative InfoNCE (THN-InfoNCE) loss function, and improves cross-modal feature representation and semantic discrimination by mining the most challenging hard-negative samples and incorporating a temperature coefficient optimization strategy. We conducted extensive comparative and ablation experiments, and the results show that the combination of ResNet50 and BERT achieves the best performance when THN-InfoNCE optimization is introduced. Our method achieves an mAP of 79.56% and shows significant improvements in metrics such as Recall@1 and MRR. Inference experiments further validate that the model can accurately perform image-to-text and text-to-image retrieval, demonstrating strong cross-modal semantic understanding and robust retrieval.

  • Open Access

    A Novel Multi-Sensor Fusion SLAM Framework for Anti-‎Interference

    by Yu Ji, Jian Qu

    Nowadays, people have high requirements for the robustness of autonomous driving. As a key technology in the field of autonomous driving, SLAM requires a lightweight and explainable algorithm framework when dealing with perception degradation scenes. At present, most ‎multi-sensor fusion SLAM algorithms use methods such as training neural networks or adding new odometry constraints to achieve anti-‎interference, but these methods do not meet the requirements. We use the data communication technology of the ROS (Robot Operating ‎System) platform to integrate the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm, the LiDAR Noise Filtering algorithm, and RTAB-Map (a multi-sensor fusion algorithm based on graph optimization). We then conducted experiments in three designed ‎perception degradation scenes and used the MME indicator to quantify the experiments. The results showed that the MME of our framework in the perception-degraded environment was reduced by an average of 0.107, proving that the framework we proposed performs bet-‎ter than RTAB-Map in dealing with some perception degradation scenes.

  • Open Access

    A Novel ARM-DC AutoConNet for Accurate Long‐Term ‎Time‐Series Forecasting

    by Yangyang Li, Jian Qu

    Time series forecasting is essential in many fields, such as financial analysis, climate forecasting, and energy demand. This ‎study proposes an improved dilated convolutional(DC) AutoConNet architecture to solve the problem of accurate long-term forecasting of complex time series data. The model significantly improves its robustness and generalization ability by ‎integrating multi-scale dilated convolution, layer normalization, and a new adaptive rescaling mechanism(ARM). The ‎main improvement is that while maintaining the efficiency of the original AutoConNet, it effectively solves the overfitting ‎problem and the defect of insufficient capture of temporal dependencies. We evaluated the model performance on 16 ‎standard datasets (including finance, climate, health, etc.), such as M4, M5, ETTh1, ETTh2, ETTm1, and ETTm2. The ‎ARM-DC AutoConNet achieved significant improvements on multiple datasets, especially in the long forecast period, ‎which can significantly reduce the SMAPE index and stabilize the shape value. Comparative experiments demonstrate ‎that the proposed model consistently outperforms or equals the benchmark AutoConNet in terms of error indicators.‎ Furthermore, the proposed model surpasses the AutoConNet Model in error metrics. The most significant improvement is ‎the combination of the adaptive rescaling mechanism and dilated convolution. The improved convolutional architecture ‎provides a feasible solution for reliable long-term prediction and inspires the future development of time series deep learning‎.

  • Open Access

    Research on Deep Learning-Based Methods for Matching Traffic Sign Images with Textual Captions

    by Ning Wang, Jian Qu

    Intelligent transportation systems face challenges in matching traffic sign images with natural language descriptions, particularly in modal heterogeneity and fine-grained semantic alignment. This issue is crucial for accurately understanding the traffic environment and safety decision-making in autonomous driving, carrying significant application value. Most existing methods are based on classification or template matching and lack deep semantic modelling between images and texts, making it difficult to adapt to real-world complex scenarios. To address this, this paper proposes a deep learning-based image-text matching method that automatically extracts directory structures to generate fine-grained labels, and introduces InfoNCE contrastive loss based on intra-batch negative samples to achieve cross-modal learning. Pré-trained ResNeXt50_32x4d and DistilBERT are employed as image and text encoders, which are uniformly mapped to a shared embedding space. Experimental results demonstrate that the proposed method outperforms existing methods regarding Recall@1, mean Average Precision (mAP), and Mean Reciprocal Rank (MRR), showcasing stronger semantic alignment capability and application potential.


  • Open Access

    Semantic-Aware Path Planning by Using Dynamic Weighted‎Dijkstra for Autonomous Driving

    by Hao Gu, Jian Qu

    In the current urban road environment, it is difficult to balance path planning, semantic perception, and energy consumption management. The existing algorithms respond slowly to sudden congestion, traffic lights, and pedestrian activities, and ‎lack energy constraint considerations. This paper builds a closed-loop autonomous driving system covering path planning, ‎positioning fusion, and energy perception control on the MATLAB simulation platform. The path planning module uses ‎built-in traffic signals, speed limit areas, and pedestrian activity areas as dynamic weights, and generates smooth feasible ‎trajectories through the improved dynamic weighted Dijkstra algorithm combined with B-spline interpolation to ensure ‎efficient response in various scenarios. The positioning fusion module adopts extended Kalman filtering technology to ‎integrate GPS, wheel speed odometer, front-mounted camera, and LiDAR data, and simulates signal loss and Gaussian ‎noise interference to ensure high-precision positioning under harsh conditions. The energy perception control module ‎just the acceleration and steering strategies in real time based on simplified vehicle dynamics and residual energy budget, ‎and supports dry/wet road braking simulation, to achieve endurance optimization under the premise of ensuring ‎safety. The study shows that the proposed method can simultaneously improve safety and energy efficiency in dynamic ‎traffic and multi-source noise interference environments‎.


  • Open Access

    Enhancing Autonomous Driving: A Novel Approach of Mixed Attack and Physical Defense Strategies

    by Chuanxiang Bi, Shang Shi, Jian Qu

    Adversarial attacks are a significant threat to autonomous driving safety, especially in the physical world where there is a prevalence of "sticker-paste" attacks on traffic signs. However, most of these attacks are single-category attacks with little interference effect. This paper builds an autonomous driving platform and conducts extensive experiments on five single-category attacks. Moreover, we proposed a new physical attack - a mixed attack consisting of different single-category physical attacks. The proposed method outperforms existing methods and can reduce the accuracy of traffic sign recognition of an autonomous driving platform by 38%. Furthermore, we proposed a new anti-jamming model for physical adversarial defense, CBAM-ResNet26 & CBAM-Alexnet, which improves an autonomous driving platform's traffic sign recognition accuracy to 63% under mixed attack. Finally, experiments were also conducted with datasets with different ratios of adversarial attack examples, and the experimental results showed that in adversarial training, the higher the ratio of adversarial examples, the higher the recognition accuracy. However, a too high ratio would reduce the accuracy of normal traffic signs. Finally, the optimal ratio for physical adversarial defense training is 1:2.


  • Open Access

    A Study on Bilingual Deep Learning PIS Neural Network Model Based on Graph-Text Modal Fusion

    by Yan Xie, Jian Qu

    This research investigates a multilingual cross-modal pedestrian information search (PIS) technique based on graph-text modal fusion. Initially, we used a combination of replacement neural networks to improve the English Language-Based Pedestrian Information Search model with Graph-Text Modal Fusion (GTMFLPIS) performance. In addition, existing research lacks GTMFLPIS models for other languages. Therefore, we propose to train GTMFLPIS models for Chinese. The Chinese GTMFLPIS model was trained using our previously constructed Chinese CUHK-PEDES dataset. The Rank1 of the Chinese RN50_PMML12V2 model reached 0.5989. In addition, we found that a single model could not adapt to the limitations of multiple languages. Therefore, we propose a novel architecture to implement a single-model multilingual cross-modal GTMFLPIS model in this research. We propose RN50_DBMCV2 and ENB7_DBM-CV2, both of which have improved performance over the existing ones. We constructed a bilingual dataset using our Chinese CUHK-PEDES dataset and existing English CUHK-PEDES dataset to test our novel multilingual cross-modal GTMFLPIS model. In addition, we found that the loss function significantly impacts the model during our experiments. Therefore, we optimized the performance of the existing loss functions for cross-modal GTMFLPIS models. Our proposed CCMPM loss function improves the performance of the model by 2%. The experimental results of this research show that our proposed model has advantages in improving the accuracy of PIS.


  • A novel neural network architecture and cross-model transfer learning for multi-task autonomous driving

    by Youwei Li, Jian Qu

    Purpose: The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.Design/methodology/approach: First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.Findings: This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.Originality/value: This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.


  • Open Access

    BM5-SP-SC: A Dual Model Architecture for Contradiction Detection on Crowdfunding Projects

    by Wenting Hou, Jian Qu

    Despite the prevalence of scams in crowdfunding projects, currently, there is little research into the identification of fraudulent or infeasible crowdfunding projects. Since detecting fraudulent crowdfunding projects is challenging, most existing research on fake information has focused on detecting fake news or fake charity crowdfunding projects based on social media, but research on fraudulent or infeasible crowdfunding projects is very limited. Therefore, to solve this problem, we focus on how to detect fraudulent crowdfunding projects based on knowledge extraction and contradiction detection. We proposed a novel method called BM5-SP-SC (BERT-MT5-Sentence Pattern-Sentiment Classification). BM5 (BERT-MT5), which is built from a combination of a key-BERT and a fine-tuned MT5 transformers, was used to extract feature information from crowdfunding projects. We proposed a novel method for MT5 training to construct an adaptive BM5 model. The correct rate of keywords extracted by our novel adaptive BM5 model was up to 72.7%, the recall was 100%, and the F-measure was up to 84.19%. The minimum train loss of the BM5 model was up to 0.1342, and the evaluation loss achieved was 0.3064. The BLEU score of summary-to-keyword was 37.336. Moreover, we proposed an SP (Sentence Pattern) matching method to achieve knowledge extraction. Furthermore, SC (Sentiment Classification) was used to build a sentiment classifier thesaurus for identifying fraudulent and infeasible crowdfunding projects. Our proposed BM5-SP-SC achieved an overall accuracy of 85.26% in detecting fraudulent crowdfunding projects. Keywords: crowdfunding projects; contradiction detection; knowledge extraction; BERT; MT5; feature information extraction *Corresponding author: Tel.: (+66) 863759307 E-mail: jianqu@pim.ac.th