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 Xilin Chen

Locality-aware Channel-wise Dropout for Occluded Face Recognition


Jul 20, 2021
Mingjie He, Jie Zhang, Shiguang Shan, Xiao Liu, Zhongqin Wu, Xilin Chen


  Access Paper or Ask Questions

Gaze Estimation with an Ensemble of Four Architectures


Jul 05, 2021
Xin Cai, Boyu Chen, Jiabei Zeng, Jiajun Zhang, Yunjia Sun, Xiao Wang, Zhilong Ji, Xiao Liu, Xilin Chen, Shiguang Shan


  Access Paper or Ask Questions

Feature Completion for Occluded Person Re-Identification


Jun 24, 2021
Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen

* IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 
* 18 pages, 17 figures. The paper is accepted by TPAMI, and the code is available at https://github.com/blue-blue272/OccludedReID-RFCnet 

  Access Paper or Ask Questions

Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking


Apr 18, 2021
Shen Li, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen

* Accepted to ICME2018 

  Access Paper or Ask Questions

Visual Alignment Constraint for Continuous Sign Language Recognition


Apr 06, 2021
Yuecong Min, Aiming Hao, Xiujuan Chai, Xilin Chen

* The code will be released: https://github.com/Blueprintf/VAC_CSLR 

  Access Paper or Ask Questions

Attributes Aware Face Generation with Generative Adversarial Networks


Dec 03, 2020
Zheng Yuan, Jie Zhang, Shiguang Shan, Xilin Chen

* 8 pages, 5 figures, 3 tables. Accepted by ICPR2020 

  Access Paper or Ask Questions

Learn an Effective Lip Reading Model without Pains


Nov 15, 2020
Dalu Feng, Shuang Yang, Shiguang Shan, Xilin Chen


  Access Paper or Ask Questions

IAUnet: Global Context-Aware Feature Learning for Person Re-Identification


Sep 02, 2020
Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen

* 14 pages, 9 figures. Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 

  Access Paper or Ask Questions

Appearance-Preserving 3D Convolution for Video-based Person Re-identification


Jul 27, 2020
Xinqian Gu, Hong Chang, Bingpeng Ma, Hongkai Zhang, Xilin Chen

* Accepted by ECCV2020 (Oral) 

  Access Paper or Ask Questions

Temporal Complementary Learning for Video Person Re-Identification


Jul 18, 2020
Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen

* 17 pages, 6 figures, accepted by ECCV2020 

  Access Paper or Ask Questions

Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation


Jul 17, 2020
Wenbin Wang, Ruiping Wang, Shiguang Shan, Xilin Chen

* Accepted by ECCV 2020 

  Access Paper or Ask Questions

SegFix: Model-Agnostic Boundary Refinement for Segmentation


Jul 09, 2020
Yuhui Yuan, Jingyi Xie, Xilin Chen, Jingdong Wang

* ECCV 2020. Project Page: https://github.com/openseg-group/openseg.pytorch 

  Access Paper or Ask Questions

Synchronous Bidirectional Learning for Multilingual Lip Reading


May 12, 2020
Mingshuang Luo, Shuang Yang, Xilin Chen, Zitao Liu, Shiguang Shan

* 12 pages,2 figures,4 tables 

  Access Paper or Ask Questions

Single-Side Domain Generalization for Face Anti-Spoofing


Apr 29, 2020
Yunpei Jia, Jie Zhang, Shiguang Shan, Xilin Chen


  Access Paper or Ask Questions

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training


Apr 13, 2020
Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, Xilin Chen


  Access Paper or Ask Questions

Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation


Apr 09, 2020
Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen

* To appear at CVPR 2020 (Oral) 

  Access Paper or Ask Questions

Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning


Apr 04, 2020
Guoqing Wang, Hu Han, Shiguang Shan, Xilin Chen

* Accepted by CVPR2020 

  Access Paper or Ask Questions

Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text


Mar 31, 2020
Difei Gao, Ke Li, Ruiping Wang, Shiguang Shan, Xilin Chen

* Published as a CVPR2020 paper 

  Access Paper or Ask Questions

Mutual Information Maximization for Effective Lip Reading


Mar 13, 2020
Xing Zhao, Shuang Yang, Shiguang Shan, Xilin Chen

* 8 pages, Accepted in the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) 

  Access Paper or Ask Questions

Deformation Flow Based Two-Stream Network for Lip Reading


Mar 13, 2020
Jingyun Xiao, Shuang Yang, Yuanhang Zhang, Shiguang Shan, Xilin Chen

* 7 pages, FG 2020 

  Access Paper or Ask Questions

Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading


Mar 09, 2020
Mingshuang Luo, Shuang Yang, Shiguang Shan, Xilin Chen

* 8 pages, Accepted in the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) 

  Access Paper or Ask Questions

Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition


Mar 09, 2020
Yuanhang Zhang, Shuang Yang, Jingyun Xiao, Shiguang Shan, Xilin Chen

* 8 pages; accepted in the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) 

  Access Paper or Ask Questions

UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation


Feb 15, 2020
Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Xilin Chen, Ming Zhou


  Access Paper or Ask Questions

Emotion Recognition for In-the-wild Videos


Feb 13, 2020
Hanyu Liu, Jiabei Zeng, Shiguang Shan, Xilin Chen


  Access Paper or Ask Questions

$M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild


Feb 07, 2020
Yuan-Hang Zhang, Rulin Huang, Jiabei Zeng, Shiguang Shan, Xilin Chen

* 6 pages, technical report; submission to ABAW Challenge at FG 2020 

  Access Paper or Ask Questions

Deep Heterogeneous Hashing for Face Video Retrieval


Nov 04, 2019
Shishi Qiao, Ruiping Wang, Shiguang Shan, Xilin Chen

* IEEE Transactions on Image Processing 2019 
* 14 pages, 17 figures, 4 tables, accepted by IEEE Transactions on Image Processing (TIP) 2019 

  Access Paper or Ask Questions

FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task Learning


Nov 04, 2019
Jiancheng Cai, Hu Han, Shiguang Shan, Xilin Chen

* To appear in IEEE Trans. BIOM 

  Access Paper or Ask Questions

RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation


Nov 04, 2019
Xuesong Niu, Shiguang Shan, Hu Han, Xilin Chen


  Access Paper or Ask Questions