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 Shifeng Zhang

Shifeng Zhang

OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression


Nov 02, 2021
Chen Zhang, Shifeng Zhang, Fabio Maria Carlucci, Zhenguo Li

Figure 1 for OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
Figure 2 for OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
Figure 3 for OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
Figure 4 for OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression

  Access Paper or Ask Questions

iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder


Nov 01, 2021
Shifeng Zhang, Ning Kang, Tom Ryder, Zhenguo Li

Figure 1 for iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder
Figure 2 for iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder
Figure 3 for iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder
Figure 4 for iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder
* Accepted for NeurIPS 2021 Spotlight 
  Access Paper or Ask Questions

iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression


Mar 30, 2021
Shifeng Zhang, Chen Zhang, Ning Kang, Li Zhenguo

Figure 1 for iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
Figure 2 for iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
Figure 3 for iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
Figure 4 for iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression

  Access Paper or Ask Questions

Loss Function Search for Face Recognition


Jul 10, 2020
Xiaobo Wang, Shuo Wang, Cheng Chi, Shifeng Zhang, Tao Mei

Figure 1 for Loss Function Search for Face Recognition
Figure 2 for Loss Function Search for Face Recognition
Figure 3 for Loss Function Search for Face Recognition
Figure 4 for Loss Function Search for Face Recognition
* Accepted by ICML2020. arXiv admin note: substantial text overlap with arXiv:1912.00833; text overlap with arXiv:1905.07375 by other authors 
  Access Paper or Ask Questions

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection


Dec 05, 2019
Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li

Figure 1 for Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Figure 2 for Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Figure 3 for Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Figure 4 for Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

  Access Paper or Ask Questions

Mis-classified Vector Guided Softmax Loss for Face Recognition


Nov 26, 2019
Xiaobo Wang, Shifeng Zhang, Shuo Wang, Tianyu Fu, Hailin Shi, Tao Mei

Figure 1 for Mis-classified Vector Guided Softmax Loss for Face Recognition
Figure 2 for Mis-classified Vector Guided Softmax Loss for Face Recognition
Figure 3 for Mis-classified Vector Guided Softmax Loss for Face Recognition
Figure 4 for Mis-classified Vector Guided Softmax Loss for Face Recognition
* Accepted by AAAI2020 as Oral presentation. arXiv admin note: substantial text overlap with arXiv:1812.11317 
  Access Paper or Ask Questions

WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild


Sep 25, 2019
Shifeng Zhang, Yiliang Xie, Jun Wan, Hansheng Xia, Stan Z. Li, Guodong Guo

Figure 1 for WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Figure 2 for WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Figure 3 for WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Figure 4 for WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
* TMM: submitted on 2018.07.17, accepted on 2019.07.01. arXiv admin note: text overlap with arXiv:1805.07193, arXiv:1805.00123 by other authors 
  Access Paper or Ask Questions

Relational Learning for Joint Head and Human Detection


Sep 24, 2019
Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Figure 1 for Relational Learning for Joint Head and Human Detection
Figure 2 for Relational Learning for Joint Head and Human Detection
Figure 3 for Relational Learning for Joint Head and Human Detection
Figure 4 for Relational Learning for Joint Head and Human Detection

  Access Paper or Ask Questions

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes


Sep 15, 2019
Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Figure 1 for PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Figure 2 for PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Figure 3 for PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Figure 4 for PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

  Access Paper or Ask Questions

DARTS+: Improved Differentiable Architecture Search with Early Stopping


Sep 13, 2019
Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He, Weiran Huang, Kechen Zhuang, Zhenguo Li

Figure 1 for DARTS+: Improved Differentiable Architecture Search with Early Stopping
Figure 2 for DARTS+: Improved Differentiable Architecture Search with Early Stopping
Figure 3 for DARTS+: Improved Differentiable Architecture Search with Early Stopping
Figure 4 for DARTS+: Improved Differentiable Architecture Search with Early Stopping

  Access Paper or Ask Questions

RefineFace: Refinement Neural Network for High Performance Face Detection


Sep 10, 2019
Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li

Figure 1 for RefineFace: Refinement Neural Network for High Performance Face Detection
Figure 2 for RefineFace: Refinement Neural Network for High Performance Face Detection
Figure 3 for RefineFace: Refinement Neural Network for High Performance Face Detection
Figure 4 for RefineFace: Refinement Neural Network for High Performance Face Detection
* Journal extension of our previous conference paper: arXiv:1809.02693. arXiv admin note: text overlap with arXiv:1901.02350 by other authors 
  Access Paper or Ask Questions

CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing


Aug 28, 2019
Shifeng Zhang, Ajian Liu, Jun Wan, Yanyan Liang, Guogong Guo, Sergio Escalera, Hugo Jair Escalante, Stan Z. Li

Figure 1 for CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
Figure 2 for CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
Figure 3 for CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
Figure 4 for CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
* Journal extension of our previous conference paper: arXiv:1812.00408 
  Access Paper or Ask Questions

WIDER Face and Pedestrian Challenge 2018: Methods and Results


Feb 19, 2019
Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jianfeng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou

Figure 1 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 2 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 3 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
Figure 4 for WIDER Face and Pedestrian Challenge 2018: Methods and Results
* Report of ECCV 2018 workshop: WIDER Face and Pedestrian Challenge 
  Access Paper or Ask Questions

Pairwise Teacher-Student Network for Semi-Supervised Hashing


Feb 02, 2019
Shifeng Zhang, Jianmin Li, Bo Zhang

Figure 1 for Pairwise Teacher-Student Network for Semi-Supervised Hashing
Figure 2 for Pairwise Teacher-Student Network for Semi-Supervised Hashing
Figure 3 for Pairwise Teacher-Student Network for Semi-Supervised Hashing
Figure 4 for Pairwise Teacher-Student Network for Semi-Supervised Hashing

  Access Paper or Ask Questions

Improved Selective Refinement Network for Face Detection


Jan 23, 2019
Shifeng Zhang, Rui Zhu, Xiaobo Wang, Hailin Shi, Tianyu Fu, Shuo Wang, Tao Mei, Stan Z. Li

Figure 1 for Improved Selective Refinement Network for Face Detection
Figure 2 for Improved Selective Refinement Network for Face Detection
Figure 3 for Improved Selective Refinement Network for Face Detection
Figure 4 for Improved Selective Refinement Network for Face Detection
* Technical report, 8 pages, 6 figures 
  Access Paper or Ask Questions

Support Vector Guided Softmax Loss for Face Recognition


Dec 29, 2018
Xiaobo Wang, Shuo Wang, Shifeng Zhang, Tianyu Fu, Hailin Shi, Tao Mei

Figure 1 for Support Vector Guided Softmax Loss for Face Recognition
Figure 2 for Support Vector Guided Softmax Loss for Face Recognition
Figure 3 for Support Vector Guided Softmax Loss for Face Recognition
Figure 4 for Support Vector Guided Softmax Loss for Face Recognition

  Access Paper or Ask Questions

CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing


Dec 23, 2018
Shifeng Zhang, Xiaobo Wang, Ajian Liu, Chenxu Zhao, Jun Wan, Sergio Escalera, Hailin Shi, Zezheng Wang, Stan Z. Li

Figure 1 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing
Figure 2 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing
Figure 3 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing
Figure 4 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing
* 10 pages, 8 figures, 6 tables 
  Access Paper or Ask Questions

CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-Spoofing


Dec 02, 2018
Shifeng Zhang, Xiaobo Wang, Ajian Liu, Chenxu Zhao, Jun Wan, Sergio Escalera, Hailin Shi, Zezheng Wang, Stan Z. Li

Figure 1 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-Spoofing
Figure 2 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-Spoofing
Figure 3 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-Spoofing
Figure 4 for CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-Spoofing
* 10 pages, 8 figures, 6 tables 
  Access Paper or Ask Questions

ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch


Oct 19, 2018
Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei

Figure 1 for ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch
Figure 2 for ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch
Figure 3 for ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch
Figure 4 for ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch
* 14 pages, 9 figures, submitted to AAAI2019 
  Access Paper or Ask Questions

Selective Refinement Network for High Performance Face Detection


Sep 07, 2018
Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Figure 1 for Selective Refinement Network for High Performance Face Detection
Figure 2 for Selective Refinement Network for High Performance Face Detection
Figure 3 for Selective Refinement Network for High Performance Face Detection
Figure 4 for Selective Refinement Network for High Performance Face Detection
* The first two authors have equal contributions. Corresponding author: Shifeng Zhang ([email protected]) 
  Access Paper or Ask Questions

Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd


Jul 23, 2018
Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li

Figure 1 for Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
Figure 2 for Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
Figure 3 for Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
Figure 4 for Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
* Accepted by ECCV 2018 
  Access Paper or Ask Questions

Semantic Cluster Unary Loss for Efficient Deep Hashing


May 15, 2018
Shifeng Zhang, Jianmin Li, Bo Zhang

Figure 1 for Semantic Cluster Unary Loss for Efficient Deep Hashing
Figure 2 for Semantic Cluster Unary Loss for Efficient Deep Hashing
Figure 3 for Semantic Cluster Unary Loss for Efficient Deep Hashing
Figure 4 for Semantic Cluster Unary Loss for Efficient Deep Hashing
* 12 pages 
  Access Paper or Ask Questions

Ensemble Soft-Margin Softmax Loss for Image Classification


May 10, 2018
Xiaobo Wang, Shifeng Zhang, Zhen Lei, Si Liu, Xiaojie Guo, Stan Z. Li

Figure 1 for Ensemble Soft-Margin Softmax Loss for Image Classification
Figure 2 for Ensemble Soft-Margin Softmax Loss for Image Classification
Figure 3 for Ensemble Soft-Margin Softmax Loss for Image Classification
Figure 4 for Ensemble Soft-Margin Softmax Loss for Image Classification
* Accepted by IJCAI 2018 
  Access Paper or Ask Questions

Single-Shot Refinement Neural Network for Object Detection


Jan 03, 2018
Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li

Figure 1 for Single-Shot Refinement Neural Network for Object Detection
Figure 2 for Single-Shot Refinement Neural Network for Object Detection
Figure 3 for Single-Shot Refinement Neural Network for Object Detection
Figure 4 for Single-Shot Refinement Neural Network for Object Detection
* 14 pages, 7 figures, 7 tables 
  Access Paper or Ask Questions

FaceBoxes: A CPU Real-time Face Detector with High Accuracy


Jan 03, 2018
Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li

Figure 1 for FaceBoxes: A CPU Real-time Face Detector with High Accuracy
Figure 2 for FaceBoxes: A CPU Real-time Face Detector with High Accuracy
Figure 3 for FaceBoxes: A CPU Real-time Face Detector with High Accuracy
Figure 4 for FaceBoxes: A CPU Real-time Face Detector with High Accuracy
* Accepted by IJCB 2017; Added references 
  Access Paper or Ask Questions

S$^3$FD: Single Shot Scale-invariant Face Detector


Nov 15, 2017
Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li

Figure 1 for S$^3$FD: Single Shot Scale-invariant Face Detector
Figure 2 for S$^3$FD: Single Shot Scale-invariant Face Detector
Figure 3 for S$^3$FD: Single Shot Scale-invariant Face Detector
Figure 4 for S$^3$FD: Single Shot Scale-invariant Face Detector
* Accepted by ICCV 2017 + its supplementary materials; Updated the latest results on WIDER FACE 
  Access Paper or Ask Questions

Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization


Sep 28, 2016
Shifeng Zhang, Jianmin Li, Jinma Guo, Bo Zhang

Figure 1 for Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
Figure 2 for Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
Figure 3 for Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
Figure 4 for Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization

  Access Paper or Ask Questions