News

GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank AdaptationSohyun Lee, Yeho Gwon, Lukas Hoyer and Suha KwakAdvances in Neural Information Processing Systems (NeurIPS), San Diego, 2025Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction DetectionDongkeun Kim, Minsu Ch..

Enhancing Cost Efficiency in Active Learning with Candidate Set QueryYeho Gwon, Sehyun Hwang, Hoyoung Kim, Jungseul Ok, and Suha KwakTransactions on Machine Learning Research (TMLR), 2025

Latent Expression Generation for Referring Image Segmentation and GroundingSeonghoon Yu, Junbeom Hong, Joonseok Lee, Jeany SonIEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, Hawaii, 2025Online Generic Event Boundary DetectionHyung Rok Jung*, Daneul Kim*, Seunggyun Lim, Jeany S..

GENIUS: A Generative Framework for Universal Multimodal SearchSungyeon Kim, Xinliang Zhu, Xiaofan Lin, Muhammet Bastan, Douglas Gray, Suha KwakIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025Improving Sound Source Localization with Joint Slot Attention on Image ..

Decoupled Finetuning for Domain Generalizable Semantic SegmentationJaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, Suha KwakInternational Conference on Learning Representations (ICLR), Singapore, 2025

Boosting Semi-supervised Video Action Detection with Temporal ContextDonghyeon Kwon, Inho Kim, Suha KwakIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, Arizona, 2025Oral presentationOral presentation,Learning Unified Distance Metric Across Diverse Data Distributions wit..

ActFusion: a Unified Diffusion Model for Action Segmentation and AnticipationDayoung Gong, Suha Kwak, Minsu ChoConference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics PredictionJongmin Lee, Minsu ChoConference..

3D Geometric Shape Assembly via Efficient Point Cloud MatchingNahyuk Lee*, Juhong Min*, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, Minsu ChoInternational Conference on Machine Learning (ICML), Vienna, Austria, 2024Improving Robustness to Multiple Spurious Correlations by Multi-Objective Opt..

Extending CLIP's Image-Text Alignment to Referring Image SegmentationSeoyeon Kim, Minguk Kang, Dongwon Kim, Jaesik Park, Suha KwakAnnual Conference on the North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2024

Learning SO(3)-Invariant Semantic Correspondence via Local Shape TransformChunghyun Park*, Seungwook Kim*, Jaesik Park, Minsu ChoIEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 2024Enhancing 3D Fidelity of Text-to-3D using Cross-View CorrespondencesSeungwook Kim, Kejie Li..

Seungwook Kim's paper got included in the best paper finalist at WACV 2024.

Efficient Semantic Matching with Hypercolumn CorrelationSeungwook Kim, Juhong Min, Minsu ChoIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, 2024Oral presentationBest paper finalistSelf-supervised Learning of Semantic Correspondence Using Web VideosDonghyeon Kw..