Hanjung Kim
4 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
CORL (1)
ECCV (1)
Top co-authors
Keywords
transformer architecture
(1)
semantic segmentation
(1)
video understanding
(1)
video instance segmentation
(1)
object tracking
(1)
temporal learning
(1)
occlusion handling
(1)
temporal action localization
(1)
similarity matching
(1)
query-based learning
(1)
query-based training
(1)
task discrepancy
(1)
feature sequence
(1)
inter-frame similarity
(1)
soft-landing strategy
(1)
Papers
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
CORL 2025
VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
ECCV 2024
A Generalized Framework for Video Instance Segmentation
CVPR 2023
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
CVPR 2023