I'm a PhD student at School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), under the supervision of  Prof. Lianli Gao  and  Prof. Jingkuan Song. I obtained my Master degree in Computer Science from UESTC in 2017, under the supervision of  Prof. Lianli Gao.  I received my BS degree in Software Engineering from UESTC, in 2014. 

My research interest includes large-scale human-centric recognition, such as human pose estimation, human surface understanding, human action recognition, and the related practical applications etc.  Specifically, I am mainly focusing on human pose estimation for Human-centric Visual Content Understanding. 

Recent News

• [2022/09/22] 1 paper accepted by TCYB 2022
• [2022/07/11] 1 paper accepted by ACM MM 2022
• [2022/06/11] 1 paper accepted by TCSVT 2022
• [2021/12/03] 1 paper accepted by TMM 2021

Working Experience

• PhD Student, School of Computer Science and Engineering, UESTC, 2019.09-Present
• Algorithm Engineer, Institute of HIKVISION Research, HIKVISION, 2017-2019

Introduction to my recent researches

Applications to real-world scenes

Publications

• Xuanhan Wang, Jingkuan Song, Xiaojia Chen, Lechao Cheng, Lianli Gao, Heng Tao Shen: KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing. IEEE Trans. Cybernetics (2022) [code] [Paper]
• Xuanhan Wang, Yan Dai, Lianli Gao, Jingkuan Song: Skeleton-based Action Recognition via Adaptive Cross-Form Learning. ACM Multimedia 2022 [code] [Paper]
• Xuanhan Wang, Lianli Gao, Yixuan Zhou, Jingkuan Song, Meng Wang: KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences. IEEE Trans. Circuits and Systems for Video Technology (2022) [code] [Paper]
• Xuanhan Wang, Lianli Gao, Jingkuan Song, Yuyu Guo, Heng Tao Shen: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences. IEEE Trans. Multimedia (2021) [code] [Paper]
• Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, Jingkuan Song: From General to Specific: Informative Scene Graph Generation via Balance Adjustment. ICCV 2021 [code] [Paper]
• Xuanhan Wang, Lianli Gao, Yan Dai, Yixuan Zhou, Jingkuan Song: Semantic-aware Transfer with Instance-adaptive Parsing for Crowded Scenes Pose Estimation. ACM Multimedia 2021 [code] [Paper]
• Yan Dai, Xuanhan Wang, Jingkuan Song, Lianli Gao, Heng Tao Shen: RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation. AAAI 2021 [code] [Paper]
• Xuanhan Wang, Lianli Gao, Jingkuan Song, Heng Tao Shen: KTN: Knowledge Transfer Network for Multi-person DensePose Estimation. ACM Multimedia 2020 [code] [Paper]
• Lianli Gao, Xuanhan Wang, Jingkuan Song, Yang Liu: Fused GRU with semantic-temporal attention for video captioning. Neurocomputing 395: 222-228 [code] [Paper]
• Xiangpeng Li, Lianli Gao, Xuanhan Wang, Wu Liu, Xing Xu, Heng Tao Shen, Jingkuan Song: Learnable Aggregating Net with Diversity Learning for Video Question Answering. ACM Multimedia 2019: 1166-1174 [code] [Paper]
• Yuyu Guo, Lianli Gao, Jingkuan Song, Peng Wang, Wuyuan Xie, Heng Tao Shen: Adaptive Multi-Path Aggregation for Human DensePose Estimation in the Wild. ACM Multimedia 2019: 356-364 [code] [Paper]
• Xuanhan Wang, Lianli Gao, Jingkuan Song, Xiantong Zhen, Nicu Sebe, Heng Tao Shen: Deep appearance and motion learning for egocentric activity recognition. Neurocomputing 275: 438-447 (2018) [paper]
• Xuanhan Wang, Lianli Gao, Peng Wang, Xiaoshuai Sun, Xianglong Liu: Two-Stream 3-D convNet Fusion for Action Recognition in Videos With Arbitrary Size and Length. IEEE Trans. Multimedia 20(3): 634-644 (2018) [paper]
• Xuanhan Wang, Lianli Gao, Jingkuan Song, Heng Tao Shen: Beyond Frame-level CNN: Saliency-Aware 3-D CNN With LSTM for Video Action Recognition. IEEE Signal Process. Lett. 24(4): 510-514 (2017) [paper]