Yan-Bo Lin

Ph.D. Student

UNC Chapel Hill

yblin [at🥳] cs.unc.edu

I am currently a Ph.D. student in the Department of Computer Science at UNC Chapel Hill and working with Prof. Gedas Bertasius. My research interests lie in the areas of Deep Learning and Computer Vision, particularly multimodal learning with multi-modality data.

Previously, I was fortunate to work with Yen-Yu Lin (NYCU), Ming-Hsuan Yang (UC Merced), and Yu-Chiang Frank Wang (NTU).

I received B.S. degree in Computer Science from National Central University in 2017 and M.S. degree in Communication Engineering from National Taiwan University in 2019.

Updates

[2022-07] One paper is accepted for ECCV 2022! Stay tuned!
[2022-06] I will present our paper ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound at CVPR 2022 workshop on Sight and Sound.
[2021-11] I will present our NeurIPS paper at NeurIPS Taipei Meetup on Dec. 8.
[2021-09] One paper is accepted for NeurIPS 2021!
[2021-09] Serve as a program committee for AAAI 2022.
[2021-06] Our paper Unsupervised Sound Localization via Iterative Contrastive Learning will present in Sight and Sound workshop at CVPR 2021!
[2020-12] One paper is accepted for AAAI 2021!
[2020-09] One paper is accepted for ACCV 2020!
[2020-08] Starting working with Yen-Yu Lin (NCTU) and Ming-Hsuan Yang (UC Merced).
[2019-11] I get Master Thesis Honorable Mention Award by TAAI.
[2019-08] I get Master Thesis Honorable Mention Award by IPPR.
[2019-07] One paper is accepted for ICCV 2019!
[2019-02] One paper is accepted for ICASSP 2019!
[2017-08] Start my master studies at National Taiwan University in Communication Engineering.

B.S., Computer Science
National Central University
Sep. 2013 - Jun. 2017

M.S., Communication Engineering
National Taiwan University
Sep. 2017 - Jun. 2019

Ph.D. Student, Computer Science
UNC Chapel Hill
Aug. 2021 -

Research Intern
National Institute of Informatics
Mar. 2019 - Jun. 2019

Research Assistant
Natioanl Taiwan University
National Chiao Tung University
Aug. 2019 - Jul. 2021

Preprint

Unsupervised Sound Localization via Iterative Contrastive Learning

Preprint
Invited paper talks at CVPR21 workshop on Sight and Sound.
Preprint Demo

Publications

ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound

ECCV 2022 (Oral Presentation)
Preprint Code Demo Project Page BibTex

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

NeurIPS 2021
PDF Code BibTex

Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation

AAAI 2021

Audiovisual Transformer with Instance Attention for Audio-Visual Event Localization

ACCV 2020

Cross-Dataset Person ReIdentification via Unsupervised Pose Disentanglement and Adaptation

ICCV 2019

Dual-modality Seq2seq Network for Audio-Visual Event Localization

ICASSP 2019

Single Channel Source Separation Using Sparse NMF and Graph Regularization

ASE BigData & SocialInformatics 2015 (Best Paper)

Professional Activities

  • Program Committee of T4V: Transformers for Vision workshop at CVPR 2022.
  • Reviewer for AAAI, ECCV, and TPAMI.

Selected Honors

  • TAAI Master Thesis Honorable Mention Award (Nov. 2019)
  • IPPR Master Thesis Honorable Mention Award (Aug. 2019)
  • Undergraduate Research Project First prize (Jun. 2016)
  • Excellent Student Scholarship (Sep. 2016)
  • National Science Council (NSC) fellowship for excellent students (Aug. 2016)
  • ASE International Conference On SocialInformatics Best paper award (Aug. 2015)
  • Dean’s Award (2016 fall, 2015 spring, 2014 fall)