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 Hongsheng Li

Uniformer: Unified Transformer for Efficient Spatiotemporal Representation Learning


Jan 12, 2022
Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

* 19pages, 7 figures 

  Access Paper or Ask Questions

Pyramid Fusion Transformer for Semantic Segmentation


Jan 11, 2022
Zipeng Qin, Jianbo Liu, Xiaolin Zhang, Maoqing Tian, Aojun Zhou, Shuai Yi, Hongsheng Li


  Access Paper or Ask Questions

You Only Need End-to-End Training for Long-Tailed Recognition


Dec 14, 2021
Zhiwei Zhang, Hongsheng Li

* 16 pages, 11 figures, 8 tables 

  Access Paper or Ask Questions

PointCLIP: Point Cloud Understanding by CLIP


Dec 04, 2021
Renrui Zhang, Ziyu Guo, Wei Zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li

* Open sourced, Code and Model Available 

  Access Paper or Ask Questions

Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks


Dec 02, 2021
Xizhou Zhu, Jinguo Zhu, Hao Li, Xiaoshi Wu, Xiaogang Wang, Hongsheng Li, Xiaohua Wang, Jifeng Dai


  Access Paper or Ask Questions

A Simple Long-Tailed Recognition Baseline via Vision-Language Model


Nov 29, 2021
Teli Ma, Shijie Geng, Mengmeng Wang, Jing Shao, Jiasen Lu, Hongsheng Li, Peng Gao, Yu Qiao


  Access Paper or Ask Questions

IDR: Self-Supervised Image Denoising via Iterative Data Refinement


Nov 29, 2021
Yi Zhang, Dasong Li, Ka Lung Law, Xiaogang Wang, Hongwei Qin, Hongsheng Li


  Access Paper or Ask Questions

Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling


Nov 15, 2021
Renrui Zhang, Rongyao Fang, Wei Zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, Hongsheng Li

* preprints 

  Access Paper or Ask Questions

Rethinking Noise Synthesis and Modeling in Raw Denoising


Oct 10, 2021
Yi Zhang, Hongwei Qin, Xiaogang Wang, Hongsheng Li

* ICCV2021 

  Access Paper or Ask Questions

CLIP-Adapter: Better Vision-Language Models with Feature Adapters


Oct 09, 2021
Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, Yu Qiao

* Technical Report 

  Access Paper or Ask Questions

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP


Oct 08, 2021
Jihao Liu, Hongsheng Li, Guanglu Song, Xin Huang, Yu Liu

* technich report 

  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

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting


Sep 07, 2021
Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li

* To appear at ICCV 2021 

  Access Paper or Ask Questions

Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation


Sep 06, 2021
Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li


  Access Paper or Ask Questions

Instance-weighted Central Similarity for Multi-label Image Retrieval


Aug 28, 2021
Zhiwei Zhang, Hanyu Peng, Hongsheng Li

* 10 pages, 6 figures 

  Access Paper or Ask Questions

Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition


Aug 19, 2021
Ning Wang, Guangming Zhu, Liang Zhang, Peiyi Shen, Hongsheng Li, Cong Hua

* ACM MM Oral paper 

  Access Paper or Ask Questions

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector


Aug 18, 2021
Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li

* ICCV'21 

  Access Paper or Ask Questions

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency


Aug 18, 2021
Zhipeng Luo, Zhongang Cai, Changqing Zhou, Gongjie Zhang, Haiyu Zhao, Shuai Yi, Shijian Lu, Hongsheng Li, Shanghang Zhang, Ziwei Liu


  Access Paper or Ask Questions

LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation


Aug 17, 2021
Lin Zhao, Hui Zhou, Xinge Zhu, Xiao Song, Hongsheng Li, Wenbing Tao


  Access Paper or Ask Questions

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection


Aug 15, 2021
Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi


  Access Paper or Ask Questions

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization


Aug 14, 2021
Linjiang Huang, Liang Wang, Hongsheng Li

* Accepted by ICCV 2021. Code is available at https://github.com/LeonHLJ/FAC-Net 

  Access Paper or Ask Questions

Fast Convergence of DETR with Spatially Modulated Co-Attention


Aug 05, 2021
Peng Gao, Minghang Zheng, Xiaogang Wang, Jifeng Dai, Hongsheng Li

* Accepted by ICCV2021 

  Access Paper or Ask Questions

Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification


Jul 07, 2021
Xiaohan Xing, Yuenan Hou, Hang Li, Yixuan Yuan, Hongsheng Li, Max Q. -H. Meng


  Access Paper or Ask Questions

Mixed Supervision Learning for Whole Slide Image Classification


Jul 05, 2021
Jiahui Li, Wen Chen, Xiaodi Huang, Zhiqiang Hu, Qi Duan, Hongsheng Li, Dimitris N. Metaxas, Shaoting Zhang


  Access Paper or Ask Questions

Scalable Transformers for Neural Machine Translation


Jun 18, 2021
Peng Gao, Shijie Geng, Yu Qiao, Xiaogang Wang, Jifeng Dai, Hongsheng Li

* Mostly overlapping with version 1, with minor updates/revisions 

  Access Paper or Ask Questions

Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification


Jun 11, 2021
Xiao Zhang, Yixiao Ge, Yu Qiao, Hongsheng Li

* Accepted by CVPR2021 

  Access Paper or Ask Questions