Biography

I am an assistant professor in Dept. of Artificial Intelligence at Inha University. Before joining it, I was a postdoctoral researcher in Dept. of Computer Science at Yonsei University. In the past, I collaborated as a visiting researcher with the video understanding team at CLOVA AI Research, hosted by Dr. Taeoh Kim. Also, I was fortunate to visit Microsoft Research Asia as a research intern, working with Dr. Yan Lu and Dr. Jinglu Wang. I obtained my PhD in Computer Science at Yonsei University under the supervision of Prof. Hyeran Byun.

My research interests include computer vision, multimodal learning, video understanding, label-efficient training, model robustness, and generative models.

Notice: This homepage will rarely be updated. Please visit our Multimodal AI Lab for the latest news and updates.

News

2024.09 I have recently taken the role of an assistant professor in Dept. of Artificial Intelligence at Inha University!
2024.07 One paper[1] was accepted to ECCV 2024. I am working on the camera-ready version and code refactoring. Please stay tuned for the following update!
2024.04 I gave an invited talk titled "Weakly-supervised Learning in Computer Vision" at Chung-Ang University, hosted by Prof. Chanho Eom.
2023.12 BAM-DETR[link] is now on arXiv! It resolves two core issues each regarding moment formulation and proposal scoring in DETR-based approaches for temporal sentence grounding.
2023.09 I am now working as a postdoctoral researcher at Yonsei University.
2023.08 I gave a presentation in Doctoral Colloquium at KCCV 2023.
2023.07 Two papers were accepted to ICCV 2023.
2023.06 I successfully completed my PhD defense.
2023.03 One paper was accepted to Neurocomputing (IF: 5.779) (JCR Top-30%).
2023.02 One paper was accepted to CVPR 2023.
2023.01 One paper was accepted to BCI 2023 as Oral presentation.

Education

Mar. 2018 - Aug. 2023 Yonsei University, South Korea
PhD in Computer Science
Mar. 2014 - Feb. 2018 Chung-Ang University, South Korea
BSc in Computer Science & Engineering

Experiences

Sep. 2024 - Present Inha University
Assistant Professor
Sep. 2023 - Aug. 2024 Yonsei University
Postdoctoral Researcher
Feb. 2022 - Jan. 2023 Clova AI Research, NAVER Corp.
Visiting Researcher
Dec. 2019 - Jun. 2020 Microsoft Research Asia
Research Intern

Selected Publications

A full publication list can be found here.

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
Pilhyeon Lee†, Hyeran Byun († Corresponding author)
European Conference on Computer Vision (ECCV), 2024
(Acceptance rate: 2395 / 8585 ≈ 27.9%)
[Paper] [Code]
AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks
Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn, Kunhee Kim, Pilhyeon Lee, Daesik Kim, Youngjung Uh, Hyeran Byun
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
(Acceptance rate: 2160 / 8068 ≈ 26.8%)
[Paper] [Code]
Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations
Seogkyu Jeon, Bei Liu, Pilhyeon Lee, Kibeom Hong, Jianlong Fu, Hyeran Byun
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
(Acceptance rate: 2160 / 8068 ≈ 26.8%)
[Paper]
Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection
Pilhyeon Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Hyeran Byun
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2023
(Acceptance rate: 2360 / 9155 ≈ 25.8%)
[Paper] [Poster] [Slides]
Fair Contrastive Learning for Facial Attribute Classification
Sungho Park, Jewook Lee, Pilhyeon Lee, Sunhee Hwang, Dohyung Kim, Hyeran Byun
IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
(Acceptance rate: 2067 / 8161 ≈ 25.3%)
[Paper] [Code] [Poster]
Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
Sungpil Kho*, Pilhyeon Lee*, Wonyoung Lee, Minsong Ki, Hyeran Byun (* Equal contributions)
Pattern Recognition (PR), 2022
JCR Top-10% (Impact Factor: 8.665)
[Paper]
Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization
Pilhyeon Lee, Hyeran Byun
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Oral Presentation (Acceptance rate: 210 / 6236 ≈ 3.3%)
[Paper] [Code] [Poster] [Slides]
Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
Seogkyu Jeon, Kibeom Hong, Pilhyeon Lee, Jewook Lee, Hyeran Byun
The 29th ACM International Conference on Multimedia (MM), 2021
Oral Presentation (Acceptance rate: 179 / 1942 ≈ 9.2%)
[Paper] [Code]
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
Pilhyeon Lee, Jinglu Wang, Yan Lu, Hyeran Byun
The 35th AAAI Conference on Artificial Intelligence (AAAI), 2021
(Acceptance rate: 1692 / 7911 ≈ 21.4%)
[Paper] [Code] [Poster]
Background Suppression Network for Weakly-supervised Temporal Action Localization
Pilhyeon Lee, Youngjung Uh, Hyeran Byun
The 34th AAAI Conference on Artificial Intelligence (AAAI), 2020
Spotlight Presentation (Acceptance rate: 1591 / 7737 ≈ 20.6%)
[Paper] [Code] [Poster]