Yuan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yuan Li has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- An Gu
Conservation Department, the Palace Museum, Beijing 100009, China
1 shared publication Baoqiang Kang
Department of Conservation Science, The Palace Museum, Beijing 100009, China
1 shared publication- Guanghua Li
College of Environment and Civil Engineering, Chengdu University of Technology, Chengdu 610059, China
1 shared publication - Hong Huang
Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing, China
1 shared publication - Jianyu Liu
Key Laboratory of Structure-Based Drug Design and Discovery, Ministry of Education, Shenyang Pharmaceutical University, Shenyang 110016, PR China
1 shared publication - Jiayu Zhao
MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Microelectronics, University of Science and Technology of China, Hefei, China
1 shared publication
Latest Publications
- 24 May 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 156
Fast shallow multi-subnet detector for real-time object detection
- 24 May 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 156
Fast shallow multi-subnet detector for real-time object detection
- Top Cited Papers
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 7101-7115
EI²Det: Edge-Guided Illumination-Aware Interactive Learning for Visible-Infrared Object Detection
The complementary characteristics of visible (VIS) and infrared (IR) modalities play a crucial role in scene perception for autonomous driving, especially under poor lighting conditions. However, effectively leveraging the complementary information from visible and infrared images to further enhance perception performance remains a challenging task. These challenges stem from the difficulty of adaptively balancing the contributions of visible and infrared information under dynamic illumination conditions, the reliance on static fusion strategies that fail to fully utilize cross-modal complementarities, and the limitations of existing datasets in terms of diverse scenes, fine-grained illumination annotations, and high imaging quality. To address the challenges, we propose an Edge-guided Illumination-aware Interactive learning-based Detector (EI2Det). It includes three novel modules. The cross-modal interaction module uses visible-priority and infrared-priority multi-head cross-attention mechanisms to refine inter-modality and intra-modality feature representations, improving the model’s robustness and adaptability. The illumination-aware weighting module predicts illumination intensity levels to dynamically adjust the contributions of visible and infrared features, ensuring effective fusion under various lighting conditions. The edge-guided fusion module leverages critical edge information to guide the detector’s attention to object boundaries, significantly enhancing its localization capability. Additionally, we introduce a Multi-modality Full-time dataset for Autonomous Driving (MFAD), featuring 12,370 image pairs with fine-grained annotations of illumination intensity, covering diverse driving scenarios and weather conditions. Extensive experiments on the public M3FD, KAIST, FLIR, LLVIP, and our MFAD datasets demonstrate superior performance and generalization ability of our approach. The code and dataset will be available at https://github.com/hukefy/EI2Det.
- 7 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 7101-7115
Top Cited PapersEI²Det: Edge-Guided Illumination-Aware Interactive Learning for Visible-Infrared Object Detection
The complementary characteristics of visible (VIS) and infrared (IR) modalities play a crucial role in scene perception for autonomous driving, especially under poor lighting conditions. However, effectively leveraging the complementary information from visible and infrared images to further enhance perception performance remains a challenging task. These challenges stem from the difficulty of adaptively balancing the contributions of visible and infrared information under dynamic illumination conditions, the reliance on static fusion strategies that fail to fully utilize cross-modal complementarities, and the limitations of existing datasets in terms of diverse scenes, fine-grained illumination annotations, and high imaging quality. To address the challenges, we propose an Edge-guided Illumination-aware Interactive learning-based Detector (EI2Det). It includes three novel modules. The cross-modal interaction module uses visible-priority and infrared-priority multi-head cross-attention mechanisms to refine inter-modality and intra-modality feature representations, improving the model’s robustness and adaptability. The illumination-aware weighting module predicts illumination intensity levels to dynamically adjust the contributions of visible and infrared features, ensuring effective fusion under various lighting conditions. The edge-guided fusion module leverages critical edge information to guide the detector’s attention to object boundaries, significantly enhancing its localization capability. Additionally, we introduce a Multi-modality Full-time dataset for Autonomous Driving (MFAD), featuring 12,370 image pairs with fine-grained annotations of illumination intensity, covering diverse driving scenarios and weather conditions. Extensive experiments on the public M3FD, KAIST, FLIR, LLVIP, and our MFAD datasets demonstrate superior performance and generalization ability of our approach. The code and dataset will be available at https://github.com/hukefy/EI2Det.
- 1 April 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 144, 113089
M3DNet: A manifold-based discriminant feature learning network for hyperspectral imagery
- 1 April 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 144, 113089
M3DNet: A manifold-based discriminant feature learning network for hyperspectral imagery
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2234-2240
Trend-based symbolic aggregate approximation for time series representation
Due to high dimensionality and large volume of big time series data, the existing analysis technologies are poor for processing the raw data. The symbolic aggregate approximation (SAX) is one of the most powerful tools to deal with big time series data via reducing dimensionality. However, the SAX is a mean value-based approach that cannot analyze significant trend features of time series. In this paper, trend-based symbolic aggregate approximation (TSAX) is proposed to handle this problem by adding trend indicators to each segment. The proposed method can depict the trend characteristics precisely without losing the merits such as symbolic nature of the SAX. Moreover, it has a more reasonable distance measure for the data processing task. The utility of the proposed approach is demonstrated by experiment of predefined pattern detection on different data sets.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2234-2240
Trend-based symbolic aggregate approximation for time series representation
Due to high dimensionality and large volume of big time series data, the existing analysis technologies are poor for processing the raw data. The symbolic aggregate approximation (SAX) is one of the most powerful tools to deal with big time series data via reducing dimensionality. However, the SAX is a mean value-based approach that cannot analyze significant trend features of time series. In this paper, trend-based symbolic aggregate approximation (TSAX) is proposed to handle this problem by adding trend indicators to each segment. The proposed method can depict the trend characteristics precisely without losing the merits such as symbolic nature of the SAX. Moreover, it has a more reasonable distance measure for the data processing task. The utility of the proposed approach is demonstrated by experiment of predefined pattern detection on different data sets.