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 Xiaolin Hu

RSG: A Simple but Effective Module for Learning Imbalanced Datasets

Jun 18, 2021
Jianfeng Wang, Thomas Lukasiewicz, Xiaolin Hu, Jianfei Cai, Zhenghua Xu

* To appear at CVPR 2021. We propose a flexible data generation/data augmentation module for long-tailed classification. Codes are available at: 

  Access Paper or Ask Questions

Convolutional Neural Networks with Gated Recurrent Connections

Jun 05, 2021
Jianfeng Wang, Xiaolin Hu

* Accepted by TPAMI. An extension of our previous NeurIPS 2017 paper "Gated recurrent convolution neural network for OCR". We demonstrate the good performance of GRCNN on image classification and object detection. Codes are available at: 

  Access Paper or Ask Questions

Attack on practical speaker verification system using universal adversarial perturbations

May 19, 2021
Weiyi Zhang, Shuning Zhao, Le Liu, Jianmin Li, Xingliang Cheng, Thomas Fang Zheng, Xiaolin Hu

* 6 pages, 2 figures 

  Access Paper or Ask Questions

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

Apr 17, 2021
Gang Zhang, Xin Lu, Jingru Tan, Jianmin Li, Zhaoxiang Zhang, Quanquan Li, Xiaolin Hu

* Accepted by CVPR 2021. Code is available at 

  Access Paper or Ask Questions

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Apr 12, 2021
Chufeng Tang, Hang Chen, Xiao Li, Jianmin Li, Zhaoxiang Zhang, Xiaolin Hu

* CVPR 2021 

  Access Paper or Ask Questions

CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds

Mar 02, 2021
Ge Gao, Mikko Lauri, Xiaolin Hu, Jianwei Zhang, Simone Frintrop

* Accepted to ICRA 2021 

  Access Paper or Ask Questions

Rethinking Natural Adversarial Examples for Classification Models

Feb 23, 2021
Xiao Li, Jianmin Li, Ting Dai, Jie Shi, Jun Zhu, Xiaolin Hu

* 12 pages 

  Access Paper or Ask Questions

Annotation Cleaning for the MSR-Video to Text Dataset

Feb 12, 2021
Haoran Chen, Jianmin Li, Simone Frintrop, Xiaolin Hu

  Access Paper or Ask Questions

Frame Difference-Based Temporal Loss for Video Stylization

Feb 11, 2021
Jianjin Xu, Zheyang Xiong, Xiaolin Hu

  Access Paper or Ask Questions

Fooling thermal infrared pedestrian detectors in real world using small bulbs

Jan 20, 2021
Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, Xiaolin Hu

* accepted by AAAI-21 

  Access Paper or Ask Questions

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

Nov 25, 2020
Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang

  Access Paper or Ask Questions

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

Jun 20, 2020
Tianren Zhang, Shangqi Guo, Tian Tan, Xiaolin Hu, Feng Chen

  Access Paper or Ask Questions

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Jun 08, 2020
Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang

* 14 pages, 14 figures 

  Access Paper or Ask Questions

Delving Deeper into the Decoder for Video Captioning

Feb 15, 2020
Haoran Chen, Jianmin Li, Xiaolin Hu

* 8 pages, 3 figures, European Conference on Artificial Intelligence 

  Access Paper or Ask Questions

End-to-End Face Parsing via Interlinked Convolutional Neural Networks

Feb 12, 2020
Zi Yin, Valentin Yiu, Xiaolin Hu, Liang Tang

  Access Paper or Ask Questions

6D Object Pose Regression via Supervised Learning on Point Clouds

Jan 24, 2020
Ge Gao, Mikko Lauri, Yulong Wang, Xiaolin Hu, Jianwei Zhang, Simone Frintrop

  Access Paper or Ask Questions

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Oct 10, 2019
Chufeng Tang, Lu Sheng, Zhaoxiang Zhang, Xiaolin Hu

* Accepted by ICCV 2019 

  Access Paper or Ask Questions

Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork

Oct 07, 2019
Yulong Wang, Xiaolin Hu, Hang Su

* Accepted to 2019 ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models 

  Access Paper or Ask Questions

Pruning from Scratch

Sep 27, 2019
Yulong Wang, Xiaolu Zhang, Lingxi Xie, Jun Zhou, Hang Su, Bo Zhang, Xiaolin Hu

* 12 pages, 9 figures 

  Access Paper or Ask Questions

A Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling

Aug 31, 2019
Haoran Chen, Ke Lin, Alexander Maye, Jianming Li, Xiaolin Hu

* Submitted to Frontiers in Robotics & AI 

  Access Paper or Ask Questions

Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks

May 25, 2019
Xiang Li, Xiaolin Hu, Jian Yang

* Code available at: 

  Access Paper or Ask Questions

Knowledge Distillation via Route Constrained Optimization

Apr 19, 2019
Xiao Jin, Baoyun Peng, Yichao Wu, Yu Liu, Jiaheng Liu, Ding Liang, Junjie Yan, Xiaolin Hu

  Access Paper or Ask Questions

Dynamic Multi-path Neural Network

Apr 07, 2019
Yingcheng Su, Shunfeng Zhou, Yichao Wu, Tian Su, Ding Liang, Jiaheng Liu, Dixin Zheng, Yingxu Wang, Junjie Yan, Xiaolin Hu

  Access Paper or Ask Questions

Selective Kernel Networks

Mar 18, 2019
Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang

* CVPR 2019 

  Access Paper or Ask Questions

Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation

Mar 15, 2019
Wei Feng, Wentao Liu, Tong Li, Jing Peng, Chen Qian, Xiaolin Hu

* AAAI2019 

  Access Paper or Ask Questions

UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision

Sep 06, 2018
Yi Zhang, Weichao Qiu, Qi Chen, Xiaolin Hu, Alan Yuille

* 3DV 2018 (oral) 

  Access Paper or Ask Questions

Interlinked Convolutional Neural Networks for Face Parsing

Jun 07, 2018
Yisu Zhou, Xiaolin Hu, Bo Zhang

* International Symposium on Neural Networks. Springer, Cham, 2015 
* 11 pages, 4 figures, ISNN2015 Conference 

  Access Paper or Ask Questions

Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser

May 08, 2018
Fangzhou Liao, Ming Liang, Yinpeng Dong, Tianyu Pang, Xiaolin Hu, Jun Zhu

* CVPR 2018 

  Access Paper or Ask Questions