Hanmei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hanmei Chen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Khan Muhammad
Sungkyunkwan University, Seoul, Republic of Korea
3 shared publications - Abdul Khader Jilani Saudagar
Information Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia
2 shared publications - Mingfu Xiong
School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China
2 shared publications Abdul Khader Jilani Saudagar
Information Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia
1 shared publicationAbdullah AlTameem
Information Systems Department, College of Computer and information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi Arabia
1 shared publication- Ik Hyun Lee
Department of Mechatronics Engineering, Tech University of Korea, Siheung, Republic of Korea
1 shared publication
Latest Publications
- 10 January 2025
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 34 (04)
FRACTAL FEATURE MODELING: MULTI-DIMENSIONAL ATTENTION AND SPATIAL ADAPTIVE RELATIONSHIP LEARNING FOR PERSON RE-IDENTIFICATION
Person Re-identification (person Re-ID), as an intelligent video surveillance technology capable of retrieving the same person from different cameras, may bring about some challenges arising from the changes in the person’s poses, different camera views as well as occlusion. Recently, person Re-ID equipped with the attention mechanism has gradually emerged as one of the most active areas of study in the fields of computer vision and fractal feature modeling applications. Despite the upsurge in related research, existing fractal-attention-based methods still face two major challenges when recognizing different pedestrians in unpredictable realistic environments: (1) the adaptability of a single local attention feature to hostile scenes cannot be guaranteed, and (2) the existing methods originating from attention features usually rely on the line mapping or simple variants, which make it difficult to excavate the association relationships among pedestrians with similar appearance attributes. To address these issues, this paper proposes a simple effective fractal feature modeling method, named multi-dimensional attention and spatial adaptive relationship learning framework (MASARF) to explore the correlation between pedestrian bodies for person Re-ID. The proposed framework encompasses a multi-dimensional fractal-attention feature learning model (MDAM) and a dual-branch graph convolutional model (DGCM). In particular, the MDAM comprises the local and global attention modules, which are used to capture multi-dimensional attention features for each person. Subsequently, the DGCM is used to construct the nonlinear mapping association relationships among the various body regions for each person via a dual-branch graph convolutional optimization strategy. Extensive experiments were conducted using public person Re-ID datasets (Market-1501, DukeMTMC-reid, and CUHK-03). The results demonstrate that the performance of the proposed approach is superior to that of state-of-the-art methods between 2% and 10% at Rank-1 (mAP). Essential differences exist between our method and the existing methods in terms of feature extraction and relationship transformation, which provides the validation of its novelty in the person Re-ID domain.
- 10 January 2025
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 34 (04)
FRACTAL FEATURE MODELING: MULTI-DIMENSIONAL ATTENTION AND SPATIAL ADAPTIVE RELATIONSHIP LEARNING FOR PERSON RE-IDENTIFICATION
Person Re-identification (person Re-ID), as an intelligent video surveillance technology capable of retrieving the same person from different cameras, may bring about some challenges arising from the changes in the person’s poses, different camera views as well as occlusion. Recently, person Re-ID equipped with the attention mechanism has gradually emerged as one of the most active areas of study in the fields of computer vision and fractal feature modeling applications. Despite the upsurge in related research, existing fractal-attention-based methods still face two major challenges when recognizing different pedestrians in unpredictable realistic environments: (1) the adaptability of a single local attention feature to hostile scenes cannot be guaranteed, and (2) the existing methods originating from attention features usually rely on the line mapping or simple variants, which make it difficult to excavate the association relationships among pedestrians with similar appearance attributes. To address these issues, this paper proposes a simple effective fractal feature modeling method, named multi-dimensional attention and spatial adaptive relationship learning framework (MASARF) to explore the correlation between pedestrian bodies for person Re-ID. The proposed framework encompasses a multi-dimensional fractal-attention feature learning model (MDAM) and a dual-branch graph convolutional model (DGCM). In particular, the MDAM comprises the local and global attention modules, which are used to capture multi-dimensional attention features for each person. Subsequently, the DGCM is used to construct the nonlinear mapping association relationships among the various body regions for each person via a dual-branch graph convolutional optimization strategy. Extensive experiments were conducted using public person Re-ID datasets (Market-1501, DukeMTMC-reid, and CUHK-03). The results demonstrate that the performance of the proposed approach is superior to that of state-of-the-art methods between 2% and 10% at Rank-1 (mAP). Essential differences exist between our method and the existing methods in terms of feature extraction and relationship transformation, which provides the validation of its novelty in the person Re-ID domain.
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (9) , 12448-12457
Cloth-Changing Person Re-Identification With Invariant Feature Parsing for UAVs Applications
Recently, deep learning-based intelligent vehicle control systems have played an important role in real-time road conditions assessment applications. It relies primarily on unmanned aerial vehicles (UAVs) for specific target retrieval, especially Cloth-Changing Person Re-identification (CC-ReID) technology, to provide support for road observations and environmental monitoring. Existing CC-ReID methods mainly focus on the invariant features of the front and rear views that are independent of clothing; among them, global color enhancement is a commonly used strategy. However, this method usually reduces the chromatism between the target foreground and background, which can easily lead to the loss of features unrelated to clothing and reduce the model's performance. To solve this problem, this paper proposes a data augmentation framework with Local Invariant Feature Transformation and Clothing Adversarial Parsing (LIFTCAP) for CC-ReID. The proposed framework is equipped with a Local Invariant Feature Transition (LIFT) module and a Clothes Adversarial Parsing (CAP) module. The former aims to extract invariant features for the same person with different clothes using the local transition manners. CAP is devoted to finding adversarial associations and parsing contour differences between clothing styles. Subsequently, a feature correlation strategy is alternately implemented between the two modules to complete the optimization procedure. Extensive experiments were conducted on the public CC-ReID datasets (LTCC and PRCC), demonstrating the superiority of our proposed method over the latest methods. Furthermore, our method achieved competitive performance, particularly on a surveillance video dataset (CCVID). In addition, based on the LIFTCAP strategy, the proposed algorithm can achieve a time efficiency as low as O(n) for detecting specific targets when deployed on a UAV server (Feisi X200) for real-time road conditions assessment and monitoring applications.
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (9) , 12448-12457
Cloth-Changing Person Re-Identification With Invariant Feature Parsing for UAVs Applications
Recently, deep learning-based intelligent vehicle control systems have played an important role in real-time road conditions assessment applications. It relies primarily on unmanned aerial vehicles (UAVs) for specific target retrieval, especially Cloth-Changing Person Re-identification (CC-ReID) technology, to provide support for road observations and environmental monitoring. Existing CC-ReID methods mainly focus on the invariant features of the front and rear views that are independent of clothing; among them, global color enhancement is a commonly used strategy. However, this method usually reduces the chromatism between the target foreground and background, which can easily lead to the loss of features unrelated to clothing and reduce the model's performance. To solve this problem, this paper proposes a data augmentation framework with Local Invariant Feature Transformation and Clothing Adversarial Parsing (LIFTCAP) for CC-ReID. The proposed framework is equipped with a Local Invariant Feature Transition (LIFT) module and a Clothes Adversarial Parsing (CAP) module. The former aims to extract invariant features for the same person with different clothes using the local transition manners. CAP is devoted to finding adversarial associations and parsing contour differences between clothing styles. Subsequently, a feature correlation strategy is alternately implemented between the two modules to complete the optimization procedure. Extensive experiments were conducted on the public CC-ReID datasets (LTCC and PRCC), demonstrating the superiority of our proposed method over the latest methods. Furthermore, our method achieved competitive performance, particularly on a surveillance video dataset (CCVID). In addition, based on the LIFTCAP strategy, the proposed algorithm can achieve a time efficiency as low as O(n) for detecting specific targets when deployed on a UAV server (Feisi X200) for real-time road conditions assessment and monitoring applications.
- 30 January 2024
- Published by Springer Nature in Cognitive Computation
- Vol. 16 (5) , 1-12
Person Re-identification with Spatial Multi-granularity Feature Exploration for Social Risk Situational Assessment
- 30 January 2024
- Published by Springer Nature in Cognitive Computation
- Vol. 16 (5) , 1-12
Person Re-identification with Spatial Multi-granularity Feature Exploration for Social Risk Situational Assessment