Publications

Publications : ( C for Conference publications, J for Journal Publications. )

2025

[J24] 🔗   Gee-Sern Jison Hsu, S. Member, IEEE, Wei-Jun Lin, Wei-Chun Hsieh, Wei-Zhe Jian, Sheng-Luen Chung, Marina L. Gavrilova: Style-Preserving Generator for Synthetic License Plate Recognition. IEEE TCSVT: 1-13 (2025)

[C63]🔗   Yu-Ling Chen, Yu-Hsuan Chiu, Ching-Hsun Chang, Gee-Sern Hsu: Dynamic Age Estimation via Mixture of Experts: Bridging Semantic and Structural Models. MVA2025: 1-6

[C62] 🔗   Wei-Zhe Jian Gee-Sern Hsu: Style-Preserving Diffusion for Scene Text Editing. MVA2025: 1-5

[C61] 🔗   Ching-Hsun Chang, Ming-Hao Lee, Yu-Hsuan Chiu, Yi-Min Liao, Sheng-Luen Chung and Gee-Sern Hsu:  Efficient Face Recognition via Representative Synthetic Data.  ICME2025: 1-6 

[C60] 🔗   Ching-Hsun Chang, Ming-Hao Lee, Yu-Hsuan Chiu, Gee-Sern Jison Hsu, Sheng-Luen Chung: Attribut - Specified Generation And Style - Transfer Diffusion For Face Recognition Enhancement.  ICIP2025: 1-6

2024

[C59] 🔗   Md Abu Quwsar Ohi, Gee-Sern Jison Hsu, Marina L Gavrilova: A Novel Laguerre Voronoi Diagram Token Filtering Strategy for Computer Vision Transformers. IEEE: 1-5 (2024)

[C58] 🔗   Wei-Chun Hsieh, Gee-Sern Hsu, Jun-Yi Chen, Moi Hoon Yap, Zi-Chun Chao: Contour-Guided Context Learning for Scene Text Recognition.  ICPR: 103-117 (2024) 

[C57] 🔗   Gee-Sern Jison Hsu, Jie-Ying Zhang, Huang Yu Hsiang, Wei-Jie Hong: Pose adapted shape learning for large-pose face reenactment. CVPR: 7413-7422 (2024)

2023

[C56] 🔗   Gee-Sern Hsu, Yu-Hong Lin, Chin-Cheng Chang: Pretrained Pixel-Aligned Reference Network for 3D Human Reconstruction. CVPR Workshops 2023: 6226-6234 

[C55] 🔗   Jui-Teng Ho, Gee-Sern Hsu, Svetlana N. Yanushkevich, Marina L. Gavrilova: Outline Generation Transformer for Bilingual Scene Text Recognition. MVA 2023: 1-5

2022

[J22] 🔗   Xingdong Cao, Kenneth Lai, Gee-Sern Hsu, Michael R. Smith, Svetlana N. Yanushkevich: Cross-Spectrum Thermal Face Pattern Generator. IEEE Access 10: 9576-9586 (2022) 

[J21] 🔗   Xingdong Cao, Kenneth Lai, Gee-Sern Hsu, Michael R. Smith, Svetlana N. Yanushkevich: Masked Face Recognition From Synthesis to Reality. IEEE Access 10: 37938-37952 (2022) 

[J20] 🔗   Md. Shopon, Gee-Sern Hsu, Marina L. Gavrilova: Multiview Gait Recognition on Unconstrained Path Using Graph Convolutional Neural Network. IEEE Access 10: 54572-54588 (2022)

[J19] 🔗    Yajurv Bhatia, A. S. M. Hossain Bari, Gee-Sern Hsu, Marina L. Gavrilova: Motion Capture Sensor-Based Emotion Recognition Using a Bi-Modular Sequential Neural Network. Sensors 22(1): 403 (2022) 

[C54] 🔗   Gee-Sern Hsu, Chun-Hung Tsai, Hung-Yi Wu: Dual-Generator Face Reenactment. CVPR 2022: 632-640 

[C53] 🔗   Gee-Sern Hsu, Rui-Cang Xie, Zhi-Ting Chen, Yu-Hong Lin: AgeTransGAN for Facial Age Transformation with Rectified Performance Metrics. ECCV (12) 2022: 580-595 

[C52] 🔗   Chia-Hao Tang, Gee-Sern Hsu, Ting-Yu Tai: Graph Refinement with Regression Prior for 3D Face Reconstruction. ICIP 2022: 2436-2440 

[C51] 🔗   Yan-Tsung Peng, Chen-Yu Liu, He-Hao Liao, Wei-Cheng Lien, Gee-Sern Hsu: Traffic Violation Detection via Depth and Gradient Angle Change. ICITE 2022: 326-330

2021

[J18] 🔗   Gee-Sern Hsu, Rui-Cang Xie, Zhi-Ting Chen: Wasserstein Divergence GAN With Cross-Age Identity Expert and Attribute Retainer for Facial Age Transformation. IEEE Access 9: 39695-39706 

[J17] 🔗    Marina L. Gavrilova, Gee-Sern Hsu, Khalid Saeed, Svetlana N. Yanushkevich: IEEE Access Special Section Editorial: Intelligent Biometric Systems for Secure Societies. IEEE Access 9: 71418-71421 (2021) 

[J16] 🔗   Jireh Jam, Connah Kendrick, Kevin Walker, Vincent Drouard, Gee-Sern Hsu, Moi Hoon Yap: A comprehensive review of past and present image inpainting methods. Comput. Vis. Image Underst. 203: 103147 (2021) 

[J15] 🔗    Rui-Cang Xie, Zhi-Ting Chen, Gee-Sern Hsu: Successive Multitask GAN for Age Progression and Regression. J. Inf. Sci. Eng. 37(4): 779-792 (2021) 

[C50] 🔗   Yu-Hong Lin, Chia-Hao Tang, Zhi-Ting Chen, Gee-Sern Hsu, Md. Shopon, Marina L. Gavrilova: Age-Style and Alignment Augmentation for Facial Age Estimation. CAIP (2) 2021: 297-307 

[C49] 🔗   Chia-Hao Tang, Yi-Mei Chou, Gee-Sern Hsu: Multi-View Normalization For Face Recognition. ICIP 2021: 2343-2347 

[C48] 🔗   Gee-Sern Hsu, Hung-Yi Wu: Pose-Guided And Style-Transferred Face Reenactment. ICIP 2021: 2458-2462 

[C47] 🔗   Jireh Jam, Connah Kendrick, Vincent Drouard, Kevin Walker, Gee-Sern Hsu, Moi Hoon Yap: Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting. VISIGRAPP (4: VISAPP) 2021: 35-44 

[C46] 🔗   Jireh Jam, Connah Kendrick, Vincent Drouard, Kevin Walker, Gee-Sern Hsu, Moi Hoon Yap: R-MNet: A Perceptual Adversarial Network for Image Inpainting. WACV 2021: 2713-2722

2020

[J14] 🔗    Gee-Sern Hsu, Wen-Fong Huang, Moi Hoon Yap: Edge-Embedded Multi-Dropout Framework for Real-Time Face Alignment. IEEE Access 8: 6032-6044 (2020) 

[J13] 🔗    Gee-Sern Hsu, Chia-Hao Tang: Dual-View Normalization for Face Recognition. IEEE Access 8: 147765-147775 (2020)  

[J12]  🔗    Gee-Sern Hsu, Rui-Cang Xie, Arul-Murugan Ambikapathi, Kae-Jy Chou: A deep learning framework for heart rate estimation from facial videos. Neurocomputing 417: 155-166 (2020) 

[C45] 🔗   Chia-Hao Tang, Gee-Sern Hsu: Discriminative Representation Learning for Face Recognition. AICV 2020: 574-583 

[C44] 🔗   Gee-Sern Hsu, Hung-Yi Wu, Moi Hoon Yap: A Comprehensive Study on Loss Functions for Cross-Factor Face Recognition. CVPR Workshops 2020: 3604-3611 

[C43] 🔗   Gee-Sern Hsu, Chia-Hao Tang, Svetlana N. Yanushkevich, Marina L. Gavrilova: Contrastive Data Learning for Facial Pose and Illumination Normalization. ICPR 2020: 8336-8343 

2019

[J11]  🔗    Gee-Sern Hsu, Jiunn-Horng Kang, Wen-Fong Huang: Deep Hierarchical Network With Line Segment Learning for Quantitative Analysis of Facial Palsy. IEEE Access 7: 4833-4842 (2019) 

[C42] 🔗   Sheng-Luen Chung, Chih-Fang Chen, Gee-Sern Hsu, Shen-Te Wu: Identification of Partially Occluded Pharmaceutical Blister Packages. AVSS 2019: 1-8 

[C41] 🔗   Gee-Sern Hsu, Chia-Hao Tang, Moi Hoon Yap: Face Synthesis and Recognition Using Disentangled Representation-Learning Wasserstein GAN. CVPR Workshops 2019: 2371-2379 

[C40] 🔗   Chia-Hao Tang, Gee-Sern Hsu, Moi Hoon Yap: Face Recognition with Disentangled Facial Representation Learning and Data Augmentation. ICIP 2019: 1670-1674 

[C39] 🔗   Hung-Yi Wu, Min-Hsiang Chang, Gee-Sern Hsu: Comparison of Face Recognition Loss Functions. ISPACS 2019: 1-2

2018 

[J10] 🔗    Choon-Ching Ng, Moi Hoon Yap, Yi-Tseng Cheng, Gee-Sern Hsu: Hybrid Ageing Patterns for Face Age Estimation. Image Vis. Comput. 69: 92-102 (2018) 

[J9]  🔗     Gee-Sern Hsu, Arul-Murugan Ambikapathi, Sheng-Luen Chung, Hung-Cheng Shie: Robust cross-pose face recognition using Landmark-Oriented depth warping. J. Vis. Commun. Image Represent. 53: 273-280 (2018) 

[J8]  🔗     Gee-Sern Hsu, Hung-Cheng Shie, Cheng-Hua Hsieh, Jui-Shan Chan: Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition. IEEE Trans. Circuits Syst. Video Technol. 28(11):  3194-3207 (2018) 

[C38] 🔗   Gee-Sern Hsu, Min-Hsiang Chang: Deep Hybrid Network for Automatic Quantitative Analysis of Facial Paralysis. AVSS 2018: 1-7 

[C37] 🔗   Gee-Sern Hsu, Wen-Fong Huang, Jiunn-Horng Kang: Hierarchical Network for Facial Palsy Detection. CVPR Workshops 2018: 580-586 

[C36] 🔗   Gee-Sern Hsu, Kang-Chi Ho: Edge-Coupled and Multi-Dropout Face Alignment. ICIP 2018: 2645-2649 

[C35] 🔗   Kwanghoon Sohn, Ming-Hsuan Yang, Hyeran Byun, Jongwoo Lim, Gee-Sern Hsu, Stephen Lin, Euntai Kim, Seungryong Kim:  CoVieW'18: The 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild. ACM Multimedia 2018: 2113-2115 

2017

[C34] 🔗   Gee-Sern Hsu, Arul-Murugan Ambikapathi, Sheng-Luen Chung, Cheng-Po Su: Robust license plate detection in the wild. AVSS 2017: 1-6 

[C33] 🔗   Gee-Sern Hsu, Yi-Tseng Cheng, Choon-Ching Ng, Moi Hoon Yap: Component Biologically Inspired Features with Moving Segmentation for Age Estimation. CVPR Workshops 2017: 540-547 

[C32] 🔗   Gee-Sern Hsu, Arul-Murugan Ambikapathi, Ming-Shiang Chen:  Deep learning with time-frequency representation for pulse estimation from facial videos. IJCB 2017: 383-389 

[C31] 🔗   Gee-Sern Hsu, Cheng-Hua Hsieh: Cross-pose landmark localization using multi-dropout framework. IJCB 2017: 390-396 

[C30] 🔗   Jui-Shan Chan, Gee-Sern Hsu, Hung-Cheng Shie, Yan-Xiang Chen: Face recognition by facial attribute assisted network. ICIP 2017: 3825-3829 

[C29] 🔗   Gee-Sern Hsu, Cheng-Hua Hsieh:  Multi-dropout regression for wide-angle landmark localization. ICIP 2017: 3830-3834 

[C28] 🔗   Choon-Ching Ng, Yi-Tseng Cheng, Gee-Sern Hsu, Moi Hoon Yap: Multi-layer age regression for face age estimation. MVA 2017: 294-297 

2016

[C27] 🔗   Arul-Murugan Ambikapathi, Yi-Tseng Cheng, Gee-Sern Hsu, Cheng-Hua Hsieh: Reliable Age Estimation Based on Apt Gabor Features Selection and SVM. ACCV Workshops (2) 2016: 407-416 

[C26] 🔗   Gee-Sern Hsu, Jun-Wei Huang: A photographer robot with multiview face detector. ICIT 2016: 2152-2156 

[C25] 🔗   Gee-Sern Hsu, Chun-Wei Chiu: A comparison study on real-time tracking motorcycle license plates. IVMSP 2016: 1-5

2015

[J7]    🔗  Gee-Sern Hsu, Hsiao-Chia Peng, Ding-Yu Lin, Chyi-Yeu Lin: Face Recognition Across Poses Using a Single 3D Reference Model. IEICE Trans. Inf. Syst. 98-D(6): 1238-1246 (2015) 

[C24] 🔗  Gee-Sern Hsu, Kai-Hsiang Chang, Shih-Chieh Huang: Regressive Tree Structured Model for Facial Landmark Localization. ICCV 2015: 3855-3861 

[C23] 🔗   Gee-Sern Hsu, Kai-Hsiang Chang, Shih-Chieh Huang, Sheng-Luen Chung: Face detection and landmark localization using Bilayer Tree Structured Model. ICIP 2015: 4303-4307 

[C22] 🔗   Gee-Sern Hsu, Si-De Zeng, Chun-Wei Chiu, Sheng-Luen Chung: A comparison study on motorcycle license plate detection. ICME Workshops 2015: 1-6

2014

[J6]    🔗  Gee-Sern Hsu, Tsu-Ying Chu: A Framework for Making Face Detection Benchmark Databases. IEEE Trans. Circuits Syst. Video Technol. 24(2): 230-241 (2014) 

[J5]    🔗  Gee-Sern Hsu, Yu-Lun Liu, Hsiao-Chia Peng, Po-Xun Wu: RGB-D-Based Face Reconstruction and Recognition. IEEE Trans. Inf. Forensics Secur. 9(12): 2110-2118 (2014) 

[C21]  🔗  Gee-Sern Hsu, Hsiao-Chia Peng, Kai-Hsiang Chang: Landmark Based Facial Component Reconstruction for Recognition across Pose. CVPR Workshops 2014: 34-39 

[C20] 🔗   Gee-Sern Hsu, Yu-Lun Liu, Hsiao-Chia Peng, Sheng-Luen Chung: RGB-D Based Face Reconstruction and Recognition. ICPR 2014: 339-344

2013

[J4]   🔗   Ping-Han Lee, Gee-Sern Hsu, Tsuhan Chen, Yi-Ping Hung: Facial Trait Code. IEEE Trans. Circuits Syst. Video Technol. 23(4): 648-660 (2013) 

[J3]   🔗   Gee-Sern Hsu, Jiun-Chang Chen, Yu-Zu Chung: Application-Oriented License Plate Recognition. IEEE Trans. Veh. Technol. 62(2): 552-561 (2013) 

[C19] 🔗   Dao Huu Hung, Hideo Saito, Gee-Sern Hsu: Detecting Fall Incidents of the Elderly Based on Human-Ground Contact Areas. ACPR 2013: 516-521 

[C18] 🔗   Gee-Sern Hsu, Ding-Yu Lin: Face recognition using sparse representation with illumination normalization and component features. APSIPA 2013: 1-5 

[C17] 🔗   Gee-Sern Hsu, Hsiao-Chia Peng: Face Recognition across Poses Using a Single 3D Reference Model. CVPR Workshops 2013: 869-874 

[C16] 🔗   Gee-Sern Hsu, Shang-Min Yeh: Heterogeneous feature code for expression recognition. ICIP 2013: 2407-2411 

[C15] 🔗   Gee-Sern Hsu, Hsiao-Chia Peng: Pose-Invariant Face Recognition Using A Single 3D Reference Model. MVA 2013: 443-446

2012

[J2]  🔗   Dao Huu Hung, Gee-Sern Hsu, Sheng-Luen Chung, Hideo Saito: Real-Time Counting People in Crowded Areas by Using Local Empirical Templates and Density Ratios. IEICE Trans. Inf. Syst. 95-D(7): 1791-1803 (2012) 

[J1]   🔗   Ping-Han Lee, Gee-Sern Hsu, Yun-Wen Wang, Yi-Ping Hung: Subject-Specific and Pose-Oriented Facial Features for Face Recognition Across Poses. IEEE Trans. Syst. Man Cybern. Part B 42(5): 1357-1368 (2012) 

[C14] 🔗   Gee-Sern Hsu, Truong Tan Loc, Sheng-Luen Chung:  A comparison study on appearance-based object recognition. ICPR 2012: 3500-3503 

[C13] 🔗   Gee-Sern Hsu, Hong Phuoc Nguyen, Chien-Hung Wu, Sheng-Luen Chung: Pedestrian tracking in low contrast regions using aggregated background model and Silhouette Components. ICPR 2012: 3680-3683 

[C12] 🔗   Gee-Sern Hsu, Hsiao-Chia Peng, Shang-Min Yeh: Color and illumination invariant dice recognition. SMC 2012: 857-862

2011

[C11] 🔗   Gee-Sern Hsu, Hsiao-Chia Peng, Chyi-Yeu Lin, Pendry Alexandra: Dice Recognition in Uncontrolled Illumination Conditions by Local Invariant Features. CAIP (2) 2011: 188-195

2010

[C10] 🔗   Dao Huu Hung, Sheng-Luen Chung, Gee-Sern Hsu: Local Empirical Templates and Density Ratios for People Counting. ACCV (4) 2010: 90-101 

[C9]   🔗   Ping-Han Lee, Gee-Sern Hsu, Szu-Wei Wu, Yi-Ping Hung: Robust Face Recognition Using Probabilistic Facial Trait Code. ECCV (1) 2010: 271-284 

[C8]  🔗   Ping-Han Lee, Szu-Wei Wu, Gee-Sern Hsu, Yi-Ping Hung: Probabilistic Facial Trait Code for face recognition. ICIP 2010: 2429-2432 

[C7]  🔗   Gee-Sern Hsu, Thu Ha Tran, Sheng-Luen Chung: Benchmark face detection using a face recognition database. ICIP 2010: 3821-3824 

2009

[C6]  🔗   Ping-Han Lee, Gee-Sern Hsu, Yi-Ping Hung: Polymorphous Facial Trait Code. ACCV (3) 2009: 560-569 

[C5]  🔗   Ping-Han Lee, Gee-Sern Hsu, Yi-Ping Hung: Face verification and identification using Facial Trait Code. CVPR 2009: 1613-1620 

[C4]  🔗   Ping-Han Lee, Gee-Sern Hsu, Tsuhan Chen, Yi-Ping Hung: Real-time 3-D object recognition using Scale Invariant Feature Transform and stereo vision. ICARA 2009: 239-244

2008

[C3]  🔗   Ping-Han Lee, Gee-Sern Hsu, Yi-Ping Hung: Facial Trait Code and Its Application to Face Recognition. ISVC (2) 2008: 317-328

2007

[C2]  🔗   Ping-Han Lee, Yun-Wen Wang, Gee-Sern Hsu, Ming-Hsuan Yang, Yi-Ping Hung: Robust Facial Feature Extraction Using Embedded Hidden Markov Model for Face Recognition under Large Pose Variation. MVA 2007: 392-395 

2006

[C1]  🔗   Ping-Han Lee, Yun-Wen Wang, Ming-Hsuan Yang, Gee-Sern Hsu, Yi-Ping Hung: Distinctive Personal Traits for Face Recognition Under Occlusion. SMC 2006: 4202-4207