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 Hao Li

Hao Li

Fine-Grained AutoAugmentation for Multi-Label Classification


Jul 13, 2021
Ya Wang, Hesen Chen, Fangyi Zhang, Yaohua Wang, Xiuyu Sun, Ming Lin, Hao Li

Figure 1 for Fine-Grained AutoAugmentation for Multi-Label Classification
Figure 2 for Fine-Grained AutoAugmentation for Multi-Label Classification
Figure 3 for Fine-Grained AutoAugmentation for Multi-Label Classification
Figure 4 for Fine-Grained AutoAugmentation for Multi-Label Classification

  Access Paper or Ask Questions

A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention


Jul 11, 2021
Zheyi Ma, Hao Li, Wen Fang, Qingwen Liu, Bin Zhou, Zhiyong Bu

Figure 1 for A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention
Figure 2 for A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention
Figure 3 for A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention
Figure 4 for A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention
* 6 pages, 8 figures, INFOCOMW ICCN 2021 
  Access Paper or Ask Questions

LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation


Jul 09, 2021
Dewei Hu, Can Cui, Hao Li, Kathleen E. Larson, Yuankai K. Tao, Ipek Oguz

Figure 1 for LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
Figure 2 for LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
Figure 3 for LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
Figure 4 for LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
* Accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021 
  Access Paper or Ask Questions

Graph Convolution for Re-ranking in Person Re-identification


Jul 05, 2021
Yuqi Zhang, Qian Qi, Chong Liu, Weihua Chen, Fan Wang, Hao Li, Rong Jin

Figure 1 for Graph Convolution for Re-ranking in Person Re-identification
Figure 2 for Graph Convolution for Re-ranking in Person Re-identification
Figure 3 for Graph Convolution for Re-ranking in Person Re-identification
Figure 4 for Graph Convolution for Re-ranking in Person Re-identification

  Access Paper or Ask Questions

Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment


Jun 30, 2021
Di Wu, Siyuan Li, Zelin Zang, Kai Wang, Lei Shang, Baigui Sun, Hao Li, Stan Z. Li

Figure 1 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 2 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 3 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
Figure 4 for Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment

  Access Paper or Ask Questions

Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement


Jun 21, 2021
Huiwen Luo, Koki Nagano, Han-Wei Kung, Mclean Goldwhite, Qingguo Xu, Zejian Wang, Lingyu Wei, Liwen Hu, Hao Li

Figure 1 for Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
Figure 2 for Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
Figure 3 for Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
Figure 4 for Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

Task-Generic Hierarchical Human Motion Prior using VAEs


Jun 07, 2021
Jiaman Li, Ruben Villegas, Duygu Ceylan, Jimei Yang, Zhengfei Kuang, Hao Li, Yajie Zhao

Figure 1 for Task-Generic Hierarchical Human Motion Prior using VAEs
Figure 2 for Task-Generic Hierarchical Human Motion Prior using VAEs
Figure 3 for Task-Generic Hierarchical Human Motion Prior using VAEs
Figure 4 for Task-Generic Hierarchical Human Motion Prior using VAEs

  Access Paper or Ask Questions

An Efficient Training Approach for Very Large Scale Face Recognition


Jun 04, 2021
Kai Wang, Shuo Wang, Zhipeng Zhou, Xiaobo Wang, Xiaojiang Peng, Baigui Sun, Hao Li, Yang You

Figure 1 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 2 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 3 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 4 for An Efficient Training Approach for Very Large Scale Face Recognition
* This is a very effcient framework for ultra-large-scale classification tasks. Our code is available at https://github.com/tiandunx/FFC. We will keep updating! 
  Access Paper or Ask Questions

KVT: k-NN Attention for Boosting Vision Transformers


May 28, 2021
Pichao Wang, Xue Wang, Fan Wang, Ming Lin, Shuning Chang, Wen Xie, Hao Li, Rong Jin

Figure 1 for KVT: k-NN Attention for Boosting Vision Transformers
Figure 2 for KVT: k-NN Attention for Boosting Vision Transformers
Figure 3 for KVT: k-NN Attention for Boosting Vision Transformers
Figure 4 for KVT: k-NN Attention for Boosting Vision Transformers

  Access Paper or Ask Questions

Unsupervised Visual Representation Learning by Online Constrained K-Means


May 24, 2021
Qi Qian, Yuanhong Xu, Juhua Hu, Hao Li, Rong Jin

Figure 1 for Unsupervised Visual Representation Learning by Online Constrained K-Means
Figure 2 for Unsupervised Visual Representation Learning by Online Constrained K-Means
Figure 3 for Unsupervised Visual Representation Learning by Online Constrained K-Means
Figure 4 for Unsupervised Visual Representation Learning by Online Constrained K-Means

  Access Paper or Ask Questions

An Empirical Study of Vehicle Re-Identification on the AI City Challenge


May 20, 2021
Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu, Yuqi Zhang, Chong Liu, Yiqi Jiang, Shuting He, Fan Wang, Hao Li

Figure 1 for An Empirical Study of Vehicle Re-Identification on the AI City Challenge
Figure 2 for An Empirical Study of Vehicle Re-Identification on the AI City Challenge
Figure 3 for An Empirical Study of Vehicle Re-Identification on the AI City Challenge
Figure 4 for An Empirical Study of Vehicle Re-Identification on the AI City Challenge
* CVPR 2021 AI CITY CHALLENGE City-Scale Multi-Camera Vehicle Re-Identification Top 1. arXiv admin note: text overlap with arXiv:2004.10547 
  Access Paper or Ask Questions

Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection


May 19, 2021
Cangning Fan, Fangyi Zhang, Peng Liu, Xiuyu Sun, Hao Li, Ting Xiao, Wei Zhao, Xianglong Tang

Figure 1 for Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
Figure 2 for Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
Figure 3 for Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
Figure 4 for Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection

  Access Paper or Ask Questions

Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations


May 14, 2021
Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li

Figure 1 for Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
Figure 2 for Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
Figure 3 for Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
Figure 4 for Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations

  Access Paper or Ask Questions

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones


May 14, 2021
Chong Liu, Yuqi Zhang, Hao Luo, Jiasheng Tang, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Yi-Dong Shen

Figure 1 for City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Figure 2 for City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Figure 3 for City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Figure 4 for City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
* CVPR 2021 AI CITY CHALLENGE City-Scale Multi-Camera Vehicle Tracking Top 1 
  Access Paper or Ask Questions

Why Does Multi-Epoch Training Help?


May 13, 2021
Yi Xu, Qi Qian, Hao Li, Rong Jin


  Access Paper or Ask Questions

DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement


May 06, 2021
Kanghao Zhang, Shulin He, Hao Li, Xueliang Zhang

Figure 1 for DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement
Figure 2 for DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement
Figure 3 for DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement
Figure 4 for DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement
* 5 pages 
  Access Paper or Ask Questions

Learning to Cluster Faces via Transformer


Apr 23, 2021
Jinxing Ye, Xioajiang Peng, Baigui Sun, Kai Wang, Xiuyu Sun, Hao Li, Hanqing Wu

Figure 1 for Learning to Cluster Faces via Transformer
Figure 2 for Learning to Cluster Faces via Transformer
Figure 3 for Learning to Cluster Faces via Transformer
Figure 4 for Learning to Cluster Faces via Transformer
* Face Transformer 
  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

Figure 1 for A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
Figure 2 for A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
Figure 3 for A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
Figure 4 for A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
* 11 pages. Fixed typos 
  Access Paper or Ask Questions

Spatiotemporal Entropy Model is All You Need for Learned Video Compression


Apr 13, 2021
Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Dongyang Li, Yichen Qian, Hao Li

Figure 1 for Spatiotemporal Entropy Model is All You Need for Learned Video Compression
Figure 2 for Spatiotemporal Entropy Model is All You Need for Learned Video Compression
Figure 3 for Spatiotemporal Entropy Model is All You Need for Learned Video Compression
Figure 4 for Spatiotemporal Entropy Model is All You Need for Learned Video Compression

  Access Paper or Ask Questions

A Theoretical Analysis of Learning with Noisily Labeled Data


Apr 08, 2021
Yi Xu, Qi Qian, Hao Li, Rong Jin


  Access Paper or Ask Questions

Equivariant Point Network for 3D Point Cloud Analysis


Apr 02, 2021
Haiwei Chen, Shichen Liu, Weikai Chen, Hao Li

Figure 1 for Equivariant Point Network for 3D Point Cloud Analysis
Figure 2 for Equivariant Point Network for 3D Point Cloud Analysis
Figure 3 for Equivariant Point Network for 3D Point Cloud Analysis
Figure 4 for Equivariant Point Network for 3D Point Cloud Analysis
* 10 pages, to be published in CVPR2021 
  Access Paper or Ask Questions

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation


Mar 30, 2021
Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng

Figure 1 for Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Figure 2 for Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Figure 3 for Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Figure 4 for Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
* 12 pagess, 4 figures 
  Access Paper or Ask Questions

MogFace: Rethinking Scale Augmentation on the Face Detector


Mar 29, 2021
Yang Liu, Fei Wang, Baigui Sun, Hao Li

Figure 1 for MogFace: Rethinking Scale Augmentation on the Face Detector
Figure 2 for MogFace: Rethinking Scale Augmentation on the Face Detector
Figure 3 for MogFace: Rethinking Scale Augmentation on the Face Detector
Figure 4 for MogFace: Rethinking Scale Augmentation on the Face Detector

  Access Paper or Ask Questions

Guided Training: A Simple Method for Single-channel Speaker Separation


Mar 26, 2021
Hao Li, Xueliang Zhang, Guanglai Gao

Figure 1 for Guided Training: A Simple Method for Single-channel Speaker Separation
Figure 2 for Guided Training: A Simple Method for Single-channel Speaker Separation
Figure 3 for Guided Training: A Simple Method for Single-channel Speaker Separation
Figure 4 for Guided Training: A Simple Method for Single-channel Speaker Separation
* 5 pages 
  Access Paper or Ask Questions

AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks


Mar 25, 2021
Hao Li, Tianwen Fu, Jifeng Dai, Hongsheng Li, Gao Huang, Xizhou Zhu

Figure 1 for AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
Figure 2 for AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
Figure 3 for AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
Figure 4 for AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks

  Access Paper or Ask Questions