photo

Nam-Gyu Cho

Email : southq (at) korea (dot) ac (dot) kr

Phone : +82-2-3290-3572

Address : 145, Anam-ro Seongbuk-gu, Seoul, 02841, Korea

About Me

I joined T-Brain, SK Telecom Nov. 2017. Previously I was a Postdoctoral Researcher at Korea University working on Human Activity Detection. I received my Ph.D. from Korea University, working with Prof. Seong-Whan Lee (and Prof. Alan Yuille for the first three years). My research interests are computer vision and machine learning. My current focus is exploiting deep learning for solving computer vision prolems.

Over the course of my Ph.D. I participated in several projects: human behavior understanding using the Kinect sensor at Korea University (2010 - now), human body parsing at Korea University (2011 - 2013), constructing a large scale dataset at Korea University and UCLA (2011 - 2014), geometry estimation and perceptual organization methods for assisting visually impaired people at UCLA (2013 - 2014), and deep learning-based remote sensing image understanding at Korea University (2016 - now).

Publication - International

  • N.-G. Cho, A. Yuille, and S.-W. Lee, “A novel linelet-based representation for line segment detection,” IEEE Transaction on Pattern Analysis and Machine Intelligence, 10.1109/TPAMI.2017.2703841, 2017. [Code]
  • N.-G. Cho, S.-H. Park, J.-S. Park, U. Park, and S.-W. Lee, “Compositional interaction descriptor for human interaction recognition,” Neurocomputing, 10.1016/j.neucom.2017.06.009, 2017.
  • N.-G. Cho, Y.-J. Kim, U. Park, J.-S. Park, and S.-W. Lee, “Group activity recognition with group interaction zone based on relative distance between human objects,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 29, no. 05, p. 1555007, 2015.
  • Y.-J. Kim, N.-G. Cho, and S.-W. Lee, “Group activity recognition with group interaction zone,” in 22nd International Conference on Pattern Recognition, pp. 3517–3521, Aug 2014.
  • R. Mottaghi, X. Chen, X. Liu, N.-G. Cho, S.-W. Lee, S. Fidler, R. Urtasun, and A. Yuille, “The role of context for object detection and semantic segmentation in the wild,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 891–898, June 2014.
  • N.-G. Cho and S.-W. Lee, “Incorporating global and local observation models for human pose tracking,” IEEE RO-MAN, pp. 25-30, 2013.
  • N.-G. Cho, A. Yuille, and S.-W. Lee, “Adaptive occlusion state estimation for human pose tracking under self-occlusions,” Pattern Recognition, vol. 46, no. 3, pp. 649–661, 2013.
  • N.-G. Cho, A. Yuille, and S.-W. Lee, “Self-occlusion robust 3d human pose tracking from monocular image sequence,” in Proceedings of IEEE International Conference on Systems, Man and Cybernetics, pp. 254–257, 2012.
  • N.-G. Cho, A. Yuille, and S.-W. Lee, “Nonflat observation model and adaptive depth order estimation for 3d human pose tracking,” in Proceedings of IEEE First Asian Conference on Pattern Recognition, pp. 382–386, 2011.

Publication - Domestic

  • 윤다혜, 조남규, 이성환, "Modeling temporal subclasses of action for online action localization from untrimmed video stream," 뇌와 인공지능 하계워크숖, PS-04, 2017.
  • 송현승, 조남규, 이성환, "Siamese structure convolutional neural network for aerial image registration," 한국군사과학기술학회 종합학술대회, pp. 1414-1415, 2017.
  • 곽인엽, 조남규, 이성환, "단안 영상으로부터 복원된 3차원 궤적을 이용한 도심 주행 시나리오에서의 보행자-차량 충돌 예측," 뇌와 인공지능 하계워크숖, pp. P-7, 2016.
  • 이상준, 조남규, 이성환, "Spatio-Temporal Action Descriptor 기반 시점 변화에 강인한 개인 행동 인식," 2015년 한국컴퓨터종합학술대회 논문집, pp. 841-843, 2015.
  • 조남규, 이성환, "Linelet 기반 디지털 영상 속 라인 세그먼트 검출," 2015년 한국컴퓨터종합 학술대회 논문집, pp. 876-878, 2015.
  • 박세호, 조남규, 이성환, "Actionlet Gradient를 이용한 휴먼 상호 행동 인식," 한국정보과학회 제41회 정기총회 및 동계학술발표회, 2014.
  • 김영지, 조남규, 이성환, "개별 휴먼 객체간 거리 변화 특성에 따른 상호 작용 영역 기반의 그룹 행동 인식," 26회 영상처리 및 이해에 관한 워크샵, P-145, 2014.
  • 조남규, Alan Yuille, 이성환, "Introduction to KU dataset for object parsing, scene segmentation, and scene 3D geometry estimation," 뇌와 인공지능 심포지엄, 2013, PS-19.
  • 조남규, Alan Yuille, 이성환, "인체 구성요소 분석을 위한 변형 가능한 구성 모델," 한국인지과학회 춘계학술대회논문집, pp. 136, 2012.
  • 조남규, Alan Yuille, 이성환, "Hierarchical configural deformable templates for human body parsing under self-occlusion," 뇌와 인공지능 심포지엄, 2012.
  • 조남규, 이성환, "3차원 인체 포즈 추적을 위한 가려짐에 강인한 관측치 모델," 한국컴퓨터종합학술대회 논문집, pp. 390-392, 2011.
  • 조남규, 이성환, "연속적인 단안 영상에서의 3차원 인체 포즈 추적을 위한 적응적인 자체 가려짐 추론 방법," 제 37회 한국정보과학회 추계학술발표회 발표 논문집, pp. 348-351, 2010.