Jeongseok Hyun
5 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
WACV (2)
CVPR (1)
ECCV (1)
ICCV (1)
Top co-authors
Keywords
model compression
(1)
transformer architecture
(1)
semantic segmentation
(1)
online learning
(1)
feature extraction
(1)
video understanding
(1)
video instance segmentation
(1)
object tracking
(1)
efficient computing
(1)
multi-object tracking
(1)
temporal learning
(1)
occlusion handling
(1)
vision-language model
(1)
temporal action localization
(1)
token merging
(1)
video large language model
(1)
graph neural network
(1)
query-based learning
(1)
query-based training
(1)
action localizer
(1)
Papers
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
ICCV 2025
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization
WACV 2025
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
ECCV 2024
A Generalized Framework for Video Instance Segmentation
CVPR 2023
Detection Recovery in Online Multi-Object Tracking With Sparse Graph Tracker
WACV 2023