Yachao Zhang(张亚超)

🌈 I am a postdoctoral researcher at the Intelligent Computing Lab, SIGS of Tsinghua University, working with Prof. Xiu Li (李秀教授). Previously, I did my Ph.D. from September 2018 to June 2022 at the School of Informatics, at Xiamen University, China, supervised by Professor Cuihua Li (李翠华教授) and co-supervised by Professor Yanyun Qu (曲延云教授). I received the M.S. degree in Control Theory and Control Engineering from Lanzhou University of Technology, China, in 2018, supervised by Professor Ce Li (李策教授).

🏳️‍🌈 My research interests include, but are not limited to: Computer Vision (3D computer vision, point cloud semantic segmentation), Machine Learning (weakly-supervised learning, unsupervised learning, transfer learning). Recently, I also focus on digital human avatar, including 3D human pose reconstruction, multimodality-driven 3D human motion generation. If you are interested in my research or have any use cases that you want to share, feel free to contact me!


News滚动展示

✍News

  • [Sep 2024] Three papers about multi-modal learning are accepted by NeurIPS 2024!
  • [Aug 2024] Three papers about multi-modal learning are accepted by ACMMM 2024!
  • [Jul 2024] One paper about multi-modal label efficient learning is accepted by ECCV 2024!
  • [Jun 2024] One paper about Object Detection is accepted by TNNLS!
  • [Feb 2024] One paper about AI ChoreoMaster is accepted by CVPR 2024!
  • [Jan 2024] One papers about about camouflaged object detection is accepted by ICLR 2024!
  • [Dec 2023] Three papers about digital human avatar and cross-modal zero-shot learning are accepted by ICASSP 2024!
  • [Dec 2023] Two papers about multi-modal understanding and multi-modal gestures generation are accepted by AAAI 2024!
  • [Oct 2023] Our paper about Semi-Supervised Defect Segmentation is accepted by TNNLS!
  • [Sep 2023] One paper about weakly supervised learning is accepted by NeurIPS 2023!
  • [Aug 2023] My application of the National Natural Science Foundation of China is approved!
  • [Jul 2023] One paper about multi-modal unsupervised domain adaptation semantic segmentation is accepted by ACMMM 2023!
  • [Jul 2023] Four papers about multi-modal learning, ANN2SNN, and AI ChoreoMaster are accepted by ICCV 2023!
  • [Jun 2023] My application of the China Postdoctoral Science Foundation is approved!
  • [Apr 2023] One paper about zero-shot learning is accepted by IJCAI 2023!
  • [Mar 2023] One paper about camouflaged object detection is accepted by CVPR 2023!
  • [Feb 2023] One paper about long-tailed learning is accepted by ICASSP 2023!
  • [Nov 2022] One paper about weakly-supervised point cloud semantic segmentation is accepted by AAAI 2023!
  • [Aug 2022] One paper about binary multi-view cluster is accepted by TNNLS!
  • [Jul 2022] Two papers about multi-modal unsupervised domain adaptation semantic segmentation are accepted by ACMMM 2022!
  • [Jun 2022] I am the winner of the title of "Outstanding Graduate" of Xiamen University!
  • [Jun 2022] I successfully defended my PhD thesis!
  • [Mar 2022] I am the winner of Xiamen University Liu Yubin Youth Science and Technology Scholarship!
  • [Nov 2021] I am the winner of the title of "Outstanding Student" of Xiamen University!
  • [Dec 2021] I am the winner of the first prize of the 2021 Excellent Paper Award of Fujian Computer Society!
  • [Jul 2021] One paper about weakly-supervised point cloud semantic segmentation is accepted by ICCV 2021!
  • [Mar 2021] One paper about PolSAR Image Classification is accepted by Remote Sensing!
  • [Dec 2020] One paper about weakly-supervised large scale point cloud semantic segmentation is accepted by AAAI 2021!

📚Selected Publications (1️⃣ Equal contribution, 📧 Corresponding author)

UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
Yao Wu, Mingwei Xing, Yachao Zhang📧, Xiaotong Luo, Yuan Xie, Yanyun Qu📧
Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[Paper][Code]
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
Zunnan Xu, Yukang Lin,Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang📧,Xiu Li📧.
Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[Paper]
Consistent123: One image to highly consistent 3d asset using case-aware diffusion priors
Yukang Lin,Haonan Han, Chaoqun Gong, Zunnan Xu, Yachao Zhang📧,Xiu Li📧.
ACM International Conference on Multimedia (ACMMM 2024)
[Paper][Project]
Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control
Zunnan Xu,Yachao Zhang📧,Sicheng Yang,Ronghui Li,Xiu Li📧.
Association for the Advance of Artificial Intelligence (AAAI 2024)
[Paper][Code coming soon!]
Cross-Modal Match for Language Conditioned 3D Object Grounding
Yachao Zhang, Runze Hu, Ronghui Li, Yanyun Qu, Yuan Xie, Xiu Li📧.
Association for the Advance of Artificial Intelligence (AAAI 2024)
[Paper][Code coming soon!]
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification
Jiangming Shi1️⃣, Yachao Zhang1️⃣, Xiangbo Yin, Yuan Xie, Zhizhong Zhang, Jianping Fan, zhongchao shi, Yanyun Qu.
IEEE/CVF International Conference on Computer Vision (ICCV 2023)
[Paper][Code]
Efficient Converted Spiking Neural Network for 3D and 2D Classification
Yuxiang Lan, Yachao Zhang 📧, Xu Ma, Yanyun Qu, Yun Fu.
IEEE/CVF International Conference on Computer Vision (ICCV 2023)
[Paper]
BEV-DG: Cross-Modal Learning under Bird’s-Eye View for Domain Generalization of 3D Semantic Segmentation
Miaoyu Li, Yachao Zhang 📧, Xu Ma, Yanyun Qu, Yun Fu.
IEEE/CVF International Conference on Computer Vision (ICCV 2023)
[Paper]
Weakly Supervised 3D Segmentation via Receptive-driven Pseudo Label Consistency and Structural Consistency
Yuxiang Lan1️⃣, Yachao Zhang1️⃣, Yanyun Qu, Cong Wang, Yuan Xie, Zongze Wu.
Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023)
[Paper][Code]
VS-Boost: Boosting Visual-Semantic Association for Generalized Zero-Shot Learning
Xiaofan Li, Yachao Zhang 📧, Shiran Bian, Yanyun Qu, Yuan Xie, Zhongchao Shi, Jianping Fan.
International Joint Conference on Artificial Intelligence (IJCAI 2023)
[Paper]
Cross-Domain and Cross-Modal Knowledge Distillation in Domain Adaptation for 3D Semantic Segmentation
Miaoyu Li1️⃣,Yachao Zhang1️⃣,Miaoyu Li, Yuan Xie, Zhizhong Zhang, Cuihua Li, Yanyun Qu.
ACM International Conference on Multimedia (ACMMM 2022)
[Paper][Code]
Learning All-In Collaborative Multiview Binary Representation for Clustering
Yachao Zhang, Yuan Xie, Zongze Wu, Cuihua Li, Yanyun Qu.
Transactions on Neural Networks and Learning Systems (TNNLS 2022)
[Paper][Code]
SSE-xMUDA: Self-supervised Exclusive Learning for 3D Segmentation in Cross-Modal Unsupervised Domain Adaptation
Yachao Zhang,Miaoyu Li, Yuan Xie, Zhizhong Zhang, Cuihua Li, Yanyun Qu.
ACM International Conference on Multimedia (ACMMM 2022)
[Paper][Code]
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
Yachao Zhang, Yanyun Qu, Zhonghao Li, Shanshan Zheng, Cuihua Li.
IEEE Conference on International Conference on Computer Vision (ICCV 2021)
[Paper][Code]
Weakly supervised semantic segmentation for large-scale point cloud
Yachao Zhang, Zonghao Li, Yuan Xie, Yanyun Qu, Cuihua Li, Tao Mei.
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021)
[Paper][Code]

[Please visit my google scholar profile for the full publication list.] ___________________________________

📠Academic Services

  • Conference Reviewer: CVPR, ICML, NeurIPS, AAAI, ICCV, ACMMM, ICLR
  • Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Artificial Intelligence, IEEE Transactions on Image Processing

✨Hobby