Kaihong Wang (王 锴宏)

kaiwkh@bu.edu

CV

Google Scholar

Github


Biography

I am a third year PhD candidate in the department of Computer Science at Boston University and my advisor is Margrit Betke. I obtained my Master of Science degree in CS at BU in 2020. I am generally interested in topics that seek to minimize human efforts in supervision among various computer vision tasks via domain adaptive approaches, espcially learning from synthetic data.


Research

SG-NMS

BiSIDA

UnsupRecycle-GAN


Publications

Wang K*, Kim D*, Saenko K, Betke M, Sclaroff S, A Unified Framework for Domain Adaptive Pose Estimation, 22 pages, ECCV 2022, Code

Kim D, Wang K, Sclaroff S, Saenko K, A Broad Study of Pre-training for Domain Generalization and Adaptation, 22 pages, ECCV 2022, Code

Wang K, Akash K, Teruhisa M. Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Generated Optical Flow, 13 pages, AAAI 2022, Code

Wang K, Yang C, Betke M. Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation, 9 pages, AAAI 2021, Code

Yang C, Ablavsky V, Wang K, et al. Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes, 17 pages, ECCV 2020, Code

Wang K*, Jalal M*, Jefferson S, et al. Scraping Social Media Photos Posted in Kenya and Elsewhere to Detect and Analyze Food Types[C], Proceedings of the 5th International Workshop on Multimedia Assisted Dietary Management, 10 pages, ACM 2019, Code


Coursework

CS585

CS640


Teaching

2020 Fall: CS440 Artificial Intelligence

2021 Fall: CS506 Computational Tools for Data Science

2022 Spring: CS542 Machine Learning