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 Xinlong Wang

Xinlong Wang

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


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

Figure 1 for FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
Figure 2 for FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
Figure 3 for FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
Figure 4 for FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
* Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR) 2021. Code is at https://git.io/AdelaiDet 
  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

Figure 1 for TFPose: Direct Human Pose Estimation with Transformers
Figure 2 for TFPose: Direct Human Pose Estimation with Transformers
Figure 3 for TFPose: Direct Human Pose Estimation with Transformers
Figure 4 for TFPose: Direct Human Pose Estimation with Transformers
* 15 pages 
  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

Figure 1 for Conditional Positional Encodings for Vision Transformers
Figure 2 for Conditional Positional Encodings for Vision Transformers
Figure 3 for Conditional Positional Encodings for Vision Transformers
Figure 4 for Conditional Positional Encodings for Vision Transformers
* A general purpose conditional position encoding for vision transformers 
  Access Paper or Ask Questions

Diverse Knowledge Distillation for End-to-End Person Search


Dec 21, 2020
Xinyu Zhang, Xinlong Wang, Jia-Wang Bian, Chunhua Shen, Mingyu You

Figure 1 for Diverse Knowledge Distillation for End-to-End Person Search
Figure 2 for Diverse Knowledge Distillation for End-to-End Person Search
Figure 3 for Diverse Knowledge Distillation for End-to-End Person Search
Figure 4 for Diverse Knowledge Distillation for End-to-End Person Search
* Accepted to AAAI, 2021. Code is available at: https://git.io/DKD-PersonSearch 
  Access Paper or Ask Questions

End-to-End Video Instance Segmentation with Transformers


Dec 04, 2020
Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, Huaxia Xia

Figure 1 for End-to-End Video Instance Segmentation with Transformers
Figure 2 for End-to-End Video Instance Segmentation with Transformers
Figure 3 for End-to-End Video Instance Segmentation with Transformers
Figure 4 for End-to-End Video Instance Segmentation with Transformers

  Access Paper or Ask Questions

BoxInst: High-Performance Instance Segmentation with Box Annotations


Dec 03, 2020
Zhi Tian, Chunhua Shen, Xinlong Wang, Hao Chen

Figure 1 for BoxInst: High-Performance Instance Segmentation with Box Annotations
Figure 2 for BoxInst: High-Performance Instance Segmentation with Box Annotations
Figure 3 for BoxInst: High-Performance Instance Segmentation with Box Annotations
Figure 4 for BoxInst: High-Performance Instance Segmentation with Box Annotations
* Code is available at: https://git.io/AdelaiDet 
  Access Paper or Ask Questions

Dense Contrastive Learning for Self-Supervised Visual Pre-Training


Nov 18, 2020
Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li

Figure 1 for Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Figure 2 for Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Figure 3 for Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Figure 4 for Dense Contrastive Learning for Self-Supervised Visual Pre-Training
* 10 pages 
  Access Paper or Ask Questions

SOLOv2: Dynamic, Faster and Stronger


Mar 23, 2020
Xinlong Wang, Rufeng Zhang, Tao Kong, Lei Li, Chunhua Shen

Figure 1 for SOLOv2: Dynamic, Faster and Stronger
Figure 2 for SOLOv2: Dynamic, Faster and Stronger
Figure 3 for SOLOv2: Dynamic, Faster and Stronger
Figure 4 for SOLOv2: Dynamic, Faster and Stronger
* 12 pages 
  Access Paper or Ask Questions

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data


Feb 14, 2020
Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Changming Sun, Dou Renyin

Figure 1 for DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Figure 2 for DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Figure 3 for DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Figure 4 for DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
* 10 pages. Fixed typos 
  Access Paper or Ask Questions

SOLO: Segmenting Objects by Locations


Dec 15, 2019
Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei Li

Figure 1 for SOLO: Segmenting Objects by Locations
Figure 2 for SOLO: Segmenting Objects by Locations
Figure 3 for SOLO: Segmenting Objects by Locations
Figure 4 for SOLO: Segmenting Objects by Locations
* 10 pages. Add "error analysis"; and fix typos 
  Access Paper or Ask Questions

Task-Aware Monocular Depth Estimation for 3D Object Detection


Sep 17, 2019
Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei Li, Chunhua Shen

Figure 1 for Task-Aware Monocular Depth Estimation for 3D Object Detection
Figure 2 for Task-Aware Monocular Depth Estimation for 3D Object Detection
Figure 3 for Task-Aware Monocular Depth Estimation for 3D Object Detection
Figure 4 for Task-Aware Monocular Depth Estimation for 3D Object Detection

  Access Paper or Ask Questions

Associatively Segmenting Instances and Semantics in Point Clouds


Feb 28, 2019
Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia

Figure 1 for Associatively Segmenting Instances and Semantics in Point Clouds
Figure 2 for Associatively Segmenting Instances and Semantics in Point Clouds
Figure 3 for Associatively Segmenting Instances and Semantics in Point Clouds
Figure 4 for Associatively Segmenting Instances and Semantics in Point Clouds
* Accepted by CVPR2019 
  Access Paper or Ask Questions

Repulsion Loss: Detecting Pedestrians in a Crowd


Mar 26, 2018
Xinlong Wang, Tete Xiao, Yuning Jiang, Shuai Shao, Jian Sun, Chunhua Shen

Figure 1 for Repulsion Loss: Detecting Pedestrians in a Crowd
Figure 2 for Repulsion Loss: Detecting Pedestrians in a Crowd
Figure 3 for Repulsion Loss: Detecting Pedestrians in a Crowd
Figure 4 for Repulsion Loss: Detecting Pedestrians in a Crowd
* Accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 
  Access Paper or Ask Questions

Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition


Nov 10, 2017
Xinlong Wang, Zhipeng Man, Mingyu You, Chunhua Shen

Figure 1 for Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
Figure 2 for Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
Figure 3 for Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
Figure 4 for Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition

  Access Paper or Ask Questions