SO
Seoung Wug Oh
cs.CVcs.AIcs.LGeess.IV
On Valency
published · living versionsW_n2ku7bua·v1 · currentpublished
VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token
with Sangbeom Lim, Heeji Yoon, Seungryong Kim, Joon-Young Lee
1 version
Preprints & journals
39 papers in the corpus · 2016–2026VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Token2610.26857v1 · Sangbeom Lim, Seoung Wug Oh, Heeji Yoon et al.2026 · 0 citationsarXivon Valency
ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits2609.00505v1 · Sethuraman T V, Savya Khosla, Onkar Kishor Susladkar et al.2026 · 0 citationsarXiv
Unified Video Dense Prediction from Disjoint Data2607.21592v1 · Yihong Sun, Seoung Wug Oh, Jiahui Huang et al.2026 · 0 citationsarXiv
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation2603.03744v2 · Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh et al.2026 · 0 citationsarXiv
VideoMaMa: Mask-Guided Video Matting via Generative Prior2601.14255v1 · Sangbeom Lim, Seoung Wug Oh, Jiahui Huang et al.2026 · 0 citationsarXiv
FRAME: Pre-Training Video Feature Representations via Anticipation and Memory2506.05543v1 · Sethuraman TV, Savya Khosla, Vignesh Srinivasakumar et al.2025 · 0 citationsarXiv
Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling2503.08605v1 · Subin Kim, Seoung Wug Oh, Jui-Hsien Wang et al.2025 · 1 citationarXiv
Elevating Flow-Guided Video Inpainting with Reference Generation2412.08975v1 · Suhwan Cho, Seoung Wug Oh, Sangyoun Lee et al.2024 · 4 citationsarXiv
IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation2412.04000v2 · Sejong Yang, Seoung Wug Oh, Yang Zhou et al.2024 · 0 citationsarXiv
HARIVO: Harnessing Text-to-Image Models for Video Generation2410.07763v1 · Mingi Kwon, Seoung Wug Oh, Yang Zhou et al.2024 · 4 citationsarXiv
MaGGIe: Masked Guided Gradual Human Instance Matting2404.16035v1 · Chuong Huynh, Seoung Wug Oh, Abhinav Shrivastava et al.2024 · 11 citationsarXiv
VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement2312.04885v2 · Hanjung Kim, Jaehyun Kang, Miran Heo et al.2023 · 6 citationsarXiv
Putting the Object Back into Video Object Segmentation2310.12982v2 · Ho Kei Cheng, Seoung Wug Oh, Brian Price et al.2023 · 148 citationsarXiv
Tracking Anything with Decoupled Video Segmentation2309.03903v1 · Ho Kei Cheng, Seoung Wug Oh, Brian Price et al.2023 · 193 citationsarXiv
In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing2302.04871v4 · Yiran Xu, Zhixin Shu, Cameron Smith et al.2023 · 8 citationsarXiv
Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection2212.10147v1 · Sanghyun Woo, Kwanyong Park, Seoung Wug Oh et al.2022 · 7 citationsarXiv
Tracking by Associating Clips2212.10149v1 · Sanghyun Woo, Kwanyong Park, Seoung Wug Oh et al.2022 · 14 citationsarXiv
A Generalized Framework for Video Instance Segmentation2211.08834v2 · Miran Heo, Sukjun Hwang, Jeongseok Hyun et al.2022 · 52 citationsarXiv
Per-Clip Video Object Segmentation2208.01924v1 · Kwanyong Park, Sanghyun Woo, Seoung Wug Oh et al.2022 · 52 citationsarXiv
One-Trimap Video Matting2207.13353v1 · Hongje Seong, Seoung Wug Oh, Brian Price et al.2022 · 15 citationsarXiv
Error Compensation Framework for Flow-Guided Video Inpainting2207.10391v1 · Jaeyeon Kang, Seoung Wug Oh, Seon Joo Kim2022 · 30 citationsarXiv
VITA: Video Instance Segmentation via Object Token Association2206.04403v2 · Miran Heo, Sukjun Hwang, Seoung Wug Oh et al.2022 · 72 citationsarXiv
Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos2206.02116v1 · Sukjun Hwang, Miran Heo, Seoung Wug Oh et al.2022 · 4 citationsarXiv
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation2112.04177v2 · Su Ho Han, Sukjun Hwang, Seoung Wug Oh et al.2021 · 29 citationsarXiv
Space-Time Memory Networks for Video Object Segmentation With User Guidance.32750815 · Oh, Seoung Wug, Lee, Joon-Young, Xu, Ning et al.2021 · 44 citationsIEEE transactions on pattern analysis and machine intelligence. 2022;44(1):442-455
Hierarchical Memory Matching Network for Video Object Segmentation2109.11404v1 · Hongje Seong, Seoung Wug Oh, Joon-Young Lee et al.2021 · 129 citationsarXiv
Video Instance Segmentation using Inter-Frame Communication Transformers2106.03299v1 · Sukjun Hwang, Miran Heo, Seoung Wug Oh et al.2021 · 76 citationsarXiv
Polygonal Point Set Tracking2105.14584v1 · Gunhee Nam, Miran Heo, Seoung Wug Oh et al.2021 · 4 citationsarXiv
Exemplar-Based Open-Set Panoptic Segmentation Network2105.08336v2 · Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee et al.2021 · 46 citationsarXiv
Single-shot Path Integrated Panoptic Segmentation2012.01632v2 · Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim2020 · 13 citationsarXiv
Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling2007.08786v1 · Subin Jeon, Seonghyeon Nam, Seoung Wug Oh et al.2020 · 9 citationsarXiv
Deep Space-Time Video Upsampling Networks2004.02432v2 · Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh et al.2020 · 19 citationsarXiv
Learning the Loss Functions in a Discriminative Space for Video Restoration2003.09124v1 · Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh et al.2020 · 2 citationsarXiv
DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval2003.09171v1 · Gunhee Nam, Seoung Wug Oh, Joon-Young Lee et al.2020 · 0 citationsarXiv
Copy-and-Paste Networks for Deep Video Inpainting1908.11587v1 · Sungho Lee, Seoung Wug Oh, DaeYeun Won et al.2019 · 148 citationsarXiv
Onion-Peel Networks for Deep Video Completion1908.08718v1 · Seoung Wug Oh, Sungho Lee, Joon-Young Lee et al.2019 · 113 citationsarXiv
Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks1904.09791v2 · Seoung Wug Oh, Joon-Young Lee, Ning Xu et al.2019 · 68 citationsarXiv
Video Object Segmentation using Space-Time Memory Networks1904.00607v2 · Seoung Wug Oh, Joon-Young Lee, Ning Xu et al.2019 · 779 citationsarXiv
Approaching the Computational Color Constancy as a Classification Problem through Deep Learning1608.07951v1 · Seoung Wug Oh, Seon Joo Kim2016 · 99 citationsPattern Recognition, Volume 61, January 2017, Pages 405 to 416
Career total: 50 works. 39 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.