Xiaoqing Ye

Serving as a Researcher & Developer in Department of Computer Vision Technology (VIS). Baidu Inc.

My google scholar page: [Google scholar]

---

About Me

I am now working at Baidu VIS as an Reseacher & Developer.
My research interest is 3D vision, including 3D object detection (monocular/BEV/lidar/stereo), NeRF, depth estimation, point cloud semantic segmentation, 6DoF pose estimation, and human motion capture, especially for Autonomous Driving and AIGC. I received my B.E degree from Wuhan University in 2014 and my Ph.D. degree from the Chinese Academy of Sciences in 2019.

---

Recent Acitivities

• 1 Paper accepted by NeurIPS 2023!
• 3 Papers accepted by ICCV 2023!
• Our NeRF paper received an Oral in ICCV23!
• 4 Papers accepted by CVPR 2023!
• 1 Paper accepted by ICRA 2023!
• 1 Paper accepted by AAAI 2023!
• 1 Paper accepted by NeurIPS 2022.
• 1 Paper accepted by ACCV 2022 as oral.
• 1 Paper accepted by ECCV2022!
• Won the Champion both in the Pitch Localization and Camera Calibration Track in SoccerNet Challenge (CVPR2022)!
• 2 Papers accepted by ACM MM 2022.
• 1 Paper accepted by KDD 2022 as oral.
• 2 Papers accepted by CVPR 2022.
• 1 Paper accepted by AAAI 2022.
• 2 Papers accepted by ICCV 2021.
• 1 paper accepted by TPAMI 2021.
• 4 Papers accepted by ACM MM 2021.
• 1 Paper accepted by CVPR 2021.
• Won the Champion in ROD Challenge!
• 1 workshop paper accepted by ICMR 2021.
• 1 Paper accepted by ECCV 2020.
• 1 Paper accepted by CVPR 2020.
• 1 Paper accepted by AAAI 2020 as oral!
• Won the Champion in AI City Challenge 2020 Track 1.
• Won the Champion in AI City Challenge 2019 ReID Track.
• 1 Paper accepted by IROS 2020.
• 1 Paper accepted by ICCV 2019.
• 1 Paper accepted by ECCV 2018.

---

Publications

*: co-first author

[2023]

• Forward Flow for Novel View Synthesis of Dynamic Scenes. ICCV 2023. Oral. [PDF][Code]
  • Xiang Guo, Jiadai Sun, Yuchao Dai, Guanying Chen, Xiaoqing Ye, Xiao Tan, Errui Ding, Yumeng Zhang, Jingdong Wang.
• Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes. Technical report. [PDF] [Code]
  • Jiang-Tian Zhai, Ze Feng, Jinhao Du, Yongqiang Mao, Jiang-Jiang Liu, Zichang Tan, Yifu Zhang, Xiaoqing Ye, Jingdong Wang.
• SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model. Technical report. [PDF] [Code]
  • Dingyuan Zhang, Dingkang Liang, Hongcheng Yang, Zhikang Zou, Xiaoqing Ye, Zhe Liu, Xiang Bai.
• Diffusion-based 3D Object Detection with Random Boxes. PRCV 2023. [PDF]

• Xin Zhou, Jinghua Hou, Tingting Yao, Dingkang Liang, Zhe Liu, Zhikang Zou, Xiaoqing Ye, Jianwei Cheng, Xiang Bai.

• CAPE: Camera View Position Embedding for Multi-View 3D Object Detection. CVPR 2023. [PDF] [Paddle3D version] [Pytorch Code]
  • Kaixin Xiong*, Shi Gong*, Xiaoqing Ye*, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai.
• StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection. AAAI 2023.[PDF]
  • Zhe Liu, Xiaoqing Ye, Xiao Tan, Errui Ding, Xiang Bai.

[2022]

• Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task. CVPR 2022. [PDF] [Code] [Project]
  • Xiaoqing Ye, Mao Shu, Hanyu Li, Yifeng Shi, Yingying Li, Guangjie Wang, Xiao Tan, Errui Ding.
• GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation. ECCV 2022. [PDF]
  • Shi Gong*, Xiaoqing Ye*, Xiao Tan, Jingdong Wang, Errui Ding, Yu Zhou, Xiang Bai.
• TWIST: Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation. CVPR 2022. [PDF]
  • Ruihang Chu, Xiaoqing Ye, Zhengzhe Liu, Xiao Tan, Xiaojuan Qi, Chi-Wing Fu, Jiaya Jia.
• Spatial Pruned Sparse Convolution for Efficient 3D Object Detection. NeurIPS 2022. [PDF]
  • Jianhui Liu, Yukang Chen, Xiaoqing Ye, Zhuotao Tian, Xiao Tan, Xiaojuan Qi.
• Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network. ACM MM 2022. [PDF]
  • Bo Ju, Zhikang Zou, Xiaoqing Ye, Minyue Jiang, Xiao Tan, Errui Ding, Jingdong Wang.
• Repainting and Imitating Learning for Lane Detection. ACM MM 2022.
  • Yue He*, Minyue Jiang*, Xiaoqing Ye*, Liang Du, Zhikang Zou, Wei Zhang, Xiao Tan, Errui Ding.
• Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis. ACCV 2022. [PDF] [Project]
  • Xiang Guo*, Guanying Chen*, Yuchao Dai, Xiaoqing Ye, Jiadai Sun, Xiao Tan, Errui Ding.
• DuARE: Automatic Road Extraction with Aerial Images and Trajectory Data at Baidu Maps, KDD 2022.[PDF]
  • Jianzhong Yang*, Xiaoqing Ye*, Bin Wu, Yanlei Gu, Ziyu Wang, Deguo Xia, Jizhou Huang.
• SGM3D: Stereo Guided Monocular 3D Object Detection, IEEE Robotics and Automation Letters (RAL) 2022.[PDF]
  • Zheyuan Zhou, Liang Du, Xiaoqing Ye, Zhikang Zou, Xiao Tan, Li Zhang, Xiangyang Xue, Jianfeng Feng.
• Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation, IEEE Robotics and Automation Letters (RAL) 2022. [PDF]
  • Peizhe Jiang, Wei Yang, Xiaoqing Ye, Xiao Tan, Meng Wu.
• Modify the self-attention via skeleton decomposition for effective point-cloud transformer， AAAI 2022. [PDF]
  • Jiayi Han, Longbin Zeng, Liang Du, Xiaoqing Ye, Weiyang Ding, Jianfeng Feng.
• The devil is in the face: Exploiting harmonious representations for facial expression recognition, NeuralComputing. [PDF]
  • Jiayi Han, Liang Du, Xiaoqing Ye, Li Zhang, Jianfeng Feng.

[2021]

• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network. IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI) 2021. [PDF]
  • Liang Du, Xiaoqing Ye, Xiao Tan, Edward Johns, Bo Chen, Errui Ding, Xiangyang Xue, Jianfeng Feng.
• The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection. ICCV 2021. [PDF]
  • Zhikang Zou*, Xiaoqing Ye*, Liang Du*, Xianhui Cheng*, Xiao Tan, Li Zhang, Jianfeng Feng, Xiangyang Xue, Errui Ding.
• Revealing the Reciprocal Relations between Self-Supervised Stereo and Monocular Depth Estimation. ICCV 2021. [PDF]
  • Zhi Chen, Xiaoqing Ye, Zhikang Zou, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang.
• Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection. CVPR 20201. [PDF][Code]
  • Li Wang*, Liang Du*, Xiaoqing Ye*, Yanwei Fu, Guodong Guo, Xiangyang Xue, Jianfeng Feng, Li Zhang.
• AggNet for Self-supervised Monocular Depth Estimation: Go An Aggressive Step Further. ACM International Conference on Multimedia (ACM MM) 2021.[PDF]
  • Zhi Chen*, Xiaoqing Ye*, Liang Du, Wei Yang, Liusheng Huang, Xiao Tan, Zhenbo Shi, Fumin Shen, Errui Ding.
• Lifting the Veil of Frequency in Joint Segmentation and Depth Estimation. ACM International Conference on Multimedia (ACM MM) 2021.
  • Tianhao Fu*, Yingying Li*, Xiaoqing Ye*, Xiao Tan, Hao Sun, Fumin Shen, Errui Ding.
• Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network. ACM International Conference on Multimedia (ACM MM) 2021.[PDF]
  • Zhikang Zou*, Xiaoye Qu*, Pan Zhou, Shuangjie Xu, Xiaoqing Ye, Wenhao Wu, Jin Ye.
• Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting. ACM International Conference on Multimedia (ACM MM) 2021.[PDF]
  • Qiming Wu*, Zhikang Zou*, Pan Zhou, Xiaoqing Ye, Binghui Wang, Ang Li.
• DANet: Dimension Apart Network for Radar Object Detection. ICMRworkshop 2021.[PDF]
  • Bo Ju, Wei Yang, Jinrang Jia, Xiaoqing Ye, Qu Chen, Xiao Tan, Hao Sun, Yifeng Shi, Errui Ding.

[2020]

• Monocular 3d object detection via feature domain adaptation. ECCV 2020. [PDF]
  • Xiaoqing Ye*, Liang Du*, Yifeng Shi, Yingying Li, Xiao Tan, Jianfeng Feng, Errui Ding, Shilei Wen.
• Zoomnet: Part-aware adaptive zooming neural network for 3d object detection. AAAI 2020 oral. [PDF], [code]
  • Zhenbo Xu, Wei Zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang.
• Associate-3Ddet: Perceptual-to-conceptual association for 3D point cloud object detection. CVPR 2020. [PDF]
  • Liang Du*, Xiaoqing Ye*, Xiao Tan, Jianfeng Feng, Zhenbo Xu, Errui Ding, Shilei Wen.
• RegionNet: Region-feature-enhanced 3D Scene Understanding Network with Dual Spatial-aware Discriminative Loss. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020. [PDF]
  • Guanghui Zhang, Dongchen Zhu, Xiaoqing Ye, Wenjun Shi, Minghong Chen, Jiamao Li, Xiaolin Zhang.
• Leaping from 2D Detection to Efficient 6DoF Object Pose Estimation. ECCVw 2020. [PDF]
  • Jinhui Liu*, Zhikang Zou*, Xiaoqing Ye*, Xiao Tan, Errui Ding, Feng Xu, Xin Yu.
• Object reidentification via joint quadruple decorrelation directional deep networks in smart transportation. IEEE Internet of Things Journal 2020. [PDF]
  • Jianqing Zhu, Jingchang Huang, Huanqiang Zeng, Xiaoqing Ye, Baoqing Li, Zhen Lei, Lixin Zheng.
• Robust movement-specific vehicle counting at crowded intersections. CVPR 2020. [PDF]
  • Zhongji Liu, Wei Zhang, Xu Gao, Hao Meng, Xiao Tan, Xiaoxing Zhu, Zhan Xue, Xiaoqing Ye, Hongwu Zhang, Shilei Wen, Errui Ding

[2019]

• Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features. CVPR 2019workshops.[PDF]
  • Xiao Tan, Zhigang Wang, Minyue Jiang, Xipeng Yang, Jian Wang, Yuan Gao, Xiangbo Su, Xiaoqing Ye, Yuchen Yuan, Dongliang He, Shilei Wen, Errui Ding.
• SSf-DAN: Separated semantic feature based domain adaptation network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019.[PDF] [Code]
  • Liang Du, Jingang Tan, Hongye Yang, Jianfeng Feng, Xiangyang Xue, Qibao Zheng, Xiaoqing Ye, Xiaolin Zhang.

[2018]

• 3D Recurrent neural networks with context fusion for point cloud semantic segmentation. ECCV 2018. [PDF]
  • Xiaoqing Ye, Jiamao Li, Hexiao Huang, Liang Du, Xiaolin Zhang.

[2017]

• Order-based disparity refinement including occlusion handling for stereo matching. IEEE Signal Processing Letters 2017. [PDF]
  • Xiaoqing Ye, Yuzhang Gu, Lili Chen, Jiamao Li, Han Wang, Xiaolin Zhang.
• Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching. IEICE TRANSACTIONS on Information and Systems 2017. [PDF]
  • Xiaoqing Ye, Jiamao Li, Han Wang, Xiaolin Zhang.