Quoc-Huy Tran CTO at Retrocausal, Inc. 4176 NE 148th Ave, Redmond, WA 98052 Email: huy [at] retrocausal [dot] ai Web: http://cs.adelaide.edu.au/~huy

I am a CTO and Co-Founder at Retrocausal, Inc., a Redmond-based startup building Visual Mistake-Proofing for Manual Assembly (Techstars Accelerator - Seattle 2020 Batch).

I was a Research Staff Member at NEC Labs America, Inc. in San Jose, CA from February 2015 to January 2020, working with Manmohan Chandraker on 3D Scene Understanding with applications in Advanced Driver-Assistance System and Dashcam Video Analysis. Before that, I received my PhD degree in Computer Vision from the University of Adelaide, Australia under the supervision of Tat-Jun Chin and David Suter in December 2014.

LinkedIn - GoogleScholar - ResearchGate

Updates

• [Oct 2022] *NEW* Retrocausal demos PathFinder at ISMAR 2022.
• [Jul 2022] *NEW* Retrocausal is among the top 50 Advanced Manufacturing startups by CB Insights. Read the press release here.
• [Jul 2022] One paper on few-shot video classification is accepted to ECCV 2022.
• [Jun 2022] One paper on weakly-supervised action segmentation is accepted to IROS 2022.
• [Mar 2022] Retrocausal announced a $3.4M funding round. Read the press release here.
• [Mar 2022] One paper on unsupervised action segmentation is accepted to CVPR 2022.
• [Oct 2021] Recordings of our ICCV Workshop on Computer Vision for the Factory Floor (CV4FF) are uploaded.
• [Sep 2021] One paper on few-shot image classification is accepted to NeurIPS 2021.
• [May 2021] Retrocausal won the Judges' Award at Vision Tank Start-Up Competition 2021. Read the announcement here.
• [Apr 2021] I am co-organizing the ICCV Workshop on Computer Vision for the Factory Floor (CV4FF).
• [Feb 2021] One paper on video alignment is accepted to CVPR 2021.
• [Nov 2020] Retrocausal received the Best Demo Award at ISMAR 2020. Read the announcement here.
• [Oct 2020] ThomasNet covers the release of RetroActivity - our human-centric AI solution for quality improvement.
• [Oct 2020] I gave a talk at Global Young Scholars Vietnam.
• [Jul 2020] Three papers on visual odometry, monocular depth estimation, and rolling shutter stitching are accepted to ECCV 2020.
• [Jun 2020] Retrocausal won a SBIR Phase I contract with NASA. Here is the GeekWire article, with cover photo featuring our project.

Papers

	1. AI-Mediated Job Status Tracking in AR as a No-Code Service A. Konin, S. Siddiqui, H. Gilani, M. Mudassir, M. H. Ahmed, T. Shaukat, M. Naufil, A. Ahmed, Q.-H. Tran, M. Zeeshan Zia IEEE International Symposium on Mixed and Augmented Reality Demonstration (ISMAR Demo), 2022 Link - PDF - Demo
	2. Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments K. D. Nguyen, Q.-H. Tran, K. Nguyen, B.-S. Hua, R. Nguyen European Conference on Computer Vision (ECCV), 2022 Link - PDF - Supp [Project page & code]
	3. Timestamp-Supervised Action Segmentation with Graph Convolutional Networks H. Khan, S. Haresh, A. Ahmed, S. Siddiqui, A. Konin, M. Z. Zia, Q.-H. Tran IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 Link - PDF - Supp [Project page]
	4. Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering S. Kumar†, S. Haresh†, A. Ahmed, A. Konin, M. Z. Zia, Q.-H. Tran IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Link - PDF - Supp - Talk [Project page]
	5. POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples D. H. Le†, K. D. Nguyen†, K. Nguyen, Q.-H. Tran, R. Nguyen, B.-S. Hua 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 Link - PDF - Supp [Project page & code]
	6. Learning by Aligning Videos in Time S. Haresh†, S. Kumar†, H. Coskun, S. N. Syed, A. Konin, M. Z. Zia, Q.-H. Tran IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Link - PDF - Supp - Talk [Project page]
	7. RetroActivity: Rapidly Deployable Live Task Guidance Experiences [Best Demo Award] A. Konin, S. N. Syed, S. Siddiqui, S. Kumar, Q.-H. Tran, M. Zeeshan Zia IEEE International Symposium on Mixed and Augmented Reality Demonstration (ISMAR Demo), 2020 Link - PDF - Demo
	8. Towards Anomaly Detection in Dashcam Videos S. Haresh†, S. Kumar†, M. Z. Zia, Q.-H. Tran IEEE Intelligent Vehicles Symposium (IV), 2020 Link - PDF - Dataset - Talk
	9. Image Stitching and Rectification for Hand-Held Cameras B. Zhuang, Q.-H. Tran European Conference on Computer Vision (ECCV), 2020 Link - PDF - Supp - Talk [Project page]
	10. Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction L. Tiwari*, P. Ji, Q.-H. Tran, B. Zhuang, S. Anand, M. Chandraker European Conference on Computer Vision (ECCV), 2020 Link - PDF - Supp - Talk [Project page]
	11. Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling Y. Zou*, P. Ji, Q.-H. Tran, J.-B. Huang, M. Chandraker European Conference on Computer Vision (ECCV), 2020 Link - PDF - Supp - Talk [Project page]
	12. Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM B. Zhuang*, Q.-H. Tran, G. H. Lee, L. F. Cheong, M. Chandraker IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019 Link - PDF - Supp - Slides [Project page]
	13. Learning Structure-And-Motion-Aware Rolling Shutter Correction [Oral Presentation] B. Zhuang*, Q.-H. Tran, P. Ji, L. F. Cheong, M. Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 Link - PDF - Supp - Slides [Project page]
	14. Deep Supervision with Intermediate Concepts C. Li*, M. Z. Zia, Q.-H. Tran, X. Yu, G. D. Hager, M. Chandraker IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018 Link - PDF [Project page]
	15. Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences M. E. Fathy*, Q.-H. Tran, M. Z. Zia, P. Vernaza, M. Chandraker European Conference on Computer Vision (ECCV), 2018 Link - PDF - Supp - Poster [Project page]
	16. Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing C. Li*, M. Z. Zia, Q.-H. Tran, X. Yu, G. D. Hager, M. Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 Link - PDF - Supp - Poster Rendered images (Car) - Rendered images (Chair+Sofa) - Annotated CAD models - Annotated KITTI images [Project page]
	17. A Continuous Occlusion Model for Road Scene Understanding V. Dhiman*, Q.-H. Tran, J. J. Corso, M. Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 Link - PDF - Supp - Poster
	18. Robust Parameter Estimation in Computer Vision: Geometric Fitting and Deformable Registration Q.-H. Tran PhD Thesis, Australian Centre for Visual Technologies, University of Adelaide, 2014 Link - PDF
	19. As-Projective-As-Possible Image Stitching with Moving DLT J. Zaragoza, T.-J. Chin, Q.-H. Tran, M. S. Brown, D. Suter IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014 Link - PDF - Supp [Project page & code]
	20. Sampling Minimal Subsets with Large Spans for Robust Estimation Q.-H. Tran, T.-J. Chin, W. Chojnacki, D. Suter International Journal of Computer Vision (IJCV), 2013 Link - PDF
	21. In Defence of RANSAC for Outlier Rejection in Deformable Registration Q.-H. Tran, T.-J. Chin, G. Carneiro, M. S. Brown, D. Suter European Conference on Computer Vision (ECCV), 2012 Link - PDF - Supp Code

Patents

1. Systems and Methods for Determining Sub-Activities in Videos and Segmenting the Videos with Little to No Annotation (US Patent Application)
2. System and Method for Learning Human Activities from Video Demonstrations Using Video Augmentation (US Patent Application)
3. System and Method for Correlating Video Frames in a Computing Environment (US Patent)
4. System and Method for Management and Evaluation of One or More Human Activities (US Patent)
5. System and Method for Building Computational Models of a Goal-Driven Task from Demonstration (US Patent)
6. Joint Rolling Shutter Image Stitching and Rectification (US Patent Application)
7. Joint Rolling Shutter Correction and Image Deblurring (US Patent)
8. Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction (US Patent)
9. Self-Supervised Visual Odometry Framework Using Long-Term Modeling and Incremental Learning (US Patent)
10. Image/Video Deblurring Using Convolutional Neural Networks with Applications to SFM/SLAM with Blurred Images/Videos (US Patent)
11. Multi-Task Perception Network with Applications to Scene Understanding and Advanced Driver-Assistance System (US Patent)
12. Rolling Shutter Rectification Using Convolutional Neural Networks with Applications to SFM/SLAM with Rolling Shutter Images/Videos (US Patent)
13. Learning Good Features for Visual Odometry (US Patent)
14. Aerial Drone Utilizing Pose Estimation (US Patent)
15. Dense Three-Dimensional Correspondence Estimation with Multi-Level Metric Learning and Hierarchical Matching (US Patent)
16. Dense Correspondence Estimation with Multi-Level Metric Learning and Hierarchical Matching (US Patent)
17. Computer Aided Traffic Enforcement Using Dense Correspondence Estimation with Multi-Level Metric Learning and Hierarchical Matching (US Patent)
18. Landmark Localization on Objects in Images Using Convolutional Neural Networks (US Patent)
19. Advanced Driver-Assistance System with Landmark Localization on Objects in Images Using Convolutional Neural Networks (US Patent)
20. Surveillance System with Landmark Localization on Objects in Images Using Convolutional Neural Networks (US Patent)
21. Action Recognition System with Landmark Localization on Objects in Images Using Convolutional Neural Networks (US Patent)

Activities

• Conference Reviewers: International Conference on Computer Vision (ICCV), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), European Conference on Computer Vision (ECCV), International Conference on 3D Vision (3DV), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IAPR Conference on Machine Vision Applications (MVA)
• Workshop Reviewers: Workshop on 3D Reconstruction in the Wild (3DRW) (in conjunction with ECCV/ICCV), Workshop on Visual Odometry and Computer Vision Applications Based on Location Clues (VOCVALC) (in conjunction with CVPR)
• Journal Reviewers: International Journal of Computer Vision (IJCV), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Robotics (T-RO), IEEE Robotics and Automation Letters (RA-L), ISPRS Journal of Photogrammetry and Remote Sensing (JPRS), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Journal of Computer Graphics Forum (CGF), Neurocomputing Journal (NEUCOM), The Visual Computer Journal (TVCJ), IEEE Journal of Selected Topics in Signal Processing (STSP), IEEE Signal Processing Letters (SPL)

Awards, Grants & Scholarships

• Top 50 Advanced Manufacturing Startups by CB Insights, 2022
• Judges' Award at Vision Tank Start-Up Competition, 2021
• Best Demo Award at IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2020
• NASA SBIR Phase I Grant ($125K), 2020
• Dean's Commendation for Doctoral Thesis Excellence, 2014
• International Postgraduate Research Scholarship (IPRS), 2011-2014
• Australian Postgraduate Award (APA), 2011-2014
• Scholarship of Pony Chung Foundation - Hyundai Motor Company, 2009
• Bronze Medal in Vietnam National Olympiad in Informatics (VNOI), 2005
• Gold Medal in Mekong River Delta Olympiad in Informatics, 2005