Sukjun Hwang
9 papers · 2021–2025 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Keywords
video instance segmentation
(4)
object tracking
(4)
semantic segmentation
(2)
transformer architecture
(2)
video understanding
(2)
efficient computing
(1)
temporal classification
(1)
real-time processing
(1)
temporal learning
(1)
occlusion handling
(1)
set classification
(1)
state space model
(1)
sequence model
(1)
long-tailed distribution
(1)
panoptic segmentation
(1)
convolutional filter
(1)
token merging
(1)
bidirectional model
(1)
fully convolutional network
(1)
video large language model
(1)
Papers
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
ICCV 2025
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
NeurIPS 2024
VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
ECCV 2024
A Generalized Framework for Video Instance Segmentation
CVPR 2023
Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints To Better Classify Objects in Videos
CVPR 2022
Single-Shot Path Integrated Panoptic Segmentation
WACV 2022
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
CVPR 2022
VITA: Video Instance Segmentation via Object Token Association
NeurIPS 2022
Video Instance Segmentation using Inter-Frame Communication Transformers
NeurIPS 2021