Seungryong Kim, Postdoctoral Researcher (김승룡)

Seungryong Kim at Switzerland 

Postdoctoral Researcher
Digital Image Media Lab.
Department of Electrical and Electronic Engineering
Yonsei University

The 3rd Engineering Building, Yonsei University
50 Yonsei-ro, Seodaemun-Gu, Seoul 120-749, Korea
Phone: +82 2 2123 2879
Fax: +82 2 2123 7712
Email: srkim89@yonsei.ac.kr

[Curriculum Vitae]

News

  • 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 NIPS 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.

  • 12/2017, Our paper on dense cross-modal correspondence in TPAMI 2017 was posted at Yonsei Research Blog.

  • 11/2017, Our paper on dense semantic correspondence in ICCV 2017 was posted at Microsoft Research Blog.

  • 08/2017, Our paper on stereo confidence estimation was accepted to IEEE TIP.

  • 07/2017, Our paper on dense semantic correspondence was accepted to ICCV 2017.

  • 05/2017, Our joint MSRA-Yonsei project was posted at Microsoft Research Blog.

  • 05/2017, Our 6 papers were accepted to IEEE ICIP 2017.

  • 02/2017, Our paper on dense semantic correspondence was accepted to IEEE CVPR 2017.

  • 11/2016, Our paper on modality-invariant image classification was accepted to IEEE TIP.

  • 11/2016, I received Microsoft Research Asia Fellowship Nomination Award 2016.

  • 08/2016, Our paper on cross-modal dense correspondence was accepted to IEEE TPAMI.

  • 08/2016, Our paper on cross-modal correspondence was accepted to PR.

  • 08/2016, Our paper on foreground detection was accepted to ESWA.

  • 08/2016, Our team ranked top 2 on Hackatone Competition of HYUNDAI Motor Group.

  • 07/2016, Our 2 papers on multi-modal dense visual correspondence and joint depth/intrinsic inference were accepted to ECCV 2016.

  • 07/2016, Our paper on multi-spectral pedestrian detection was accepted to ICPR 2016.

  • 05/2016, Our paper on dense visual correspondence was accepted to ICIP 2016.

  • I joined Microsoft Research Asia to work with Stephen Lin as research intern from Sep. 2015 to Feb. 2016.

[Top]

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

[Top]

Education

[Top]

Publications - Journal

Seungryong Kim, IJCV2018 Dense Cross-Modal Correspondence Estimation with the Deep Self-Correlation Descriptor
  Seungryong Kim, Dongbo Min, Stephen Lin, and Kwanghoon Sohn
  International Journal of Computer Vision (IJCV), (Under Review)
Seungryong Kim, PR2018 Unsupervised Stereo Matching Using Confidential Correspondence Consistency
  Sunghun Joung, Seungryong Kim, kihong Park, and Kwanghoon Sohn
  IEEE Trans. on Intelligent Transportation Systems (TITS), (Under review)
Seungryong Kim, TITS2018 High-precision Depth Estimation Using Uncalibrated LiDAR and Stereo Fusion
  Kihong Park, Seungryong Kim, and Kwanghoon Sohn
  IEEE Trans. on Intelligent Transportation Systems (TITS), (Major Revision)
Seungryong Kim, TIP2017 Unified Confidence Estimation Networks for Robust Stereo Matching
  Sunok Kim, Dongbo Min, Seungryong Kim, and Kwanghoon Sohn
  IEEE Trans. on Image Processing (TIP), (Minor Revision)
Seungryong Kim, TPAMI2017 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)
Seungryong Kim, TPAMI2017 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), (Accepted)
Seungryong Kim, PR2017 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
Seungryong Kim, TIP2017 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
Seungryong Kim, TPAMI2015 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
Seungryong Kim, TIP2016 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
Seungryong Kim, PR2015 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
Seungryong Kim, ESWA2016 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
Seungryong Kim, ESWA2015 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
Seungryong Kim, TCSVT2014 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

[Top]

Publications - Conference

Seungryong Kim, NIPS2018 Recurrent Transformer Networks for Semantic Correspondence
  Seungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, and Kwanghoon Sohn
  Neural Information Processing Systems (NIPS), Dec. 2018 (Spotlight Presentation) (3.46% acceptance rate)
Seungryong Kim, MMW2018 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
Seungryong Kim, MMW2018 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
Seungryong Kim, ECCV2018 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
Seungryong Kim, CVPRW2018 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
Seungryong Kim, ICASSP2018 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
Seungryong Kim, ICRA2018 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
Seungryong Kim, ICCV2017 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)
Seungryong Kim, ICIP2017 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
Seungryong Kim, ICIP2017 Unsupervised Stereo Matching Using Correspondence Consistency
  Sunghun Joung, Seungryong Kim, Bumsub Ham, and Kwanghoon Sohn
  IEEE International Conference on Image Processing (ICIP), Sep. 2017
Seungryong Kim, ICIP2017 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
Seungryong Kim, ICIP2017 Convolutional Feature Pyramid Fusion via Attention Network
  Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn
  IEEE International Conference on Image Processing (ICIP), Sep. 2017
Seungryong Kim, ICIP2017 Pedestrian Proposal Generation Using Depth Aware Scale Estimation
  Kihong Park, Seungryong Kim, and Kwanghoon Sohn
  IEEE International Conference on Image Processing (ICIP), Sep. 2017
Seungryong Kim, ICIP2017 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
Seungryong Kim, arxiv2017 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)
Seungryong Kim, APSIPA2016 Homography Flow for Dense Correspondences
  Kihong Park, Seungryong Kim, and Kwanghoon Sohn
  Asia-Pacific Signal and Information Processing Association Conference (APSIPA), Dec. 2016
Seungryong Kim, ECCV2016 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)
Seungryong Kim, ECCV2016 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)
Seungryong Kim, ICPR2016 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
Seungryong Kim, ICIP2016 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
Seungryong Kim, EI2016 Multilevel Segment Based Dense Correspondence: An Affine Transformation Approach
  Sungil Choi, Seungryong Kim, Kihong Park, and Kwanghoon Sohn
  Electronic Imaging (EI), Nov. 2016
Seungryong Kim, BMVC2015 Randomized Global Transformation Approach for Dense Correspondence
  Kihong Park, Seungryong Kim, Seungchul Ryu, and Kwanghoon Sohn
  British Machine Vision Conference (BMVC), Sep. 2015
Seungryong Kim, ICIP2015 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
Seungryong Kim, CVPR2015 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)
Seungryong Kim, EI2015 Statistical Approach for Supervised Codeword Selection
  Kihong Park, Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn
  Electronic Imaging (EI), Feb. 2015
Seungryong Kim, EI2015 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
Seungryong Kim, ACCV2014 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)
Seungryong Kim, ICIP2014 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
Seungryong Kim, ICIP2014 Synthesis Quality Prediction Model Based on Distortion Intolerance
  Seungchul Ryu, Seungryong Kim, and Kwanghoon Sohn
  IEEE International Conference on Image Processing (ICIP), Oct. 2014
Seungryong Kim, ICIP2013 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)
Seungryong Kim, ICIEA2013 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

[Top]

Domestic Journal/Conference

  • Journal: 1 papers, Conference: 7 papers (in Korean)

[Top]

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

[Top]

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

[Top]

Invited Talks

  • 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), 2017, 2018

[Top]

Media Coverage

  • 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

[Top]

Software Proficiency

  • C/C++ with OpenCV or OpenGL and Parallel Programming

  • Python, MATLAB Programming

[Top]

words