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 Chunhua Shen

Poseur: Direct Human Pose Regression with Transformers


Jan 19, 2022
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton van den Hengel


  Access Paper or Ask Questions

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation


Jan 18, 2022
Yutong Dai, Brian Price, He Zhang, Chunhua Shen

* 19 pages 

  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

NAS-FCOS: Efficient Search for Object Detection Architectures


Oct 24, 2021
Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang

* 14 pages, 11 figures, journal extension of NAS-FCOS (CVPR 2020), accepted by IJCV. arXiv admin note: substantial text overlap with arXiv:1906.04423 

  Access Paper or Ask Questions

TSG: Target-Selective Gradient Backprop for Probing CNN Visual Saliency


Oct 11, 2021
Lin Cheng, Pengfei Fang, Yanjie Liang, Liao Zhang, Chunhua Shen, Hanzi Wang

* Submitted to IEEE Transactions on Image Processing 

  Access Paper or Ask Questions

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning


Sep 13, 2021
Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen

* Accepted by ICCV2021 

  Access Paper or Ask Questions

Explainable Deep Few-shot Anomaly Detection with Deviation Networks


Aug 01, 2021
Guansong Pang, Choubo Ding, Chunhua Shen, Anton van den Hengel

* 16 pages, 8 figures, 5 tables 

  Access Paper or Ask Questions

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation


Jul 30, 2021
Bowen Zhang, Yifan Liu, Zhi Tian, Chunhua Shen


  Access Paper or Ask Questions

Dynamic Convolution for 3D Point Cloud Instance Segmentation


Jul 18, 2021
Tong He, Chunhua Shen, Anton van den Hengel

* Extended version of arXiv:2011.13328 

  Access Paper or Ask Questions

SOLO: A Simple Framework for Instance Segmentation


Jun 30, 2021
Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li

* 20 pages. arXiv admin note: substantial text overlap with arXiv:1912.04488, arXiv:2003.10152 

  Access Paper or Ask Questions

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting


May 29, 2021
Yuliang Liu, Chunhua Shen, Lianwen Jin, Tong He, Peng Chen, Chongyu Liu, Hao Chen

* Table 7 updated. Code is at: https://git.io/AdelaiDet. Journal extension of arXiv:2002.10200 

  Access Paper or Ask Questions

FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions


May 29, 2021
Weian Mao, Zhi Tian, Xinlong Wang, Chunhua Shen

* Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR) 2021. Code is at https://git.io/AdelaiDet 

  Access Paper or Ask Questions

Unsupervised Scale-consistent Depth Learning from Video


May 25, 2021
Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Zhichao Li, Le Zhang, Chunhua Shen, Ming-Ming Cheng, Ian Reid

* Accept to IJCV. The source code is available at https://github.com/JiawangBian/SC-SfMLearner-Release 

  Access Paper or Ask Questions

HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding


May 17, 2021
Ruibo Li, Guosheng Lin, Tong He, Fayao Liu, Chunhua Shen

* Accepted to CVPR2021 

  Access Paper or Ask Questions

Twins: Revisiting the Design of Spatial Attention in Vision Transformers


May 11, 2021
Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* Two simple and effective designs of vision transformer, which is on par with the Swin transformer 

  Access Paper or Ask Questions

PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text


May 09, 2021
Wenhai Wang, Enze Xie, Xiang Li, Xuebo Liu, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen

* Accepted to TPAMI 2021 

  Access Paper or Ask Questions

Twins: Revisiting Spatial Attention Design in Vision Transformers


Apr 28, 2021
Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* Two simple and effective designs of vision transformer, which is on par with the Swin transformer 

  Access Paper or Ask Questions

Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition


Apr 21, 2021
Delian Ruan, Yan Yan, Shenqi Lai, Zhenhua Chai, Chunhua Shen, Hanzi Wang

* accepted to CVPR 2021 

  Access Paper or Ask Questions

A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation


Apr 19, 2021
Jianlong Yuan, Yifan Liu, Chunhua Shen, Zhibin Wang, Hao Li

* 11 pages. Fixed typos 

  Access Paper or Ask Questions

Kernel Agnostic Real-world Image Super-resolution


Apr 19, 2021
Hu Wang, Congbo Ma, Chunhua Shen


  Access Paper or Ask Questions

An Adversarial Human Pose Estimation Network Injected with Graph Structure


Apr 05, 2021
Lei Tian, Guoqiang Liang, Peng Wang, Chunhua Shen

* The paper is accepted by Pattern Recognition 

  Access Paper or Ask Questions

TFPose: Direct Human Pose Estimation with Transformers


Mar 29, 2021
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang

* 15 pages 

  Access Paper or Ask Questions

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation


Mar 21, 2021
Lingtong Kong, Chunhua Shen, Jie Yang

* Accepted by ICRA 2021 

  Access Paper or Ask Questions

Generic Perceptual Loss for Modeling Structured Output Dependencies


Mar 18, 2021
Yifan Liu, Hao Chen, Yu Chen, Wei Yin, Chunhua Shen

* Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2021 

  Access Paper or Ask Questions

Conditional Positional Encodings for Vision Transformers


Mar 18, 2021
Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Xiaolin Wei, Huaxia Xia, Chunhua Shen

* A general purpose conditional position encoding for vision transformers 

  Access Paper or Ask Questions