Zhensong Zhang （张镇嵩）
PhD (CUHK), MS (UCAS), BEng (Xidian)
Senior researcher
Huawei Noah's Ark Lab
Email: zhensongzhang[at]hotmail[dot]com
Biography
I joined Huawei Noah's Ark Lab after I obtained my Ph.D. degree from The Chinese University of Hong Kong in 2018. Before that, I received a BEng. degree and a M.S. degree from Xidian University and University of Chinese Academy of Sciences in 2011 and 2014, respectively. I am currently working on MLLM/AIGC/3DGS.
We are looking for self-motivated interns, if you are insterested in doing cool MLLM/AIGC/3DGS projects, welcome to join us, please drop me an email.
News
[02/2024] Three papers are accepted to CVPR 2024，congrats to all coauthors!
[12/2023] One paper is accepted to ICASSP 2024.
[10/2023] We won the Reproducibility Award in GENEA Challenge 2023.
[09/2023] Our work on robust monocular depth estimation is accepted to IJCV.
[07/2023] Our UnifiedGesture is accepted to ACM MM 2023.
[05/2023] Our DiffuseStyleGesture is accepted to IJCAI 2023.
[05/2023] Our QPGesture is accepted to CVPR 2023 as a highlight.
[11/2022] Our sign language avatar appears on HDC 2022 / HC 2022 and helps translate Chinese keynotes into CSL, 量子位, 华为人, 华为开发者联盟服务.
[10/2022] Our joint team Megatron_RVC won the RVC 2022 single image depth prediction challenge, news
[8/2022] Our human pose and shape estimation paper CLIFF is accepted to ECCV as oral presentation, news
Selected Publications （dblp, Google Scholar）
[CVPR] Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model
Xu He, Qiaochu Huang, Zhensong Zhang, Zhiwei Lin, Zhiyong Wu, Sicheng Yang, Minglei Li, Zhiyi Chen, Songcen Xu, Xiaofei Wu
In CVPR 2024.
[CVPR] Semantics-aware Motion Retargeting with Vision-Language Models
Haodong Zhang, Zhike Chen, Haocheng Xu, Lei Hao, Xiaofei Wu, Songcen Xu, Zhensong Zhang, Yue Wang, Rong Xiong
In CVPR 2024.
[CVPR] Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Youliang Yan, Zhensong Zhang, Lei Zhu
In CVPR 2024.
[Website]
[ICASSP] Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion, and Context with Diffusion Models
Haiwei Xue, Sicheng Yang, Zhensong Zhang, Zhiyong Wu, Minglei Li, Zonghong Dai, Helen Meng
In ICASSP 2024.
[IJCV] Towards A Unified Network for Robust Monocular Depth Estimation: Network Architecture, Training Strategy and Dataset
Mochu Xiang, Yuchao Dai, Feiyu Zhang, Jiawei Shi, Xinyu Tian, Zhensong Zhang
In IJCV.
[ICMI] The DiffuseStyleGesture+ Entry to the GENEA Challenge 2023
Sicheng Yang, Haiwei Xue, Zhensong Zhang, Minglei Li, Zhiyong Wu, Xiaofei Wu, Songcen Xu, Zonghong Dai
In ICMI 2023.
[Code] [Reproducibility Award]
[ACM MM] UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons
Sicheng Yang, Zilin Wang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Qiaochu Huang, Lei Hao, Songcen Xu, Xiaofei Wu, Changpeng Yang, Zonghong Dai
In ACM MM 2023.
[Code] [Demo] [presentation]
[IJCAI] DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models
Sicheng Yang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Lei Hao, Weihong Bao, Ming Cheng, Long Xiao
In IJCAI 2023.
[Code] [Demo]
[CVPR Highlight] QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation
Sicheng Yang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Lei Hao, Weihong Bao, Haolin Zhuang
In CVPR 2023.
[Code] [Demo] [presentation]
[ECCV Oral] CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
Zhihao Li, Jianzhuang Liu, Zhensong Zhang, Songcen Xu, Youliang Yan
In ECCV 2022.
[Code]
[TIP] Multi-View Video Synopsis via Simultaneous Object-Shifting and View-Switching Optimization
Zhensong Zhang, Yongwei Nie, Hanqiu Sun, Qing Zhang, Qiuxia Lai, Guiqing Li, Mingyu Xiao
In IEEE Transactions Image Processing, 2020.
[TIP] Video Synopsis Incorporating Object Speed and Size Changes
Yongwei Nie, Zhenkai Li, Zhensong Zhang, Qing Zhang, Tiezheng Ma, Hanqiu Sun
In IEEE Transactions Image Processing, 2020.
[TVCG] Effective Video Stabilization via Joint Trajectory Smoothing and Frame Warping
Tiezheng Ma, Yongwei Nie, Qing Zhang, Zhensong Zhang, Hanqiu Sun, Guiqing Li
In IEEE Transactions on Visualization and Computer Graphics, 2020.
[TCSVT] Interactive Contour Extraction via Sketch-Alike Dense-Validation Optimization
Yongwei Nie, Xu Cao, Ping Li, Qing Zhang, Zhensong Zhang, Guiqing Li, Hanqiu Sun
In IEEE Transactions on Circuits Systems for Video Technology, 2020
[TIP] Dynamic Video Stitching via Shakiness Removing
Yongwei Nie, Tan Su, Zhensong Zhang, Hanqiu Sun and Guiqing Li
In IEEE Transactions on Image Processing, 2018.
[Code] [Demo]
[TVCG] Homography Propagation and Optimization for Wide-Baseline Street Image Interpolation
Yongwei Nie, Zhensong Zhang, Hanqiu Sun, Tan Su and Guiqing Li
In IEEE Transactions on Visualization and Computer Graphics, 2017.
[Code] [Demo]
[ICDE] A Novel Fast and Memory Efficient Parallel MLCS Algorithm for Long and Large-Scale Sequences Alignments
Yanni Li, Yuping Wang, Zhensong Zhang, Yaxin Wang, Ding Ma, Jianbin Huang
In the Proceedings of the 32nd IEEE International Conference on Data Engineering, Helsinki, Finland, 2016.
[IUI] Left and Right Hand Distinction for Multi-Touch Tabletop Interactions
Zhensong Zhang, Fengjun Zhang, Hui Chen, Jiasheng Liu, Hongan Wang and Guozhong Dai
In the Proceedings of the 19th international conference on Intelligent User Interfaces, Haifa, Israel, 2014.
Honors & Awards
Winner, ECCV 2022 RVC monoculer depth estimation prediction challenge