SL
Sangbeom Lim
cs.CVcs.AI
On Valency
published · living versionsW_h2mepfcs·v1 · currentpublished
Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
with Siyoon Jin, Dahyun Chung, Honggyu An, Wonjin Nam +3
1 version
W_n2ku7bua·v1published
Preprints & journals
6 papers in the corpus · 2024–2026VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token2610.26857v1 · Sangbeom Lim, Seoung Wug Oh, Heeji Yoon et al.2026 · 0 citationsarXivon Valency
VideoMaMa: Mask-Guided Video Matting via Generative Prior2601.14255v1 · Sangbeom Lim, Seoung Wug Oh, Jiahui Huang et al.2026 · 0 citationsarXiv
Visual Representation Alignment for Multimodal Large Language Models2509.07979v2 · Heeji Yoon, Jaewoo Jung, Junwan Kim et al.2025 · 0 citationsarXiv
URECA: Unique Region Caption Anything2504.05305v1 · Sangbeom Lim, Junwan Kim, Heeji Yoon et al.2025 · 0 citationsarXiv
Referring Video Object Segmentation via Language-aligned Track Selection2412.01136v2 · Seongchan Kim, Woojeong Jin, Sangbeom Lim et al.2024 · 1 citationarXiv
Multi-Granularity Video Object Segmentation2412.01471v2 · Sangbeom Lim, Seongchan Kim, Seungjun An et al.2024 · 0 citationsarXiv
Career total: 8 works. 6 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.