• 

  向孫程

  向孫程🤼‍♀️，工學博士，國研評審中心評閱專家，意昂4平台優秀畢業生，於2022年加入意昂4体育平台，目前主要從事計算機視覺、機器學習以及可解釋人工智能方面的研究。旨在構建以人為中心的人工智能框架，更好地去推動智慧城市、智慧醫療和智慧金融的建設步伐📅🧑‍🎓。近年來在圖像檢索、人體行為分析、多模態大模型👝🙎🏿‍♀️、醫學圖像處理領域頂級國際期刊和會議上發表論文40余篇，已授權中國發明專利2項，研究成果同時獲得蒙民偉國際交流基金的資助。當前主持國家自然科學基金青年科學基金項目1項🤘🏽、校級理科項目2項，先後參與國家自然科學基金面上項目、上海市衛健委🚮🎅🏼、上海市本科重點教改等多項科研項目，兼任中技協醫療器械專委會專家。此外🙇🏽‍♂️，向孫程博士還擔任ELSP👰🏿、OAJDA、IJAET等期刊編委和客座編輯，ICTAI 2019、IEEE ICME 2022、IEEE ICASSP 2024💂🏼、ACML 2024 Session Chair以及CVPR、ACM MM、AAAI🧑‍🚒、ACL等多個人工智能國際會議的程序委員會委員，並獲得國際研究數據分析“最佳研究者獎”、IEEE TMI Distinguished Reviewer獎。

  主頁🔖：[點擊這裏]

2017-2022，意昂4平台，電子信息與電氣工程意昂4🧿，博士

2014-2017，國防科技大學🕺🏻，計算機意昂4，碩士

2010-2014，長沙理工大學☂️，電氣與信息工程意昂4，學士

1. 2024-2026，國家自然科學基金青年科學基金項目，62301315，在研，主持；

2. 2022-2025，意昂4平台新進教師啟動計劃，23X010501967🔁，在研，主持🖕🏽🎸；

3. 2024-2025，意昂4平台人工智能+教育專項基金，CTLD24A0059，在研👩🏽‍🦲，主持

4. 2025-2028🌚，國家自然科學基金面上項目，62471288，在研，參與🧜🏿‍♂️；

5. 2023-2026👨🏽‍💼，上海市衛生健康委員會科研項目🧑🏽‍💻，202340010，在研，參與🦶🏽；

6. 2020-2023，國家自然科學基金面上項目🤾🏿‍♂️，61977045，結題，參與；

[41] Xiang S, Gao J, Xie M, et al. Learning Visual-Semantic Embedding for Generalizable Person Re-identification: A Unified Perspective[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2025.

[40] Ruan J, Xie M, Gao J, Gao X, Xiang S, et al. TTE: Two Tokens are Enough to Improve Parameter-Efficient Tuning [C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2025.

[39] Xie M, Xiang S, Ruan J, Gao X, Yu Z, Liu T, Fu Y. GPA: Enhancing Generalizable Physical Adversarial Attacks Across Multiple Vision Tasks[C]//ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025: 1-5.

[38] Ran W, Yu Z, Xiang S, Liu T, Fu Y. A Training-Free Correlation-Weighted Model for Zero-/Few-Shot Industrial Anomaly Detection with Retrieval Augmentation[C]//ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025: 1-5.

[37] Ruan J, Gao J, Xie M, Xiang S*. Learning multi-axis representation in frequency domain for medical image segmentation[J]. Machine Learning, 2025, 114(1): 10.

[36] Ruan J, Gao J, Xie M, Xiang S, et al. GIST: Improving Parameter Efficient Fine-Tuning via Knowledge Interaction[C]//Proceedings of the 32nd ACM International Conference on Multimedia. 2024: 8835-8844.

[35] Li Z, Xiang S, Yu T, et al. Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition[C]//International Conference on Intelligent Computing. Singapore: Springer Nature Singapore, 2024: 475-486.

[34] Zhang Z, Cai C, Du S, Xiang S, Qian D. Enhancing Nasopharyngeal Carcinoma Classification Based on Multi-View Cross-Modal Knowledge Distillation[C]//2024 IEEE International Symposium on Biomedical Imaging (ISBI). IEEE, 2024: 1-5.

[33] Han D, Qian D, Yan G, Kuang S, Wen R, Xiang S. Optimization of transcutaneous energy transmission system suitable for implanted devices[C]//Journal of Physics: Conference Series. IOP Publishing, 2024, 2787(1): 012003.

[32] Xiang S, Xu H, Xie M, et al. SubFace: learning with softmax approximation for face recognition[J]. Multimedia Tools and Applications, 2024: 1-17.

[31] Ruan J, Gao J, Xie M, Dong D, Xiang S, Liu T, Fu Y. iDAT: inverse Distillation Adapter-Tuning[C]//2024 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2024: 1-6.

[30] Gao J, Li Z, Xiang S, et al. Toward an end-to-end implicit addressee modeling for dialogue disentanglement[J]. Multimedia Tools and Applications, 2024: 1-24.

[29] Zhou C, Wang J, Xiang S, et al. A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images[J]. IEEE Transactions on Medical Imaging, 2024, 43(6): 2086-2097.

[28] Xiang S, Liu C, Ruan J, et al. VT-ReID: Learning Discriminative Visual-Text Representation for Polyp Re-Identification[C]//ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024: 1-5.

[27] Gao J, Ruan J, Xiang S, et al. LAMM: Label Alignment for Multi-Modal Prompt Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2024, 38(3): 1815-1823.

[26] Xiang S, Qian D, Gao J, et al. Rethinking person re-identification via semantic-based pretraining[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 20(3): 1-17.

[25] Xie M, Liu Z, Xiang S, et al. Editing outdoor scenes with a large annotated synthetic dataset[J]. Multimedia Tools and Applications, 2023: 1-18.

[24] Liu H, Gao J, Xiang S, et al. SAE-NTM: Sentence-Aware Encoder for Neural Topic Modeling[C]//Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023). 2023: 106-111.

[23] J. Gao, Z. Li, S. Xiang, T. Liu and Y. Fu. CluCDD: Contrastive Dialogue Disentanglement Via Clustering[C]//2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSPW59220.2023.10193381.

[22] Xiang S, Chen H, Ran W, et al. Deep multimodal representation learning for generalizable person re-identification[J]. Machine Learning, 2023: 1-19.

[21] Chen Q, Cai S, Cai C, Yu Z, Qian D, Xiang S*. Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval[C]//2023 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2023: 1-6.

[20] You D, Xia P, Chen Q, Wu M, Xiang S*, Wang J. AutoKary2022: A Large-Scale Densely Annotated Dateset for Chromosome Instance Segmentation[C]//2023 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2023: 1-6.

[19] Xiang S, Qian D, Guan M, et al. Less is more: Learning from synthetic data with fine-grained attributes for person re-identification[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19(5s): 1-20.

[18] Li Y, Yu Z, Xiang S, et al. AV-TAD: Audio-Visual Temporal Action Detection With Transformer[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023: 1-5.

[17] Han C, Xiang S*, Qian D. MTDL-NET: Morphological and Temporal Discriminative Learning for Heartbeat Classification[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023: 1-5.

[16] Yu Z, Hu Y, Xiang S, et al. CC-PoseNet: Towards Human Pose Estimation in Crowded Classrooms[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023: 1-5.

[15] Xiang S, Fu Y, Guan M, et al. Learning from self-discrepancy via multiple co-teaching for cross-domain person re-identification[J]. Machine Learning, 2023, 112(6): 1923-1940.

[14] Ruan J, Xiang S*, Xie M, et al. MALUNet: A multi-attention and light-weight unet for skin lesion segmentation[C]//2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2022: 1150-1156.

[13] Guan M, Xiang S, Liu T, et al. CDTNET: Cross-Domain Transformer Based on Attributes for Person Re-Identification[C]//2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, 2022: 1-6.

[12] Xiang S, You G, Li L, et al. Rethinking illumination for person re-identification: A unified view[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022: 4731-4739.

[11] Xie M, Xiang S, Wang F, et al. Spatial Attention Guided Local Facial Attribute Editing[C]//2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2022: 01-06.

[10] Wang F, Xiang S, Liu T, et al. Attention Based Facial Expression Manipulation[C]//2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 2021: 1-6.

[9] Xiang S, Fu Y, You G, et al. Taking a closer look at synthesis: Fine-grained attribute analysis for person re-identification[C]//ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021: 3765-3769.

[8] Xiang S, Fu Y, Chen H, et al. Multi-level feature learning with attention for person re-identification[J]. Multimedia Tools and Applications, 2020, 79: 32079-32093.

[7] Xiang S, Fu Y, Liu T. Progressive learning with style transfer for distant domain adaptation[J]. IET Image Processing, 2020, 14(14): 3527-3535.

[6] Xiang S, Fu Y, You G, et al. Unsupervised domain adaptation through synthesis for person re-identification[C]//2020 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2020: 1-6.

[5] Xiang S, Fu Y, Xie M, et al. Unsupervised person re-identification by hierarchical cluster and domain transfer[J]. Multimedia Tools and Applications, 2020, 79: 19769-19786.

[4] Xiang S, Fu Y, Liu T. Deep unsupervised progressive learning for distant domain adaptation[C]//2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2019: 903-908.

[3] Xu R, Fu Y, Liu T, Xiang S. Enhancing Model Performance of Person Re-Indentification on Unknown Target Domain[C]//2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS). IEEE, 2018: 1-4.

[2] Xiang S C, Zhang M X, Xing Z C, et al. Circuit design and optimization based on EXT, EXTU instruction[C]//Design, Manufacturing and Mechatronics: Proceedings of the International Conference on Design, Manufacturing and Mechatronics (ICDMM2016). 2017: 208-216.

[1] Xiang S, Zhang M, Xing Z, et al. Hardware design of ML algorithm in MIMO-OFDM system[C]//2016 3rd International Conference on Systems and Informatics (ICSAI). IEEE, 2016: 965-970.

人工智能與醫學，研究生

醫學影像智能技術😅，研究生

人機交互技術，本科生