Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

Nov 19, 2020
Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Yuexin Ma, Wei Li, Hongsheng Li, Dahua Lin

* This work achieves the 1st place in the leaderboard of SemanticKITTI (until CVPR DDL) and based on this work, we also achieve the 1st place in the leaderboard of SemanticKITTI panoptic segmentation; Code at https://github.com/xinge008/Cylinder3D 

  Access Paper or Ask Questions

End-to-End Object Detection with Adaptive Clustering Transformer

Nov 18, 2020
Minghang Zheng, Peng Gao, Xiaogang Wang, Hongsheng Li, Hao Dong

* technique report 

  Access Paper or Ask Questions

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks

Oct 19, 2020
Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li

* Accepted to CoRL 2020 

  Access Paper or Ask Questions

PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges

Aug 28, 2020
Shaoshuai Shi, Chaoxu Guo, Jihan Yang, Hongsheng Li


  Access Paper or Ask Questions

EfficientFCN: Holistically-guided Decoding for Semantic Segmentation

Aug 27, 2020
Jianbo Liu, Junjun He, Jiawei Zhang, Jimmy S. Ren, Hongsheng Li

* Accepted in ECCV 2020 

  Access Paper or Ask Questions

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020

Aug 26, 2020
Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang, Manyuan Zhang, Wei Wu, Yu Liu, Hongsheng Li, Junjie Yan

* Submitted to CVPR workshop of ActivityNet Challenge 2020 

  Access Paper or Ask Questions

Multi-organ Segmentation via Co-training Weight-averaged Models from Few-organ Datasets

Aug 17, 2020
Rui Huang, Yuanjie Zheng, Zhiqiang Hu, Shaoting Zhang, Hongsheng Li

* Accepted by MICCAI 2020 

  Access Paper or Ask Questions

Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

Aug 04, 2020
Xihui Liu, Zhe Lin, Jianming Zhang, Handong Zhao, Quan Tran, Xiaogang Wang, Hongsheng Li

* To appear on ECCV 2020. Introduction video at https://youtu.be/8E3bwvjCHYE and code at https://github.com/xh-liu/Open-Edit 

  Access Paper or Ask Questions

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

Aug 04, 2020
Hui Zhou, Xinge Zhu, Xiao Song, Yuexin Ma, Zhe Wang, Hongsheng Li, Dahua Lin

* Source code: https://github.com/xinge008/Cylinder3D 

  Access Paper or Ask Questions

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Jul 21, 2020
Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, Hongsheng Li


  Access Paper or Ask Questions

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Jul 17, 2020
Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang, Wayne Wu, Chen Qian, Hongsheng Li, Gang Zeng

* Accepted by ECCV 2020 

  Access Paper or Ask Questions

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

Jul 15, 2020
Junting Pan, Siyu Chen, Zheng Shou, Jing Shao, Hongsheng Li

* 1st place solution in ActivityNet Challenge 2020 -- AVA-Kinetics Task 

  Access Paper or Ask Questions

1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020

Jun 16, 2020
Siyu Chen, Junting Pan, Guanglu Song, Manyuan Zhang, Hao Shao, Ziyi Lin, Jing Shao, Hongsheng Li, Yu Liu

* arXiv admin note: substantial text overlap with arXiv:2006.07976 

  Access Paper or Ask Questions

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

Jun 06, 2020
Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li


  Access Paper or Ask Questions

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Jun 04, 2020
Yixiao Ge, Dapeng Chen, Feng Zhu, Rui Zhao, Hongsheng Li


  Access Paper or Ask Questions

StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

May 05, 2020
Rui Liu, Chengxi Yang, Wenxiu Sun, Xiaogang Wang, Hongsheng Li

* Accepted to CVPR2020 

  Access Paper or Ask Questions

Learning to Predict Context-adaptive Convolution for Semantic Segmentation

Apr 17, 2020
Jianbo Liu, Junjun He, Jimmy S. Ren, Yu Qiao, Hongsheng Li


  Access Paper or Ask Questions

3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior

Mar 31, 2020
Xiaokang Chen, Kwan-Yee Lin, Chen Qian, Gang Zeng, Hongsheng Li

* Accepted by CVPR 2020 

  Access Paper or Ask Questions

Structured Domain Adaptation for Unsupervised Person Re-identification

Mar 14, 2020
Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li


  Access Paper or Ask Questions

MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification

Feb 26, 2020
Yushi Lan, Yuan Liu, Maoqing Tian, Xinchi Zhou, Xuesen Zhang, Shuai Yi, Hongsheng Li


  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

* 11 pages, 8 figures, AAAI2020 

  Access Paper or Ask Questions

Structure-Feature based Graph Self-adaptive Pooling

Jan 30, 2020
Liang Zhang, Xudong Wang, Hongsheng Li, Guangming Zhu, Peiyi Shen, Ping Li, Xiaoyuan Lu, Syed Afaq Ali Shah, Mohammed Bennamoun

* 7 pages, 4 figures, The Web Conference 2020 

  Access Paper or Ask Questions

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Jan 30, 2020
Yixiao Ge, Dapeng Chen, Hongsheng Li

* Accepted in International Conference on Learning Representations (ICLR 2020) 

  Access Paper or Ask Questions

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Dec 31, 2019
Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li


  Access Paper or Ask Questions

Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis

Oct 16, 2019
Xihui Liu, Guojun Yin, Jing Shao, Xiaogang Wang, Hongsheng Li

* Accepted by NeurIPS 2019. Code will be available soon at https://github.com/xh-liu/CC-FPSE 

  Access Paper or Ask Questions

Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints

Oct 15, 2019
Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li

* Accepted to ICCV 2019 

  Access Paper or Ask Questions

CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval

Sep 12, 2019
Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao

* Accepted by ICCV 2019 

  Access Paper or Ask Questions