Seunghoon Lee

5 papers · 2023–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13)

Venues

WACV (2) AAAI (1) CVPR (1) ICLR (1)

Top co-authors

Sangyoun Lee (3) Suhwan Cho (3) Minhyeok Lee (3) Chaewon Park (2) Yoonji Lee (1) YoungBin Kim (1) Donghyeong Kim (1) Samson Zhou (1) Dogyoon Lee (1) Tamalika Mukherjee (1)

Research topics

Machine Learning (4) Learning Types (4) Computer Vision (3) Processing (3) Deep Learning (2) Architectures (2) Computer Science (1) Security & Privacy (1) Analysis (1) Core Methods (1) Differential Privacy (1) Foundations (1) Techniques (1)

Keywords

video object segmentation (3) unsupervised learning (3) optical flow (2) feature extraction (1) prototype learning (1) self-supervised learning (1) attention mechanism (1) machine unlearning (1) model forgetting (1) loss landscape (1) appearance model (1) gradient descent (1) streaming algorithm (1) salient object detection (1) heavy hitter (1) bias mitigation (1) spurious correlation (1) motion information (1) temporal fusion (1) motion cue (1)

Papers

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias AAAI 2026 Dual Prototype Attention for Unsupervised Video Object Segmentation CVPR 2024 Differentially Private L_2-Heavy Hitters in the Sliding Window Model ICLR 2023 Treating Motion as Option To Reduce Motion Dependency in Unsupervised Video Object Segmentation WACV 2023 Unsupervised Video Object Segmentation via Prototype Memory Network WACV 2023