I am a Research Fellow at S-Lab, Nanyang Technological University (NTU), Singapore, working with Prof. Cheng Long. I also work closely with Prof. Guosheng Lin from NTU, and Prof. Ziyue Li from University of Cologne. I received my Ph.D degree from NTU, Singapore, supervised by Prof. Cheng Long. I received my B.S. degree in Software Engineering (Chinese-Foreign Cooperation Program) from Nanjing University of Information Science and Technology (NUIST), Nanjing, China, in 2020, and B.S. (Honours) degree in Software Systems Practice Year 1 (NFQ Level 8 Honours Degree) from South East Technological University (SETU), Ireland, in 2020.

My research directions include Computer Vision and Spatio-Temporal Data Mining. Currently, most of my works are related to Image Segmentation (e.g., Few-Shot Segmentation and Remote Sensing), and Time Series Analysis (e.g., Forecasting, Imputation and Kriging).

I am always open to research collaborations. Please feel free to drop me an email if you are interested.

Publications (Selected)

(^* corresponding author)

Conference Papers

• [WSDM’25] Qiuyu Zhu, Liang Zhang, Qianxiong Xu, Kaijun Liu, Cheng Long, Xiaoyang Wang. HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning. [Paper]
• [NIPS’24] Qianxiong Xu, Xuanyi Liu, Lanyun Zhu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao. Hybrid Mamba for Few-Shot Segmentation. [Paper][Code]
• [ECCV’24] Qianxiong Xu, Guosheng Lin, Chen Change Loy, Cheng Long, Ziyue Li, Rui Zhao. Eliminating Feature Ambiguity for Few-Shot Segmentation. [Paper][Code]
• [MDM’24] Chenxi Liu, Yang Sun, Qianxiong Xu, Zhishuai Li, Cheng Long, Ziyue Li, Rui Zhao. Spatial-Temporal Large Language Model for Traffic Prediction. [Paper][Code]
• [ICCV’23] Qianxiong Xu, Wenting Zhao, Guosheng Lin, Cheng Long. Self-Calibrated Cross Attention Network for Few-Shot Segmentation. [Paper][Code]
• [MDM’23] Kaijun Liu, Sijie Ruan, Qianxiong Xu, Cheng Long, Nan Xiao, Nan Hu, Liang Yu, Sinno Jialin Pan. Modeling Trajectories with Multi-task Learning. [Paper]
• [CIKM’22] Qianxiong Xu, Sijie Ruan, Cheng Long, Liang Yu, Chen Zhang. Traffic Speed Imputation with Spatio-Temporal Attentions and Cycle-Perceptual Training. [Paper][Code]
• [IEEE Cloud’19] Qianxiong Xu, Yu Zheng. A Survey of Image Super Resolution based on CNN. [Paper]

Journal Papers

• [TGRS’23] Qianxiong Xu, Cheng Long, Liang Yu, Chen Zhang. Road Extraction With Satellite Images and Partial Road Maps. [Paper][Code]

Preprint Papers

• Qianxiong Xu, Cheng Long, Ziyue Li, Sijie Ruan, Rui Zhao, Zhishuai Li. KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy. [Paper][Code]
• Chenxi Liu, Qianxiong Xu^*, Hao Miao, Yang Sun, Lingzheng Zhang, Cheng Long, Ziyue Li, Rui Zhao. TimeCMA: Towards LLM-Empowered Time Series Forecasting via Cross-Modality Alignment. [Paper]

Service

• Conference Reviewer: NeurIPS, ICLR, KDD, ICDE, VLDB, CIKM, PAKDD, SIGSPATIAL, WebConf
• Journal Reviewer: TPAMI, TCSVT, GRSL