Dongdong Yu

I am a Researcher in the Visual Computing Team at ByteDance AI Lab. My research interests focus on the computer vision and artificical intelligence, specifically on the topic of image classification, human keypoint, and scene parsing. I obtained PhD from CASIA in 2017 supervised by Prof. Ruwei Dai and Prof. Jie Tian.

Email: yudongdongatcasia@gmail.com; yudongdong@bytedance.com

Google Scholar / CV

[2021.12] Our paper "AdaptivePose: Human Parts as Adaptive Points" has been accepted by AAAI2022. (AAAI 2022).

[2021.12] Our paper "Learning Quality-aware Representation for Multi-person Pose Regression" has been accepted by AAAI2022. (AAAI 2022).

[2021.09] Our team (CharlesBLWX) obtained the 2nd place of The 1st Video Scene Parsing in the Wild Challenge Workshop .(ICCVW 2021).

[2021.07] Our paper "Mining Contextual Information Beyond Image for Semantic Segmentation" has been accepted by ICCV2021. (ICCV 2021).

[2021.07] Our paper "Weakly Supervised Person Search with Region Siamese Networks" has been accepted by ICCV2021. (ICCV 2021).

[2021.03] Our paper "Body Meshes as Points" has been accepted by CVPR2021. (CVPR 2021).

[2020.12] Our paper "F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation" has been accepted by AAAI2021. (AAAI 2021).

[2020.01] Our paper "SPCNet: Spatial Preserve and Content-aware Network for Human Pose Estimation" has been accepted by IEEE ECAI2020. (ECAI 2020).

[2019.11] Our team (ByteDanceVC) obtained the 2nd place of COCO Keypoint Detection in the COCO + Mapillary Joint Challenge.(ICCV 2019).

[2019.09] Our team (youtube_test) obtained the 5th place of Video Object Segmentation in the 2nd Large-scale Video Object Segmentation Challenge.(ICCV 2019).

[2019.09] Our team (mingmingdiii) obtained the 5th place of Video Instance Segmentation in the 2nd Large-scale Video Object Segmentation Challenge.(ICCV 2019).

[2019.06] Our team (ByteDance-SEU) obtained the 1st place of Single-Person Human Pose Estimation Track in the Visual Understanding of Humans in Crowd Scene and the 3rd Look Into Person (LIP) Challenge.(CVPR 2019).

[2019.06] Our team (ByteDance-SEU) obtained the 2nd place of Single-Person Human Parsing Track in the Visual Understanding of Humans in Crowd Scene and the 3rd Look Into Person (LIP) Challenge.(CVPR 2019).

[2019.03] Our paper "Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information" has been accepted by IEEE CVPR2019. (CVPR 2019).

[2019.01] Our paper "Predicting EGFR Mutation Status in Lung Adenocarcinoma on CT Image Using Deep Learning" has been accepted by European Respiratory Journal (which is the flagship journal of the European Respiratory Society, the current impact factor 12.242). (ERJ 2019).

[2018.09] Our team (ByteDance-SEU) obtained the 5th place of COCO Keypoint Detection in the COCO + Mapillary Joint Challenge.(ECCV 2018).

[2018.09] Our team (Miracle) obtained the 5th place of Multi-Person Pose Estimation in the PoseTrack Challenge.(ECCV 2018).

[2018.09] Our team (Miracle) obtained the 3rd place of Multi-Person Pose Tracking in the PoseTrack Challenge.(ECCV 2018).

[2018.05] Our team (ByteDance-SEU) obtained the 2nd place of Single-Person Human Pose Estimation Track in the Visual Understanding of Humans in Crowd Scene and the 2nd Look Into Person (LIP) Challenge.(CVPR 2018).

[2018.05] Our team (TeamVia) obtained the 8th place of Semi-Supervised Video Segmentation in the DAVIS Challenge on Video Object Segmentation.(CVPR 2018).

[2017.04] I serve as a reviewer of IEEE Journal of Biomedical and Health Informatics(IF=3.850).

[2016.04] I worked as a Visiting Student Researcher at Stanford University.

F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation [PDF]
Daizong Liu†, Dongdong Yu†, Changhu Wang, Pan Zhou.
AAAI, 2021

SPCNet: Spatial Preserve and Content-aware Network for Human Pose Estimation [PDF]
Yabo Xiao, Dongdong Yu, Xiaojuan Wang, Tianqi Lv, Yiqi Fan, Lei Jin.
ECAI, 2020

A Context-and-Spatial Aware Network for Multi-Person Pose Estimation [PDF]
Dongdong Yu, Kai Su, Xin Geng, Changhu Wang.
Arxiv, 2019

Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information [PDF]
Kai Su†, Dongdong Yu†, Zhenqi Xu, Xin Geng, Changhu Wang.
CVPR, 2019

Multi-person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network [PDF]
Dongdong Yu†, Kai Su†, Jia Sun, Changhu Wang.
ECCVW, 2018

Mask Propagation Network for Video Object Segmentation [PDF]
Jia Sun†, Dongdong Yu†, Yinghong Li, Changhu Wang.
CVPRW, 2018

Convolutional Neural Networks for Predicting Molecular Profiles of Non-small Cell Lung Cancer [PDF]
Dongdong Yu, Mu Zhou, Feng Yang, Di Dong, Olivier Gevaert, Zaiyi Liu, Jingyun Shi, Jie Tian.
ISBI, 2017

Developing a Radiomics Framework for Classifying Non-small Cell Lung Carcinoma Subtypes [PDF]
Dongdong Yu, Yali Zang, Di Dong, Mu Zhou, Olivier Gevaert, Mengjie Fang, Jingyun Shi, Jie Tian.
SPIEMI, 2017

A New Region Descriptor for Multi-modal Medical Image Registration and Region Detection [PDF]
Xiaonan Wan, Dongdong Yu, Feng Yang, Caiyun Yang, Chengcai Leng, Min Xu, Jie Tian.
EMBC, 2015

Using Biparametric MRI Radiomics Signature to Differentiate between Benign and Malignant Prostate Lesions [PDF]
Min Xu, Mengjie Fang, Jian Zou, Shudong Yang, Dongdong Yu, Lianzhen Zhong, Chaoen Hu, Yali Zang, Di Dong, Jie Tian, Xiangming Fang
European Journal of Radiology, 2019

Predicting EGFR Mutation Status in Lung Adenocarcinoma on CT Image Using Deep Learning [PDF]
Shuo Wang†, Jingyun Shi†, Zhaoxiang Ye†, Di Dong†, Dongdong Yu†, Mu Zhou†, Ying Liu, Olivier Gevaert, Kun Wang, Yongbei Zhu, Hongyu Zhou, Zhenyu Liu, Jie Tian
European Respiratory Journal, 2019

Multi-crop Convolutional Neural Networks for Lung Nodule Malignancy Suspiciousness Classification [PDF]
Wei Shen, Mu Zhou, Feng Yang, Dongdong Yu, Di Dong, Caiyun Yang, Yali Zang, Jie Tian.
Pattern Recognition, Volume 61, Pages 663-673, 2017

Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization [PDF]
Dongdong Yu, Feng Yang, Caiyun Yang, Chengcai Leng, Jian Cao, Yining Wang, Jie Tian.
IEEE Transactions on Biomedical Engineering, Volume 63, Pages 1653-1664, 2016

Radiomic Signature as a Diagnostic Factor for Histologic Subtype Classification of Non-small Cell Lung Cancer [PDF]
Xinzhong Zhu, Di Dong, Zhendong Chen, Mengjie Fang, Liwen Zhang, Jiangdian Song, Dongdong Yu, Yali Zang, Zhenyu Liu, Jingyun Shi, Jie Tian.
European Radiology, Volume 28, Issue 7, Pages 2772-2778, 2018

Identifying the White Matter Impairments among ART-naïve HIV Patients: a Multivariate Pattern Analysis of DTI Data [PDF]
Zhenchao Tang, Zhenyu Liu, Ruili Li, Xin Yang, Xingwei Cui, Shuo Wang, Dongdong Yu, Hongjun Li, Enqing Dong, Jie Tian.
European Radiology, Volume 27, Issue 10, Pages 4153-4162, 2016

Adaptive Total-Variation for Non-Negative Matrix Factorization on Manifold [PDF]
Chengcai Leng, Guorong Cai, Dongdong Yu, Zongyue Wang.
Pattern Recognition Letters, Volume 98, Pages 68-74, 2017

Reconstruction Method for Optical Tomography Based on the Linearized Bregman Iteration with Sparse Regularization [PDF]
Chengcai Leng, Dongdong Yu, Shuang Zhang, Yu An, Yifang Hu.
Computational and Mathematical Methods in Medicine, Volume 2015, Article ID 304191, 8 pages, 2015

My Github: Dongdong Yu (喻冬东)

友情链接: Kai Su (苏凯), Changhu Wang (王长虎)