Dongwon Kim
POSTECH Computer vision lab. kdwon@postech.ac.kr
I am a Ph.D student at POSTECH Computer Vision Lab., supervised by Prof. Suha Kwak. I completed my B.S. in computer science and engineering also at POSTECH.
I am currently engaged in research that intersects visual perception with language understanding, focusing on object-centric representation. My aspiration is to delve into the intricacies of how visual objects can be mapped as the lexicon of a unique language, reflecting the compositional and symbolic essence of language where objects are the primary semantic units.
In line with this research interest, I have recently worked on developing effective representation schemes for cross-modal retrieval (DivE) and referring image segmentation with weak supervision (Shatter-Gather).
I am looking for the oppertunities of interesting collaborations and internship! If you are interested in my works or have any questions, please feel free to contact me.
News
Sep 26, 2024 | A paper about object-centric learning is accepted at NeurIPS 2024 |
---|---|
Jun 10, 2024 | One paper is accepted at ECCV 2024 |
Jun 10, 2024 | Joined Bytedance (San Jose, CA) as a research intern |
Mar 14, 2024 | Our paper about referring image segmentation has been accepted at NAACL 2024 main track. |
Dec 7, 2023 | I am really grateful to have been granted the POSTECHIAN fellowship! |
Education
Selected Publications
-
Bootstrapping Top-down Information for Self-modulating Slot AttentionIn Neural Information Processing Systems (NeurIPS), Dec 2024
-
PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part DiscoveryIn European Conference on Computer Vision (ECCV), Oct 2024
-
Extending CLIP’s Image-Text Alignment to Referring Image SegmentationIn Annual Conference on the North American Chapter of the Association for Computational Linguistics (NAACL), Jun 2024
Professional Services
Reviewer
|
Honors and Awards
POSTECHIAN Fellowship, POSTECH, 2023
|