Seungryong Kim, Postdoctoral Researcher (김승룡)
 |
Postdoctoral Researcher BC 366, Station 14, CH-1015 Lausanne, Switzerland |
News
08/2019, We are releasing Context-Aware Emotion Recognition (CAER) dataset, posted at TechXplore.
07/2019, Our two papers were accepted to ICCV 2019.
05/2019, Our paper on cross-spectral correspondence was accepted to IEEE TIP.
05/2019, Our paper on unsupervised stereo matching was accepted to IEEE ITS.
05/2019, Our two papers were accepted to ICIP 2019.
03/2019, I have joined the École Polytechnique Fédérale de Lausanne (EPFL), working with Prof. Sabine Süsstrunk and Prof. Pascal Fua.
03/2019, Our two papers were accepted to CVPR 2019.
12/2018, Our paper on high-precision depth estimation was accepted to IEEE ITS.
10/2018, Our paper on stereo confidence estimation was accepted to IEEE TIP.
10/2018, I'm serving as a Publication Chair of ACM Multimedia Workshop- The 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild (CoVieW'18).
09/2018, Our paper on dense semantic correspondence was accepted to IEEE TPAMI.
09/2018, Our paper on dense semantic correspondence was accepted to NeurIPS 2018.
07/2018, Our paper on dense semantic correspondence was accepted to ECCV 2018.
04/2018, I won the 33th Chun-Gang Outstanding Research Award.
01/2018, Our paper on dense semantic correspondence was accepted to IEEE TPAMI.
Research Interest
2-D/3-D Computer Vision, Computational Photography, Machine Learning
Deep Learning, Convolutional Neural Networks
Continuous and Discrete Optimization, Sparse Representation
Image Visual Correspondence and Its Applications
Multi-Sensor and Multi-spectral Vision
3-D Reconstruction, 3-D Modeling
Education
Ph.D. in School of Electrical and Electronics Engineering, Yonsei University, Seoul, Korea (Mar. 2012 ~ Feb. 2018)
Dissertation- Beyond Visual Similarities: Exploring Robust Feature Representation and Regularization for Dense Correspondence
Supervised by Prof. Kwanghoon Sohn
GPA: 4.2/4.3
B.S. in School of Electrical and Electronics Engineering, Yonsei University, Seoul, Korea (Mar. 2008 ~ Feb. 2012)
Graduated Cum Laude
GPA: 3.95/4.3
Experience
Postdoctoral Researcher in École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland (Mar. 2019 ~ Present)
Working with Prof. Sabine Süsstrunk and Prof. Pascal Fua
Postdoctoral Researcher in Yonsei University, Seoul, Korea (Mar. 2018 ~ Feb. 2019)
Working with Prof. Kwanghoon Sohn
Research Intern in Microsoft Research Asia, Beijing, China (Sep 2015 ~ Feb 2016)
Working with Dr. Stephen Lin
Publications - Journal
 |
Pyramidal Semantic Correspondence Networks Sangryul Jeon, Seungryong Kim, Dongbo Min, and Kwanghoon Sohn IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), (Under Review) |
 |
Non-local Feature Synthesis Network for Inpainting Sungil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), (Under Review) |
 |
Tri-modal Recurrent Attention Networks for Emotion Recognition Jiyoung Lee, Sunok Kim, Seungryong Kim, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), (Under Review) |
 |
Learning Adversarial Confidence Measures for Robust Stereo Matching Sunok Kim, Dongbo Min, Seungryong Kim, and Kwanghoon Sohn IEEE Trans. on Intelligent Transportation Systems (TITS), (Major Revision) |
 |
Dense Cross-Modal Correspondence Estimation with the Deep Self-Correlation Descriptor Seungryong Kim, Dongbo Min, Stephen Lin, and Kwanghoon Sohn IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), (Major Revision) |
 |
Learning to Find Unpaired Cross-spectral Correspondences Somi Jeong, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), (Accepted) |
 |
Unsupervised Stereo Matching Using Confidential Correspondence Consistency Sunghun Joung, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE Trans. on Intelligent Transportation Systems (TITS), (Accepted) |
 |
High-precision Depth Estimation Using Uncalibrated LiDAR and Stereo Fusion Kihong Park, Seungryong Kim, and Kwanghoon Sohn IEEE Trans. on Intelligent Transportation Systems (TITS), (Accepted) |
 |
Unified Confidence Estimation Networks for Robust Stereo Matching Sunok Kim, Dongbo Min, Seungryong Kim, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), (Accepted) |
 |
Discrete-Continuous Transformation Matching for Dense Semantic Correspondence Seungryong Kim, Dongbo Min, Stephen Lin, and Kwanghoon Sohn IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), (Accepted) |
 |
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence Seungryong Kim, Dongbo Min, Bumsub Ham, Stephen Lin, and Kwanghoon Sohn IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), vol. 41, no. 3, pp. 581-595, Mar. 2019 |
 |
Unified Multi-spectral Pedestrian Detection Based on Probabilistic Fusion Networks Kihong Park, Seungryong Kim, and Kwanghoon Sohn Pattern Recognition (PR), vol. 80, pp. 143-155, Aug. 2018 |
 |
Feature Augmentation for Learning Confidence Measure in Stereo Matching Sunok Kim, Dongbo Min, Seungryong Kim, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), vol. 26, no. 12, pp. 6019-6033, Dec. 2017 |
 |
DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation Seungryong Kim, Dongbo Min, Bumsub Ham, Minh N. Do, and Kwanghoon Sohn IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 9, pp. 1712-1729, Sep. 2017 |
 |
Modality-Invariant Image Classification Based on Modality Uniqueness and Dictionary Learning Seungryong Kim, Rui Cai, Kihong Park, Sunok Kim, and Kwanghoon Sohn IEEE Trans. on Image Processing (TIP), vol. 26, no. 2, pp. 884-899, Feb. 2017 |
 |
Local Area Transform for Cross Modal Correspondence Matching Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn Pattern Recognition (PR), vol. 63, pp. 218-228, Mar. 2017 |
 |
Fast Illumination-Robust Foreground Detection Using Hierarchical Distribution Map For Real-time Video Surveillance System Jongin Son, Seungryong Kim, and Kwanghoon Sohn Expert Systems With Applications (ESWA), vol. 66, pp. 32-41, Dec. 2016 |
 |
A Multi-Vision Sensor-based Fast Localization System with Image Matching in Challenging Outdoor Environments Jongin Son, Seungryong Kim, and Kwanghoon Sohn Expert Systems With Applications (ESWA), vol. 42, no. 22, pp. 8830-8839, Dec. 2015 |
 |
Mahalanobis Distance Cross-Correlation for Illumination Invariant Stereo Matching Seungryong Kim, Bumsub Ham, Bongjoe Kim, and Kwanghoon Sohn IEEE Trans. on Circuits Syst. Video Technol. (TCSVT), vol. 24, no. 11, pp. 1844-1859, Nov. 2014 |
Publications - Conference
 |
Context-Aware Emotion Recognition Networks Jiyoung Lee, Seungryong Kim, Sunok Kim, Jungin Park, and Kwanghoon Sohn IEEE International Conference on Computer Vision (ICCV), Oct. 2019 |
 |
Joint Learning of Semantic Alignment and Object Landmark Detection Sangryul Jeon, Dongbo Min, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Computer Vision (ICCV), Oct. 2019 |
 |
Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2019 |
 |
Unpaired Cross-Spectral Pedestrian Detection Via Adversarial Feature Learning Minsu Kim, Sunghun Joung, Kihong Park, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2019 |
 |
Semantic Attribute Matching Networks Seungryong Kim, Dongbo Min, Somi Jeong, Sunok Kim, Sangryul Jeon, and Kwanghoon Sohn IEEE Conf. on Computer Vision Pattern Recognition (CVPR), Jun. 2019 (25.2% acceptance rate) |
 |
LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation Sunok Kim, Seungryong Kim, Dongbo Min, and Kwanghoon Sohn IEEE Conf. on Computer Vision Pattern Recognition (CVPR), Jun. 2019 (Oral Presentation) (5.58% acceptance rate) |
 |
Recurrent Transformer Networks for Semantic Correspondence Seungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, and Kwanghoon Sohn Neural Information Processing Systems (NeurIPS), Dec. 2018 (Spotlight Presentation) (3.46% acceptance rate) |
 |
Audio-Visual Attention Networks for Emotion Recognition Jiyoung Lee, Sunok Kim, Seungryong Kim, and Kwanghoon Sohn ACM Multimedia Workshop- Workshop on Audio-Visual Scene Understanding for Immersive Multimedia (MMW), Oct. 2018 |
 |
Learning to Detect, Associate, and Recognize Human Actions and Surrounding Scenes in Untrimmed Videos Jungin Park, Sangryul Jeon, Seungryong Kim, Jiyoung Lee, Sunok Kim, and Kwanghoon Sohn ACM Multimedia Workshop- The 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild (MMW), Oct. 2018 |
 |
CoVieW’18: The 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild Kwanghoon Sohn, Ming-Hsuan Yang, Hyeran Byun, Jongwoo Lim, Jison Hsu, Stephen Lin, Euntai Kim, and Seungryong Kim ACM Multimedia (MM), Oct. 2018 |
 |
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence Estimation Sangryul Jeon, Seungryong Kim, Dongbo Min, and Kwanghoon Sohn European Conference on Computer Vision (ECCV), Sep. 2018 |
 |
Learning Descriptor, Confidence, and Depth Estimation in Multi-view Stereo Sungil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE CVPR Workshop- 1st International Workshop on Deep Learning for Visual SLAM (CVPRW), Jun. 2018 |
 |
Spatiotemporal Attention Based Deep Neural Networks for Emotion Recognition Jiyoung Lee, Sunok Kim, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr. 2018 |
 |
High-precision Depth Estimation with the 3D LiDAR and Stereo Fusion Kihong Park, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Robotics and Automation (ICRA), May 2018 |
 |
DCTM: Discrete-Continuous Transformation Matching for Semantic Flow Seungryong Kim, Dongbo Min, Stephen Lin, and Kwanghoon Sohn IEEE International Conference on Computer Vision (ICCV), Oct. 2017 (Oral Presentation) (2.09% acceptance rate) |
 |
Multi-spectral Human Co-segmentation via Joint Convolutional Neural Networks Sungil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
Unsupervised Stereo Matching Using Correspondence Consistency Sunghun Joung, Seungryong Kim, Bumsub Ham, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
Convolutional Cost Aggregation for Robust Stereo Matching Somi Jeong, Seungryong Kim, Bumsub Ham, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
Convolutional Feature Pyramid Fusion via Attention Network Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
Pedestrian Proposal Generation Using Depth Aware Scale Estimation Kihong Park, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
Deep Stereo Confidence Prediction for Depth Estimation Sunok Kim, Dongbo Min, Bumsub Ham, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2017 |
 |
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence Seungryong Kim, Dongbo Min, Bumsub Ham, Sangryul Jeon, Stephen Lin, and Kwanghoon Sohn IEEE Conf. on Computer Vision Pattern Recognition (CVPR), Jul. 2017 (29% acceptance rate) |
 |
Homography Flow for Dense Correspondences Kihong Park, Seungryong Kim, and Kwanghoon Sohn Asia-Pacific Signal and Information Processing Association Conference (APSIPA), Dec. 2016 |
 |
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields Seungryong Kim, Kihong Park, Kwanghoon Sohn, and Stephen Lin European Conference on Computer Vision (ECCV), Oct. 2016 (Spotlight Presentation) (4.7% acceptance rate) |
| |
Deep Self-Correlation Descriptor for Dense Cross-Modal Correspondence Seungryong Kim, Dongbo Min, Stephen Lin, and Kwanghoon Sohn European Conference on Computer Vision (ECCV), Oct. 2016 (26.6% acceptance rate) |
 |
Multi-spectral Pedestrian Detection Based on Accumulated Object Proposal with Fully Convolution Network Hangil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn IEEE International Conference on Pattern Recognition (ICPR), Dec. 2016 |
 |
ANCC Flow: Adaptive Normalized Cross-Correlation with Evolving Guidance Aggregation for Dense Correspondence Estimation Seungryong Kim, Dongbo Min, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2016 |
 |
Multilevel Segment Based Dense Correspondence: An Affine Transformation Approach Sungil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn Electronic Imaging (EI), Nov. 2016 |
 |
Randomized Global Transformation Approach for Dense Correspondence Kihong Park, Seungryong Kim, Seungchul Ryu, and Kwanghoon Sohn British Machine Vision Conference (BMVC), Sep. 2015 |
 |
Fast Affine-invariant Image Matching Based on Global Bhattacharyya Measure with Adaptive Tree Jongin Son, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Sep. 2015 |
| |
DASC: Dense Adaptive Self-Correlation Descriptor for Multi-modal and Multi-spectral Correspondence Seungryong Kim, Dongbo Min, Bumsub Ham, Seungchul Ryu, Minh N. Do, and Kwanghoon Sohn IEEE Conf. on Computer Vision Pattern Recognition (CVPR), Jun. 2015 (28.4% acceptance rate) |
 |
Statistical Approach for Supervised Codeword Selection Kihong Park, Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn Electronic Imaging (EI), Feb. 2015 |
 |
Robust Stereo Matching Based on Probabilistic Laplacian Propagation with Weighted Mutual Information Junhyung Kim, Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn Electronic Imaging (EI), Feb. 2015 |
 |
Robust Stereo Matching Using Probabilistic Laplacian Surface Propagation Seungryong Kim, Bumsub Ham, Seungchul Ryu, Seon joo Kim, and Kwanghoon Sohn Asian Conference on Computer Vision (ACCV), Nov. 2014 (27.9% acceptance rate) |
 |
Local Self-Similarity Frequency Descriptor for Multispectral Feature Matching Seungryong Kim, Seungchul Ryu, Bumsub Ham, Junhyung Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Oct. 2014 |
 |
Synthesis Quality Prediction Model Based on Distortion Intolerance Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Oct. 2014 |
 |
ABFT: Anisotropic Binary Feature Transform Based on Structure Tensor Space Seungryong Kim, Hunjae Yoo, Seungchul Ryu, Bumsub Ham, and Kwanghoon Sohn IEEE International Conference on Image Processing (ICIP), Oct. 2013 (Top 10% of accepted paper) |
 |
Robust Corner Detector Based on Corner Candidate Region Seungryong Kim, Hunjae Yoo, and Kwanghoon Sohn IEEE Conference on Industrial Electronics and Application (ICIEA), Jun. 2015 |
Domestic Journal/Conference
Journal: 1 papers, Conference: 7 papers (in Korean)
Patent
STEREO CAMERA, USA patent, 14/585,421, Filed on Dec. 2014
STEREO CAMERA, EPO patent, 14200525.5, Filed on Dec. 2014
MATCHING DEVICE AND METHOD BETWEEN MULTI SPECTRAL IMAGES,
Korea patent, 10-2014-0187297, Filed on Dec. 2014
METHOD AND DEVICE FOR MATCHING CORRESPONDENCE POINT OF MULTI SPECTRAL IMAGES,
Korea patent, 10-2014-0178239, Filed on Dec. 2014
STEREO CAMERA, Korea patent, 10-2013-0167035, Filed on Dec. 2013
Awards and Honors
Honorable Mention Award, Research Excellence Award, Yonsei University, 2018
Chun-Gang Outstanding Research Award, Chun-Gang Memorial Foundation, 2018
Doctoral Consortium Award, IEEE ICCV, 2017
Honorable Mention Award, Research Excellence Award, Yonsei University, 2017
Microsoft Research Asia Fellowship Nomination Award, 2016
Runner-up Award, Hackatone Competition, HYUNDAI Motor Group, 2016
Bronze Award, IEEE Student Paper Contest, IEEE Seoul Section, 2012
Volunteer Award, IEEE Broadcast Technology Society, 2012
Honor Graduation Award, Yonsei University, 2012
Excellent Award, COEX 2011 Capstone Design Symposium, 2011
Best Award, Capstone Design Symposium, Korea University, 2011
Best Award, Creative Research Competition, Yonsei University, 2011
Invited Talks
Yonsei University, 2019
DGIST, 2019
NAVER, 2019
Korean Conference on Computer Vision (KCCV), 2019
Korea Fixed Income Research Institute (KFIRI), 2019
HYUNDAI Motor Group, 2018
The Institute of Electronics and Information Engineers (IEIE) Image and Signal Processing Summer School, 2018
The Institute of Electronics and Information Engineers (IEIE) Summer Conference, 2018
Fast Campus, 2018
Ewha Womans University, 2018
Korean Conference on Computer Vision (KCCV), 2018
Korean Conference on Computer Vision (KCCV), 2017
Media Coverages
A deep learning technique for context-aware emotion recognition, TechXplore, 2019
The image-matching algorithm that throws the rest out of the window, Yonsei University Research Blog, 2017
Matching points between objects of different shapes and styles, Microsoft Research Blog, 2017
Collaboration between MSRA and Yonsei University generates computer vision breakthrough, Microsoft Research Blog, 2017
Software Proficiency
C/C++ with OpenCV or OpenGL and Parallel Programming
Python, MATLAB Programming
 |