李硕，博士，西安电子科技大学人工智能学院全职博士后，合作导师为焦李成教授和刘芳教授，智能感知与图像理解教育部重点实验室（IPIU）成员，获得中国电子教育学会2024年度优秀博士学位论文提名奖，主要从事人工智能算法研究，包括计算机视觉，深度学习，多模态学习，空间智能等。研究工作主要发表于CVPR、AAAI、ECCV、TIP、 TCYB、TNNLS、TCSVT、TGRS和PR等领域内国际主流会议和期刊。

研究方向：

[1] 计算机视觉、深度学习、无监督学习、小样本学习、多模态学习、标签受限学习、视觉概念学习等；

[2] 图像分类、语义分割、视频异常检测、显著目标检测、行为识别、目标跟踪等；

[3] 空间智能：三维场景重建、理解、推理和规划等。

学生培养：

欢迎学有余力、想要接触科研或致力于保研的本科生参与到课题组的科研中来，要求如下：

1）认真踏实、积极主动、坚持不懈；

2）有浓厚的研究兴趣和学术追求；

3）最好有代码基础，掌握Python，了解Pytorch。若是大一和大二学生，没有代码基础也OK，可培养。

目前课题组有教授、副教授、博士后、博士研究生和硕士研究生共40余人以及10余名本科生。本课题组致力于人工智能科学研究和论文产出，可提供前沿的研究方向、新颖的研究思路、充足的服务器资源和经费、浓厚的科研氛围和完善的指导模式。只要符合上面的要求，可确保一年半载之后在代码能力和科研素养上有质的飞跃。欢迎有志在本科阶段做科研发论文的同学通过邮箱（lishuo@xidian.edu.cn）进行联系和咨询。

主持项目：

[1] 国家自然科学基金委员会：青年科学基金项目，2025年01月至2027年12月，在研；

[2] 陕西省人力资源和社会保障厅：陕西省博士后科研项目资助三等资助，2024年12月，在研；

[3] 财政部和教育部：中央高校基本科研业务费，2024年01月至2024年12月，在研；

[4] 中国博士后科学基金会：国家资助博士后研究人员计划C档，2023年12月，在研；

[5] 中国博士后科学基金会：博士后科学基金第74批面上资助，2023年12月，在研。

学术成果（*为通讯作者）：

[1] Shuo Li, Fang Liu*, Zehua Hao, Xinyi Wang, Lingling Li, Xu Liu, Puhua Chen, Wenping Ma. Logits DeConfusion with CLIP for Few-Shot Learning[C]. Conference on Computer Vision and Pattern Recognition, 2025. [NEW]

[2] Shuo Li, Fang Liu*, Licheng Jiao, Lingling Li, Puhua Chen, Xu Liu, Wenping Ma. Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2025.3525545, 2025. [NEW]

[3] Shuo Li, Fang Liu*, Licheng Jiao, Xu Liu, Puhua Chen, Lingling Li. Mask-Guided Correlation Learning for Few-Shot Segmentation in Remote Sensing Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2024.3417965, 2024.

[4] Shuo Li, Fang Liu*, Licheng Jiao, Puhua Chen, Lingling Li. Self-supervised self-organizing clustering network: A novel unsupervised representation learning method[J]. IEEE Transactions on Neural Networks and Learning Systems, vol.35, no.2, pp. 1857-1871, Feb. 2024.

[5] Shuo Li, Fang Liu*, Zehua Hao, Licheng Jiao, Xu Liu, Yuwei Guo. MinEnt: Minimum entropy for self-supervised representation learning[J]. Pattern Recognition, vol.138, 109364, 2023.

[6] Shuo Li, Fang Liu*, Licheng Jiao, Xu Liu, Puhua Chen. Learning Salient Feature for Salient Object Detection Without Labels[J]. IEEE Transactions on Cybernetics, vol.53, no.2, pp. 1012-1025, 2023.

[7] Shuo Li, Fang Liu*, Zehua Hao, Kaibo Zhao, Licheng Jiao. Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space[C]. European Conference on Computer Vision, vol. 13691, pp. 420-436, 2022.

[8] Shuo Li, Fang Liu*, Licheng Jiao, Puhua Chen, Xu Liu, Liling Li. MFNet: A Novel GNN-Based Multi-Level Feature Network With Superpixel Priors[J]. IEEE Transactions on Image Processing, vol. 31, pp. 7306-7321, 2022.

[9] Shuo Li, Fang Liu*, Licheng Jiao. Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection[C]. AAAI Conference on Artificial Intelligence, vol. 36(2), pp. 1395-1403, 2022.

合作学术成果（*为通讯作者）：

[1] Yang Liu, Fang Liu*, Licheng Jiao, Qianyue Bao, Shuo Li, Lingling Li, Xu Liu. Knowledge-Driven Compositional action recognition[J]. Pattern Recognition, doi:10.1016/j.patcog.2025.111452, 2025. [NEW]

[2] Pengfang Li, Fang Liu*, Licheng Jiao, Shuo Li, Xu Liu, Puhua Chen, Lingling Li, Zehua Hao. LLM Knowledge-Driven Target Prototype Learning for Few-Shot Segmentation[J]. Knowledge-Based Systems, doi:10.1016/j.knosys.2025.113149, 2025. [NEW]

[3] Zehua Hao, Fang Liu*, Licheng Jiao, Yaoyang Du, Shuo Li, Hao Wang, Pengfang Li, Xu Liu, Puhua Chen. Preserving text space integrity for robust compositional zero-shot learning via mixture of pretrained experts[J]. Neurocomputing, doi: 10.1016/j.neucom.2024.128773, 2025. [NEW]

[4] Yaoyang Du, Fang Liu*, Licheng Jiao, Shuo Li, Zehua Hao, Pengfang Li, Jiahao Wang, Hao Wang, Xu Liu. Text generation and multi-modal knowledge transfer for few-shot object detection[J]. Pattern Recognition, doi: 10.1016/j.patcog.2024.111283, 2024. 

[5] Jiahao Wang, Fang Liu*, Licheng Jiao, Yingjia Gao, Hao Wang, Shuo Li, Lingling Li, Puhua Chen, Xu Liu. Visual and Language Collaborative Learning for RGBT Object Tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2024.3436878, 2024. 

[6] Jiahao Wang, Fang Liu*, Licheng Jiao, Hao Wang, Shuo Li, Lingling Li, Puhua Chen, Xu Liu. Multi-modal visual tracking based on textual generation[J]. Information Fusion, doi: 10.1016/j.inffus.2024.102531, 2024. 

[7] Yang Liu, Fang Liu*, Licheng Jiao, Qianyue Bao, Long Sun, Shuo Li, Lingling Li, Xu Liu. Multi-grained Gradual Inference Model for Multimedia Event Extraction[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[8] Hao Wang, Fang Liu*, Licheng Jiao, Jiahao Wang, Zehua Hao, Shuo Li, Lingling Li, Puhua Chen, Xu Liu. ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-guided Optimization [C]. AAAI Conference on Artificial Intelligence, 2024. 

[9] Jiahao Wang, Fang Liu*, Licheng Jiao, Yingjia Gao, Hao Wang, Lingling Li, Puhua Chen, Xu Liu, Shuo Li. Satellite Video Object Tracking based on Location Prompts[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[10] Yunpeng Li, Xiangrong Zhang, Tianyang Zhang*, Guanchun Wang, Xinlin Wang, Shuo Li. A Patch-Level Region-Aware Module with a Multi-Label Framework for Remote Sensing Image Captioning[J]. Remote Sensing, 2024.

[11] Nan Jia, Xiaolin Tian*, Ting Yang, Shuo Li, Licheng Jiao. Self-restrained contrastive enhanced network for graph structure learning[J]. Expert Systems with Applications, 2024.

[12] Pengfang Li, Fang Liu*, Licheng Jiao, Shuo Li, Lingling Li, Xu Liu, Xinyan Huang. Knowledge Transduction for Cross-Domain Few-Shot Learning[J]. Pattern Recognition, 2023.

[13] Xiaoxue Qian, Fang Liu*, Licheng Jiao, Xiangrong Zhang, Xinyan Huang, Shuo Li, Puhua Chen and Xu Liu. Knowledge transfer evolutionary search for lightweight neural architecture with dynamic inference[J]. Pattern Recognition, vol.143, 109790, 2023.

[14] Pengfang Li, Fang Liu*, Licheng Jiao, Lingling Li, Puhua Chen, Shuo Li. Task context transformer and GCN for few-shot learning of cross-domain[J]. Neurocomputing, vol.548, 2023.

[15] Yaoyang Du, Fang Liu*, Licheng Jiao, Zehua Hao, Shuo Li, Xu Liu, Jing Liu. Augmentative contrastive learning for one-shot object detection[J]. Neurocomputing, 513: 13-24, 2022.

荣誉奖励：

[1] 中国电子教育学会2024年度优秀博士学位论文提名奖，2024年；

[2] 陕西省优秀毕业生(博士)，2023年；

[3] 教育部博士研究生国家奖学金，2022年；

[4] 武汉大学优秀本科毕业生，2016年。

主讲课程：

[1] 离散数学，大一，2024年秋。

公共服务：

受邀担任ICML、CVPR、ICCV、ACM MM、NeurIPS、AAAI、ECCV、TNNLS、PR、TSP等会议和期刊的审稿人。