avatar

Chaohui Yu (于超辉)

DAMO Academy, Alibaba Group

About Me

I'm an algorithm engineer at DAMO Academy, Alibaba Group. Before this, I got my Master degree and Bachelor degree from Institute of Computing Technology (ICT) and Shandong University in 2020 and 2017, respectively. My research interest includes: Transfer Learning, Object Detection/Segmentation, Semi/Self-supervised Learning, Multimodal Learning, image/video/3D/4D Generation, and related applications.

News
[Oct. 2024]

Two papers accepted to NeurIPS 2024!

[July 2024]

Three papers accepted to ECCV 2024!

Academic Service
[Conference Reviewer]

CVPR, ICCV, ECCV, ACM MM, AAAI

[Journal Reviewer]

TCSVT, JCST

Education & Experiences
DAMO Academy, Alibaba Group
Beijing, China
July 2020 – Current
Algorithm Expert at DAMO Academy
Institute of Computing Technology (ICT), Chinese Academy of Sciences
Beijing, China.
Sep. 2017 – Jun. 2020
M.S. in Computer Science.
DAMO Academy, Alibaba Group
Beijing, China
Jun. 2019 – Sep. 2019
Algorithm intern at Mind.
Face++
Beijing, China
Mar. 2018 – Dec. 2018
Algorithm intern at Detection Group.
DeepGlint
Beijing, China
Oct. 2016 – Feb. 2017
Algorithm intern at Algorithm Group.
Intel
Beijing, China
July 2016 – Oct. 2016
Development intern at Linux Kernel Dev and Test Group.
Shandong University
Shandong, China
Sep. 2013 – Jun. 2017
B.E. in Communication Engineering
Recent Publications
animate3d.png

Animate3D: Animating Any 3D Model with Multi-view Video Diffusion

Yanqin Jiang*, Chaohui Yu*, Chenjie Cao, Fan Wang, Weiming Hu, Jin Gao.

Neural Information Processing Systems. (NeurIPS-24)

[PDF] [Project Page]
mvinpainter.png

MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

Chenjie Cao, Chaohui Yu, Yanwei Fu, Fan Wang, Xiangyang Xue.

Neural Information Processing Systems. (NeurIPS-24)

[PDF] [Project Page]
SC4D.png

SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer

Zijie Wu, Chaohui Yu, Yanqin Jiang, Chenjie Cao, Fan Wang, Xiang Bai.

European Conference on Computer Vision. (ECCV-24)

[PDF] [Project Page]
vec-texture.png

VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing

Shang Liu, Chaohui Yu, Chenjie Cao, Wen Qian, Fan Wang

European Conference on Computer Vision. (ECCV-24)

[PDF]
meshsegmenter.png

MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis

Ziming Zhong, Yanxu Xu, Jing Li, Jiale Xu, Zhengxin Li, Chaohui Yu, Shenghua Gao

European Conference on Computer Vision. (ECCV-24)

[PDF] [CODE]
points-to-3d.png

Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation

Chaohui Yu, Qiang Zhou, Jingliang Li, Zhe Zhang, Zhibin Wang, Fan Wang

The 31th ACM International Conference on Multimedia. (ACMMM-23)

[PDF]
regionblip.png

RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension

Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibin Wang, Fan Wang

Preprint

[PDF]
fmwiss.png

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

Chaohui Yu, Qiang Zhou, Jingliang Li, Jianlong Yuan, Zhibin Wang, Fan Wang

The Conference on Computer Vision and Pattern Recognition (CVPR-23)

[PDF]
lmseg.png

LMSeg: Language-guided Multi-dataset Segmentation

Qiang Zhou, Yuang Liu, Chaohui Yu, Jingliang Li, Zhibin Wang, Fan Wang

The International Conference on Learning Representations 2023. (ICLR-23)

[PDF]
mimco.png

MimCo: Masked Image Modeling Pre-training with Contrastive Teacher

Qiang Zhou, Chaohui Yu, Hao Luo, Zhibin Wang, Hao Li

The 30th ACM International Conference on Multimedia. (ACMMM-22)

[PDF]
pss.png

Object Detection Made Simpler by Eliminating Heuristic NMS

Qiang Zhou*, Chaohui Yu*, Chunhua Shen*, Zhibin Wang, Hao Li

IEEE Transactions on Multimedia (TMM-23)

[PDF]
instantteaching.png

Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Qiang Zhou, Chaohui Yu, Zhibin Wang, Qi Qian, Hao Li

The Conference on Computer Vision and Pattern Recognition (CVPR-21)

[PDF] [CODE]
daan.png

Transfer Learning with Dynamic Adversarial Adaptation Network

Chaohui Yu, Jindong Wang, Yiqiang Chen, Meiyu Huang

Proceedings of IEEE International Conference on Data Mining (ICDM-19)

[PDF] [CODE]
Awards & Scholarships
First place of LUAI Challenge on Learning to Understand Aerial Images, ICCV Workshop 2021. [] [] [LINK]
National Scholarship for Master students, Ministry of Education 2019.
Best Application Paper Award. IJCAI-19 Federated Machine Learning Workshop 2019. [LINK]
Skills
Coding: Python, C++, Shell, Java, QT
Tools: Linux, Latex, Git, Vim, Docker, Mesos, Scrapy, Webpy