Xingyu Zeng

SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers

Mar 15, 2023
Guoqiang Jin, Fan Yang, Mingshan Sun, Ruyi Zhao, Yakun Liu, Wei Li, Tianpeng Bao, Liwei Wu, Xingyu Zeng, Rui Zhao

Figure 2 for SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers

Figure 3 for SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers

Figure 4 for SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers

Access Paper or Ask Questions

An Effective Crop-Paste Pipeline for Few-shot Object Detection

Feb 28, 2023
Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao

Figure 2 for An Effective Crop-Paste Pipeline for Few-shot Object Detection

Figure 3 for An Effective Crop-Paste Pipeline for Few-shot Object Detection

Figure 4 for An Effective Crop-Paste Pipeline for Few-shot Object Detection

Access Paper or Ask Questions

Explore the Power of Dropout on Few-shot Learning

Jan 26, 2023
Shaobo Lin, Xingyu Zeng, Rui Zhao

Figure 2 for Explore the Power of Dropout on Few-shot Learning

Figure 3 for Explore the Power of Dropout on Few-shot Learning

Figure 4 for Explore the Power of Dropout on Few-shot Learning

* arXiv admin note: substantial text overlap with arXiv:2210.06409

Access Paper or Ask Questions

A Unified Framework with Meta-dropout for Few-shot Learning

Oct 12, 2022
Shaobo Lin, Xingyu Zeng, Rui Zhao

Figure 2 for A Unified Framework with Meta-dropout for Few-shot Learning

Figure 3 for A Unified Framework with Meta-dropout for Few-shot Learning

Figure 4 for A Unified Framework with Meta-dropout for Few-shot Learning

Access Paper or Ask Questions

Rethinking Pseudo-LiDAR Representation

Aug 11, 2020
Xinzhu Ma, Shinan Liu, Zhiyi Xia, Hongwen Zhang, Xingyu Zeng, Wanli Ouyang

Figure 2 for Rethinking Pseudo-LiDAR Representation

Figure 3 for Rethinking Pseudo-LiDAR Representation

Figure 4 for Rethinking Pseudo-LiDAR Representation

* ECCV2020. Supplemental Material attached

Access Paper or Ask Questions

Adapting Object Detectors with Conditional Domain Normalization

Mar 16, 2020
Peng Su, Kun Wang, Xingyu Zeng, Shixiang Tang, Dapeng Chen, Di Qiu, Xiaogang Wang

Figure 2 for Adapting Object Detectors with Conditional Domain Normalization

Figure 3 for Adapting Object Detectors with Conditional Domain Normalization

Figure 4 for Adapting Object Detectors with Conditional Domain Normalization

Access Paper or Ask Questions

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Feb 05, 2020
Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, Xiaogang Wang

Figure 2 for Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Figure 3 for Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Figure 4 for Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

* 11 pages, 8 figures, AAAI2020

Access Paper or Ask Questions

GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

Mar 27, 2019
Buyu Li, Wanli Ouyang, Lu Sheng, Xingyu Zeng, Xiaogang Wang

Figure 2 for GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

Figure 3 for GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

Figure 4 for GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

* Accepted by CVPR2019

Access Paper or Ask Questions

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

Aug 03, 2017
Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang, Ruohui Wang, Xiaogang Wang, Wanli Ouyang

Figure 2 for T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

Figure 3 for T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

Figure 4 for T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

* ImageNet 2015 VID challenge tech report. The first two authors share co-first authorship. Accepted as a Transaction paper by T-CSVT Special Issue on Large Scale and Nonlinear Similarity Learning for Intelligent Video Analysis

Access Paper or Ask Questions

Crafting GBD-Net for Object Detection

Oct 08, 2016
Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang

Figure 2 for Crafting GBD-Net for Object Detection

Figure 3 for Crafting GBD-Net for Object Detection

Figure 4 for Crafting GBD-Net for Object Detection

* This paper shows the details of our approach in wining the ImageNet object detection challenge of 2016, with source code provided on \url{https://github.com/craftGBD/craftGBD}. The preliminary version of this paper is presented at the ECCV. Xingyu Zeng and Wanli Ouyang contributed equally

Access Paper or Ask Questions

1

2

>>