Kuan-Hui Lee

Biosketch

My research area focuses on computer vision and machine learning in autonomous driving. 

Since Feb 2023,  I joined Rivian as a Deep Learning Manager, continue working on perception for self driving and advanced driver assistance system (ADAS).

Since May 2016, I joined Toyota Research Institute as a research scientist, focusing on machine learning topics in perception for autonomous driving.

I had internship at MERL in summer 2015, and the research topic is about 3-D reconstruction/localization and image retrieval.

I joined Prof. Jenq-Neng Hwang’s research group from 2011,  started my Ph.D. career in EE, UW from 2012, and got my Ph.D. in 2015.

Before my journey of Ph.D. career, I was a research assistant in ECE, UMN and EE, NTU, doing the multimedia development with GPGPU / CUDA in 2010. 

From 2007 ~ 2009, I was a member of multimedia development department of HTC, developing the YouTube / streaming player on smart phone.

Research

Conference

• V. Guizilini, K.-H. Lee, R. Ambruş and A. Gaidon, "Learning optical flow, depth, and scene flow without real-world labels," IEEE Robotics and Automation Letters/International Conf. Robotics and Automation (RAL/ICRA), Apr. 2022. (arxiv)

• N. Rai, E. Adeli, K.-H. Lee, A. Gaidon and J. C. Niebles, "CoCon: Cooperative-contrastive learning," IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshop (CVPRW), Jun. 2021. (arxiv)(github)

• X. Wang, S. Zhang, K.-H. Lee, H. Peng, "An interaction-aware evaluation method for highly automated vehicles," IEEE International Conf. Intelligent Transportation Systems (ITSC), Sep. 2021. (arxiv)

• K. Mangalam, H. Girase, S. Agarwal, K.-H. Lee, E. Adeli, J. Malik, and A. Gaidon, "It is not the journey but the destination: Endpoint conditioned trajectory prediction," European Conference on Computer Vision (ECCV), Aug. 2020. (arxiv)(github)

• S. Shiroshita, S. Maruyama, D. Nishiyama, M. Y. Castro, K. Hamzaoui, G. Rosman, J. DeCastro, K.-H. Lee, and A. Gaidon, "Behaviorally diverse traffic simulation via reinforcement learning," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2020 (arxiv).

• K.-H. Lee, M. Kliemann, A. Gaidon, J. Li, C. Fang, S. Pillai, and W. Burgard, "PillarFlow: End-to-end birds-eye-view flow estimation for autonomous driving," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2020. (arxiv)

• D. Nishiyama, M. Y. Castro, S. Maruyama, S. Shiroshita, K. Hamzaoui,Y. Ouyang, G. Rosman, J. DeCastro, K.-H. Lee and A. Gaidon, "Discovering avoidable planner failures of autonomous vehicles using counterfactual analysis in behaviorally diverse simulation," IEEE International Conf. Intelligent Transportation Systems (ITSC), Sep. 2020 (arxiv).

• B. Pan, H. Cai, D.-A. Huang, K.-H. Lee, A. Gaidon E. Adeli, and J. C. Niebles, "Spatio-temporal graph for video captioning with knowledge distillation," IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Jun. 2020. (arxiv)

• B. Liu, E. Adeli, Z. Cao, K.-H. Lee, A. Shenoi, A. Gaidon and J. C. Niebles, "Spatiotemporal relationship reasoning for pedestrian intent prediction," IEEE Robotics and Automation Letters/International Conf. Robotics and Automation (RAL/ICRA), Jun. 2020. (arxiv)

• K. Mangalam, E. Adeli, K.-H. Lee, A. Gaidon and J. C. Niebles, "Disentangling human dynamics for pedestrian locomotion forecasting with noisy supervision," IEEE Winter Conf. Applications of Computer Vision (WACV), Mar. 2020. (arxiv)

• K.-H. Lee, T. Tagawa, J.-E. M. Pan, A. Gaidon and B. Douillard, "An attention-based recurrent convolutional network for vehicle taillight recognition," IEEE Intelligent Vehicles Symposium (IV), Jun. 2019. (arxiv)

• K.-H. Lee, G. Ros, J. Li and A. Gaidon, "SPIGAN: Privileged adversarial learning from simulation," International Conf. Learning Representations (ICLR), May 2019. (arxiv)

• K.-H. Lee, Y. Kanzawa, M. Derry, M. R. James, "Multi-target track-to-track fusion based on permutation matrix track association," IEEE Intelligent Vehicles Symposium (IV), Jun. 2018.

• H.-K. Hsu, Y.-H. Tsai, X. Mei, K.-H. Lee, N. Nagasaka, D. Prokhorov, M.-H. Yang, "Learning to tell brake and turn signals in videos using CNN-LSTM structure," IEEE International Conf. Intelligent Transportation Systems (ITSC), Oct. 2017. (dataset)

• Z. Tang, Y.-S. Lin, K.-H. Lee, J.-N. Hwang, J.-H. Chuang, Z. Fang, "Camera self-calibration from tracking of moving persons," International Conf. Pattern Recognition (ICPR), Dec. 2016.

• X. Chen, J.-N. Hwang, K.-H. Lee, and R. L. de Queiroz, "Quality-of-content (QoC)-driven rate allocation for video analysis in mobile surveillance networks," IEEE International Workshop. Multimedia Signal Processing (MMSP), Oct. 2015. (pdf)

• L. Hou, W. Wan, K.-H. Lee, J.-N. Hwang, G. Okopal, and J. Pitton, "Deformable multiple-kernel based human tracking using a moving camera," IEEE International Conf. Acoustics, Speech, and Signal Processing (ICASSP), Apr. 2015. (pdf)(site)

• K.-H. Lee, J.-N. Hwang, G. Okopal, and J. Pitton, "Driving recorder based on-road pedestrian tracking using visual SLAM and constrained multiple-kernel," IEEE International Conf. Intelligent Transportation Systems (ITSC), pp. 2629－2635, Oct. 2015. (pdf)(site)

• K.-H. Lee, Y.-J. Lee, and J.-N. Hwang, "Multiple-kernel based vehicle tracking using 3-D deformable model and license plate self-similarity," IEEE International Conf. Acoustics, Speech, and Signal Processing (ICASSP), pp. 1793－1797, May 2013 (pdf)

• C.-T. Chu, K.-H. Lee, and J.-N. Hwang, "Self-organized and scalable camera networks for systematic human tracking across nonoverlapping cameras," IEEE International Conf. Acoustics, Speech, and Signal Processing (ICASSP), pp. 2322－2326, May 2013. (pdf)

• K.-H. Lee, J.-N. Hwang, J.-Y. Yu, and K.-Z. Lee, "Vehicle tracking iterative by Kalman-based constrained multiple-kernel and 3-D model-based localization", IEEE International Symposium on Circuits and Systems (ISCAS), May 2013. (pdf)

• K.-H. Lee, J.-N. Hwang, J. Yoo, and K. Choi “Effective car video retrieval using feature matching in a mobile video cloud,” 6th ACM/IEEE International Conf. Distributed Smart Camera (ICDSC), Nov. 2012. (pdf)

Journal / Transactions

• X. Chen, J.-N. Hwang, D. Meng, K.-H. Lee, R. L de Queiroz, F.-M. Yeh, "A Quality-of-Content-Based Joint Source and Channel Coding for Human Detections in a Mobile Surveillance Cloud," IEEE Trans. Circuits and Systems for Video Technology (T-CSVT), vol.27, no.1, pp. 19－31, Jan. 2017.

• L.  Hou, W. Wan, K.-H. Lee, J.-N. Hwang, G. Okopal and J. Pitton, "Robust human tracking based on DPM constrained multiple-kernel from a moving camera," Springer J. Signal Processing Systems, vol.86, no.1, pp. 27－39, Jan. 2017.

• S.-C. Huang, B.-H. Chen, S.-K. Chou, J.-N. Hwang, and K.-H. Lee, "Smart Car," IEEE Computational Intelligence Magazine (CIM), vol.11, no.4, pp. 46－58, Oct. 2016.

• K.-H. Lee, J.-N. Hwang, G. Okopal, and J. Pitton, "Ground-moving-platform-based human tracking using visual SLAM and constrained multiple kernels," IEEE Trans. Intelligent Transportation Systems (T-ITS), vol.17, no.12, pp. 3602－3612, May 2016. (pdf)(site)

• K.-H. Lee and J.-N. Hwang, "On-road pedestrian tracking across multiple driving recorders," IEEE Trans. Multimedia (T-MM), Special Issue - Multimedia: The Biggest Big Data, vol.17, no.9, pp. 1429－1438, Jul. 2015. (pdf)(site)

• K.-H. Lee, J.-N. Hwang, and S.-I Chen "Model-based vehicle localization based on three-dimensional constrained multiple-kernel tracking," IEEE Trans. Circuits and Systems for Video Technology (T-CSVT), vol.25, no.1, pp. 38－50, Jun. 2014. (pdf)(site)

• K.-H. Lee and P.-C. Chung, "An attention emphasized bit arrangement in 3-D SPIHT video coding for human vision," Elsevier J. Visual Communication and Image Representation (JVCI), vol.24, no.3, pp. 255－269, Apr. 2013.

Book Chapter

• K.-H. Lee, C.-T. Chu, Y. Lee, Z. Fang, and J.-N. Hwang, “Consistent human tracking over self-organized and scalable multiple-camera networks,” Distributed Embedded Smart Cameras, New York, NY, USA: Springer, pp. 189－209, 2014.

Thesis

• PhD: K.-H. Lee and J.-N. Hwang, Dynamic object tracking and 3-D visualization from big visual data, Seattle, US: University of Washington, 2015.

• MS: K.-H. Lee and P.-C. Chung, A Motion Emphasized 3-D SPIHT for Visual Improved Video Coding, Tainan, Taiwan: National Cheng Kung University, 2005.