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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Dahua Lin

OCSampler: Compressing Videos to One Clip with Single-step Sampling


Jan 12, 2022
Jintao Lin, Haodong Duan, Kai Chen, Dahua Lin, Limin Wang

* Video Understanding, Efficient Action Recognition 

  Access Paper or Ask Questions

CityNeRF: Building NeRF at City Scale


Dec 17, 2021
Yuanbo Xiangli, Linning Xu, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, Bo Dai, Dahua Lin

* Project page can be found in https://city-super.github.io/citynerf 

  Access Paper or Ask Questions

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion


Dec 16, 2021
Zhaoyang Lyu, Zhifeng Kong, Xudong Xu, Liang Pan, Dahua Lin

* Code will be released at https://github.com/ZhaoyangLyu/Point_Diffusion_Refinement 

  Access Paper or Ask Questions

SPTS: Single-Point Text Spotting


Dec 15, 2021
Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Shenggao Zhu, Jing Li, Dahua Lin, Chunhua Shen, Lianwen Jin


  Access Paper or Ask Questions

Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion


Nov 24, 2021
Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang, Ziwei Liu, Dahua Lin

* Accepted to NeurIPS 2021 

  Access Paper or Ask Questions

Few-Shot Object Detection via Association and DIscrimination


Nov 23, 2021
Yuhang Cao, Jiaqi Wang, Ying Jin, Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin

* NeurIPS 2021 Camera Ready 

  Access Paper or Ask Questions

INTERN: A New Learning Paradigm Towards General Vision


Nov 16, 2021
Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao


  Access Paper or Ask Questions

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis


Nov 01, 2021
Xudong Xu, Xingang Pan, Dahua Lin, Bo Dai

* Accepted to NeurIPS2021. We propose Generative Occupancy Fields(GOF), a 3D-aware generative model which could synthesize realistic images with 3D consistency and simultaneously learn compact object surfaces 

  Access Paper or Ask Questions

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception


Sep 12, 2021
Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin

* Accepted by TPAMI 2021; Source code at https://github.com/xinge008/Cylinder3D. arXiv admin note: substantial text overlap with arXiv:2011.10033 

  Access Paper or Ask Questions

Temporal RoI Align for Video Object Recognition


Sep 11, 2021
Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng

* Accpeted by AAAI 2021 

  Access Paper or Ask Questions

Towards Balanced Learning for Instance Recognition


Aug 23, 2021
Jiangmiao Pang, Kai Chen, Qi Li, Zhihai Xu, Huajun Feng, Jianping Shi, Wanli Ouyang, Dahua Lin

* Accepted by IJCV. Journal extension of paper arXiv:1904.02701 

  Access Paper or Ask Questions

MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding


Aug 14, 2021
Zhanghui Kuang, Hongbin Sun, Zhizhong Li, Xiaoyu Yue, Tsui Hin Lin, Jianyong Chen, Huaqiang Wei, Yiqin Zhu, Tong Gao, Wenwei Zhang, Kai Chen, Wayne Zhang, Dahua Lin

* Accepted to ACM MM (Open Source Competition Track) 

  Access Paper or Ask Questions

Vision Transformer with Progressive Sampling


Aug 03, 2021
Xiaoyu Yue, Shuyang Sun, Zhanghui Kuang, Meng Wei, Philip Torr, Wayne Zhang, Dahua Lin

* Accepted to ICCV 2021 

  Access Paper or Ask Questions

Probabilistic and Geometric Depth: Detecting Objects in Perspective


Jul 29, 2021
Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin


  Access Paper or Ask Questions

Transcript to Video: Efficient Clip Sequencing from Texts


Jul 25, 2021
Yu Xiong, Fabian Caba Heilbron, Dahua Lin

* Tech Report; Demo and project page at http://www.xiongyu.me/projects/transcript2video/ 

  Access Paper or Ask Questions

WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection


May 21, 2021
Shijie Fang, Yuhang Cao, Xinjiang Wang, Kai Chen, Dahua Lin, Wayne Zhang


  Access Paper or Ask Questions

Revisiting Skeleton-based Action Recognition


Apr 28, 2021
Haodong Duan, Yue Zhao, Kai Chen, Dian Shao, Dahua Lin, Bo Dai


  Access Paper or Ask Questions

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection


Apr 22, 2021
Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin

* Technical report for the best vision-only method (1st place of the camera track) in the nuScenes 3D detection challenge of NeurIPS 2020 

  Access Paper or Ask Questions

Visually Informed Binaural Audio Generation without Binaural Audios


Apr 13, 2021
Xudong Xu, Hang Zhou, Ziwei Liu, Bo Dai, Xiaogang Wang, Dahua Lin

* Accepted by CVPR 2021. Code, models, and demo video are available on our webpage: \ 

  Access Paper or Ask Questions

Adversarial Robustness under Long-Tailed Distribution


Apr 06, 2021
Tong Wu, Ziwei Liu, Qingqiu Huang, Yu Wang, Dahua Lin

* Accepted to CVPR 2021 (Oral) 

  Access Paper or Ask Questions

Towards Evaluating and Training Verifiably Robust Neural Networks


Apr 05, 2021
Zhaoyang Lyu, Minghao Guo, Tong Wu, Guodong Xu, Kehuan Zhang, Dahua Lin

* Accepted to CVPR 2021 (Oral) 

  Access Paper or Ask Questions

CARAFE++: Unified Content-Aware ReAssembly of FEatures


Dec 07, 2020
Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

* Technical Report. Extended journal version of the conference paper that appeared as arXiv:1905.02188 

  Access Paper or Ask Questions

FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds


Nov 20, 2020
Tai Wang, Conghui He, Zhe Wang, Jianping Shi, Dahua Lin

* Full technical report for the UIST 2020 Poster version 

  Access Paper or Ask Questions

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

Understanding the wiring evolution in differentiable neural architecture search


Sep 07, 2020
Sirui Xie, Shoukang Hu, Xinjiang Wang, Chunxiao Liu, Jianping Shi, Xunying Liu, Dahua Lin


  Access Paper or Ask Questions