Co-authored paper on addressing data bias problems for chest X-ray image report generation accepted by BMVC 2019.
Published work on adversarial domain adaptation using artificial titles for abstractive title generation at ACL 2019.
Developed ContextualNet for improving image-based localization with LSTMs, published at ICRA 2018.
Contributed to video summarization and captioning research, presented at BMVC 2017.
Ranked convolutional recurrent neural networks for purchase stage identification on imbalanced Twitter data, EACL 2017.
Explored business-aware visual concept discovery for multimodal business venue recognition, AAAI 2016.
Utilized business-aware latent topics for image captioning in social media, IEEE ICME 2016.
Involved in multiple US patents.
Education
Ph.D. in Computer Science, National Taiwan University, Advisors: Prof. Winston H. Hsu and Dr. Mark Liao
Background
My interest lies at the intersection of computer vision, natural language processing, and applied machine learning. I have worked on image/video to text generation, business activity/location recognition, visual/text sentiment analysis, and recently focus on free-text report generation for medical images.