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 Tong He

Tong He

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

Figure 1 for ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Figure 2 for ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Figure 3 for ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Figure 4 for ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
* Table 7 updated. Code is at: https://git.io/AdelaiDet. Journal extension of arXiv:2002.10200 
  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

Figure 1 for HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
Figure 2 for HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
Figure 3 for HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
Figure 4 for HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
* Accepted to CVPR2021 
  Access Paper or Ask Questions

DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution


Nov 26, 2020
Tong He, Chunhua Shen, Anton van den Hengel

Figure 1 for DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Figure 2 for DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Figure 3 for DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Figure 4 for DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

  Access Paper or Ask Questions

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction


Jun 15, 2020
Tong He, John Collomosse, Hailin Jin, Stefano Soatto

Figure 1 for Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Figure 2 for Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Figure 3 for Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Figure 4 for Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction

  Access Paper or Ask Questions

FCOS: A simple and strong anchor-free object detector


Jun 14, 2020
Zhi Tian, Chunhua Shen, Hao Chen, Tong He

Figure 1 for FCOS: A simple and strong anchor-free object detector
Figure 2 for FCOS: A simple and strong anchor-free object detector
Figure 3 for FCOS: A simple and strong anchor-free object detector
Figure 4 for FCOS: A simple and strong anchor-free object detector
* Extended version of "FCOS: Fully Convolutional One-Stage Object Detection". Code is at: https://git.io/AdelaiDet. arXiv admin note: substantial text overlap with arXiv:1904.01355 
  Access Paper or Ask Questions

Improving Semantic Segmentation via Self-Training


May 06, 2020
Yi Zhu, Zhongyue Zhang, Chongruo Wu, Zhi Zhang, Tong He, Hang Zhang, R. Manmatha, Mu Li, Alexander Smola

Figure 1 for Improving Semantic Segmentation via Self-Training
Figure 2 for Improving Semantic Segmentation via Self-Training
Figure 3 for Improving Semantic Segmentation via Self-Training
Figure 4 for Improving Semantic Segmentation via Self-Training

  Access Paper or Ask Questions

ResNeSt: Split-Attention Networks


Apr 19, 2020
Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Zhi Zhang, Haibin Lin, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

Figure 1 for ResNeSt: Split-Attention Networks
Figure 2 for ResNeSt: Split-Attention Networks
Figure 3 for ResNeSt: Split-Attention Networks
Figure 4 for ResNeSt: Split-Attention Networks

  Access Paper or Ask Questions

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network


Feb 25, 2020
Yuliang Liu, Hao Chen, Chunhua Shen, Tong He, Lianwen Jin, Liangwei Wang

Figure 1 for ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Figure 2 for ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Figure 3 for ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Figure 4 for ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
* Accepted to Proc. IEEE Conf. Comp. Vis. Pattern Recogn. (CVPR) 2020 
  Access Paper or Ask Questions

Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation


Jan 06, 2020
Tong He, Dong Gong, Zhi Tian, Chunhua Shen

Figure 1 for Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Figure 2 for Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Figure 3 for Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Figure 4 for Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

  Access Paper or Ask Questions

Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition


Dec 24, 2019
Jialin Gao, Tong He, Xi Zhou, Shiming Ge

Figure 1 for Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
Figure 2 for Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
Figure 3 for Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
Figure 4 for Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition

  Access Paper or Ask Questions

Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection


Dec 20, 2019
Yuliang Liu, Tong He, Hao Chen, Xinyu Wang, Canjie Luo, Shuaitao Zhang, Chunhua Shen, Lianwen Jin

Figure 1 for Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection
Figure 2 for Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection
Figure 3 for Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection
Figure 4 for Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection

  Access Paper or Ask Questions

LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning


Dec 06, 2019
Albert Zhao, Tong He, Yitao Liang, Haibin Huang, Guy Van den Broeck, Stefano Soatto

Figure 1 for LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning
Figure 2 for LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning
Figure 3 for LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning
Figure 4 for LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning

  Access Paper or Ask Questions

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing


Jul 09, 2019
Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng

Figure 1 for GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

  Access Paper or Ask Questions

Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources


May 02, 2019
Haibin Lin, Hang Zhang, Yifei Ma, Tong He, Zhi Zhang, Sheng Zha, Mu Li

Figure 1 for Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
Figure 2 for Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
Figure 3 for Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
Figure 4 for Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources

  Access Paper or Ask Questions

FCOS: Fully Convolutional One-Stage Object Detection


Apr 14, 2019
Zhi Tian, Chunhua Shen, Hao Chen, Tong He

Figure 1 for FCOS: Fully Convolutional One-Stage Object Detection
Figure 2 for FCOS: Fully Convolutional One-Stage Object Detection
Figure 3 for FCOS: Fully Convolutional One-Stage Object Detection
Figure 4 for FCOS: Fully Convolutional One-Stage Object Detection
* 13 pages. Code is available at: https://github.com/tianzhi0549/FCOS/ 
  Access Paper or Ask Questions

Bag of Freebies for Training Object Detection Neural Networks


Apr 12, 2019
Zhi Zhang, Tong He, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Figure 1 for Bag of Freebies for Training Object Detection Neural Networks
Figure 2 for Bag of Freebies for Training Object Detection Neural Networks
Figure 3 for Bag of Freebies for Training Object Detection Neural Networks
Figure 4 for Bag of Freebies for Training Object Detection Neural Networks

  Access Paper or Ask Questions

Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation


Apr 05, 2019
Zhi Tian, Tong He, Chunhua Shen, Youliang Yan

Figure 1 for Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
Figure 2 for Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
Figure 3 for Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
Figure 4 for Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
* Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2019. Content may change prior to final publication 
  Access Paper or Ask Questions

Knowledge Adaptation for Efficient Semantic Segmentation


Mar 12, 2019
Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan

Figure 1 for Knowledge Adaptation for Efficient Semantic Segmentation
Figure 2 for Knowledge Adaptation for Efficient Semantic Segmentation
Figure 3 for Knowledge Adaptation for Efficient Semantic Segmentation
Figure 4 for Knowledge Adaptation for Efficient Semantic Segmentation
* Accepted to IEEE Conf. Computer Vision and Pattern Recognition, 2019 
  Access Paper or Ask Questions

Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors


Jan 11, 2019
Tong He, Stefano Soatto

Figure 1 for Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Figure 2 for Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Figure 3 for Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Figure 4 for Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
* Proc. of the AAAI, September 2018 
  Access Paper or Ask Questions

GIF2Video: Color Dequantization and Temporal Interpolation of GIF images


Jan 09, 2019
Yang Wang, Haibin Huang, Chuan Wang, Tong He, Jue Wang, Minh Hoai

Figure 1 for GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
Figure 2 for GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
Figure 3 for GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
Figure 4 for GIF2Video: Color Dequantization and Temporal Interpolation of GIF images

  Access Paper or Ask Questions

GeoNet: Deep Geodesic Networks for Point Cloud Analysis


Jan 03, 2019
Tong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto

Figure 1 for GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Figure 2 for GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Figure 3 for GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Figure 4 for GeoNet: Deep Geodesic Networks for Point Cloud Analysis

  Access Paper or Ask Questions

Bag of Tricks for Image Classification with Convolutional Neural Networks


Dec 05, 2018
Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Figure 1 for Bag of Tricks for Image Classification with Convolutional Neural Networks
Figure 2 for Bag of Tricks for Image Classification with Convolutional Neural Networks
Figure 3 for Bag of Tricks for Image Classification with Convolutional Neural Networks
Figure 4 for Bag of Tricks for Image Classification with Convolutional Neural Networks
* 10 pages, 9 tables, 4 figures 
  Access Paper or Ask Questions

An end-to-end TextSpotter with Explicit Alignment and Attention


Mar 23, 2018
Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun

Figure 1 for An end-to-end TextSpotter with Explicit Alignment and Attention
Figure 2 for An end-to-end TextSpotter with Explicit Alignment and Attention
Figure 3 for An end-to-end TextSpotter with Explicit Alignment and Attention
Figure 4 for An end-to-end TextSpotter with Explicit Alignment and Attention
* Accepted to IEEE Conf. Computer Vision and Pattern Recognition (CVPR) 2018. Code is available at: https://github.com/tonghe90/textspotter 
  Access Paper or Ask Questions

Detecting Text in Natural Image with Connectionist Text Proposal Network


Sep 12, 2016
Zhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao

Figure 1 for Detecting Text in Natural Image with Connectionist Text Proposal Network
Figure 2 for Detecting Text in Natural Image with Connectionist Text Proposal Network
Figure 3 for Detecting Text in Natural Image with Connectionist Text Proposal Network
Figure 4 for Detecting Text in Natural Image with Connectionist Text Proposal Network
* To appear in ECCV, 2016 
  Access Paper or Ask Questions

Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network


Mar 31, 2016
Tong He, Weilin Huang, Yu Qiao, Jian Yao

Figure 1 for Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
Figure 2 for Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
Figure 3 for Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
Figure 4 for Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

  Access Paper or Ask Questions

Text-Attentional Convolutional Neural Networks for Scene Text Detection


Mar 24, 2016
Tong He, Weilin Huang, Yu Qiao, Jian Yao

Figure 1 for Text-Attentional Convolutional Neural Networks for Scene Text Detection
Figure 2 for Text-Attentional Convolutional Neural Networks for Scene Text Detection
Figure 3 for Text-Attentional Convolutional Neural Networks for Scene Text Detection
Figure 4 for Text-Attentional Convolutional Neural Networks for Scene Text Detection
* To appear in IEEE Trans. on Image Processing, 2016 
  Access Paper or Ask Questions