一、个人基本信息
Aouaidjia Kamel，男，上海交通大学博士，阿尔及利亚人。国家自然科学基金外国青年学者基金获得者
二、奖励
三、主讲课程和研究方向
主讲课程：深度学习、计算机视觉、人工智能、专业英语
研究方向：计算机视觉与机器学习
四、论文
第一作者论文：
[1]Aouaidjia Kamel, Wenhao Zhang, Aofan Li, and Chongsheng Zhang. Spatio-temporal invariant descriptors for skeleton-based human action recognition Engineering applications of artificial intelligence, 2026, DOI:
[2]Aouaidjia Kamel, Chongsheng Zhang, and Ioannis Pitas. Improving action segmentation via explicit similarity measurement Information Science, 2025, DOI: 10.1016/j.ins.2024.121832
[3]Aouaidjia Kamel, Wenhao Zhang, Aofan Li, Chongsheng Zhang. “AOG-BAT: 3D human pose estimation via Attention-Ordered Graph and Body-Aware Transformer” Pattern Recognition, 2026
[4]Aouaidjia Kamel, B Sheng, P Li, J Kim, DD Feng. Efficient Body Motion Quantification and Similarity Evaluation Using 3-D Joints Skeleton Coordinates IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, DOI: 10.1109/TSMC.2019.2916896
[5]Aouaidjia Kamel, B Sheng, P Li, J Kim, DD Feng. Hybrid Refinement-Correction Heatmaps for Human Pose Estimation IEEE Transactions on Multimedia, 2020, DOI: 10.1109/TMM.2020.2999181
[6]Aouaidjia Kamel, B Sheng, P Yang, P Li, R Shen, DD Feng. Deep Convolutional Neural Networks for Human Action Recognition Using Depth Maps and Postures IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, DOI: 10.1109/TSMC.2018.2850149
[7]Aouaidjia Kamel, B Liu, P Li, B Sheng. An investigation of 3D human pose estimation for learning Tai Chi: A human factor perspective International Journal of Human–Computer Interaction, 2018, DOI:10.1080/10447318.2018.1543081
[8]Aouaidjia Kamel, I Boukerch. Data augmentation for land cover classification using generative adversarial networks IEEE International Geoscience and Remote Sensing Symposium, 2021, DOI: 10.1109/IGARSS47720.2021.9553374
[9]Aouaidjia Kamel, I Boukerch. Multi-scale convolutional neural networks for cloud segmentation Remote Sensing of Clouds and the Atmosphere, 2020, DOI: 10.1117/12.2573810
合作论文：
[10]Hao Wang, Aouaidjia Kamel, Constantine Kotropoulos, and Chongsheng Zhang. Parameter-Efficient and Adaptive Fine-Tuning. 2026 20th international conference on document analysis and recognition (ICDAR). IEEE.
[11]Chongsheng Zhang, George Almpanidis, Gaojuan Fan, Binquan Deng, Yanbo Zhang, Ji Liu, Aouaidjia Kamel, Paolo Soda, João Gama. A Systematic Review on Long-Tailed Learning, IEEE Transactions on Neural Networks and Learning Systems, 2025, DOI: 10.1109/TNNLS.2025.3539314
[12]Binquan Deng, Aouaidjia Kamel, Chongsheng Zhang. Open-set long-tailed recognition via orthogonal prototype learning and false rejection correction. Neural Networks, 2025, DOI: 10.1016/j.neunet.2024.106789
[13]Yuanhang Cai, Kamel Aouaidjia, Chongsheng Zhang. PACAF-Net: pixel shuffling based fiderality-preserved up/downsampling and adaptive cross-attention fusion for effective medical image segmentation. Signal, Image and Video Processing, 2025, DOI: 10.1007/s11760-025-03953-8
[14]S Zeghoud, SG Ali, E Ertugrul, A Kamel, B Sheng, P Li, X Chi, J Kim, L Mao. Real-time spatial normalization for dynamic gesture classification. The Visual Computer , 2022, DOI: 10.1016/j.neunet.2024.106789
[15]A Karambakhsh, A Kamel, B Sheng, P Li, P Yang, DD Feng. Deep gesture interaction for augmented anatomy learning International Journal of Information Management, 2019, DOI: 10.1016/j.ijinfomgt.2018.03.004
五、科研项目
[1] 国家自然科学基金外国青年学者基金， 2023.01-2024.12，2年，主持
Title: Human Pose Estimation and Action Recognition for Human Behavior Understanding Using Deep Learning.
Number： 62250410371
[2] 河南省博士后科研项目, 省级项目， 2024.01-2025.12，主持
Number： 232102211021
Title: Skeleton-based Action Recognition Using Multiple Spatio-Temporal Invariant Features
[3]国家外国专家局外国学者研究基金项目，部级项目， 2023.01-2024.12，主持
Title: Human Pose Estimation and Action Recognition for Human Behavior Understanding Using Deep Learning
Number：WGXZ2023042L
六、项目代码
[1] Spatio-temporal invariant descriptors for skeleton-based human action recognition
https://github.com/adjkamel/imdar
[2] 3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer
https://github.com/adjkamel/GOA_BAT
[3] Improving action segmentation via explicit similarity measurement
https://github.com/adjkamel/segsim
[4] Multi-scale convolutional neural networks for cloud segmentation
https://github.com/adjkamel/muliscal_cloud
[5] Data augmentation for land cover classification using generative adversarial networks
https://github.com/adjkamel/data_aug
[6] Deep convolutional neural networks for human action recognition using depth maps and postures https://github.com/adjkamel/action_fusion
[7] 3D Human pose estimation from a single depth image
https://github.com/adjkamel/3Dhuman_pose
[8] Human motion quantification and similarity evaluation using 3D joints coordinates https://github.com/adjkamel/human_motion
[9] Hand gesture recognition from a single depth image
https://github.com/adjkamel/depth_hand
[10] Auto-Encoder for image reconstruction
https://github.com/adjkamel/auto_encoder
