Chaoxu Guo (郭超旭)

About Me

I am an algorithm engineer in TikTok currently, focus on content understanding/generation x recommendation, image and video generation. Previously I worked in Alimama, Alibaba Group, working on personal creative recommendation, creation of advertisement creatives, especially in types of videos. I received my master degree from National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Science in 2020. Before that, I received my bachelor degree in South China University of Technology (SCUT) in 2017.

My research interests focus on content understanding/generation x recommendation, large language model.

News

• We release PV-RCNN++!
• We release a new point cloud based object detction codebase OpenPCDet! OpenPCDet contains multiple SOTA models including SECOND, PointPillar, PartA^2 and PV-RCNN. New models are on our plan.
• We win the 1st place among all lidar-only methods on three tasks of 3D Object Detection, 3D Object Tracking and 3D Domain Adaption in Waymo Open Challenge!
• Two papers are accepted by CVPR2020!
• One paper is accepted by ICCV2019!
• We win the 3rd place on Instance Segmentation, 2nd place on Panoptic Segmentation in MS COCO2018! Our team is invited to ECCV2018 to give a talk.

Publications

• Hierarchical masked 3d diffusion model for video outpainting
  Fanda Fan, Chaoxu Guo, Litong Gong, Biao Wang, Tiezheng Ge, Yuning Jiang, Chunjie Luo, Jianfeng Zhan
  ACM Multimedia 2023
• Estimation of Reliable Proposal Quality for Temporal Action Detection
  Junshan Hu, Chaoxu Guo, Liansheng Zhuang, Biao Wang, Tiezheng Ge, Yuning Jiang, Houqiang Li
  ACM Multimedia 2022
• PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
  Shaoshuai Shi, Li Jiang, Jiajun Deng, Zhe Wang, Chaoxu Guo, Jianping Shi, Xiaogang Wang, Hongsheng Li
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
  Chaoxu Guo, Bin Fan, Qian Zhang, Shiming Xiang, Chunhong Pan
  CVPR2020 code
• PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
  ShaoShuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li
  CVPR2020 code
• Progressive Sparse Local Attention for Video Object Detection
  Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Veronique Prinet, Chunhong Pan
  ICCV2019
• Video Object Detection with Locally-Weightd Deformable Neighboors
  Zhengkai Jiang, Peng Gao, Chaoxu Guo, Qian Zhang, Shiming Xiang, and Chunhong Pan
  AAAI2019
• Pseudo low rank video representation
  Tingzhao Yu, Lingfeng Wang, Chaoxu Guo, Huxiang Gu, Shiming Xiang, Chunhong Pan
  Pattern Recognition, 2019
• Mgn: Multi-Glimpse Network for Action Recognition.
  Chaoxu Guo, Tingzhao Yu, Huxiang Gu, Shiming Xiang, Chunhong Pan, ICASSP 2018

CodeBase

OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Cloud
AugFPN: Improving Multi-scale Feature Learning for Object Detection

Competition

Rank 1st among all LiDAR-only methods on three challenge of 3D Detection, 3D Tracking, Domain Adaptation in Waymo Open Dataset Challenge
Rank 2rd in MS COCO 2018 Paoptic Segmentation Track
Rank 3rd in MS COCO 2018 Instance Segmentation Track

Contact

Google Scholar: google scholar
Email: gus_guo@outlook.com
WechatName: Gus_Guo