Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Jeongseok Hyun,  Sukjun Hwang, Su Ho Han, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Joon-Young Lee, Seon Joo Kim, Minho Shim

ICCV 2025

Propose training-free, KV-cache reusable video token merging method for long video LLMs that effectively exploits spatio-temporal locality

paper | code

Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization

Jeongseok Hyun, Su Ho Han, Hyolim Kang, Joon-Young Lee, Seon Joo Kim

WACV 2025

Propose a scalable open-vocabulary TAL method that utilizes pseudo-labels from unlabeled videos to expand the semantic context of action localization

paper | code

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos

Hyolim Kang, Jeongseok Hyun, Joungbin An, Youngjae Yu, Seon Joo Kim

ECCV 2024

• Qualcomm Innovation Fellowship 2024 Finalist

Propose an online TAL framework that can detect multiple overlapping action instances in a streaming setting based on a finite-state machine inspired model

paper | code

A Generalized Framework for Video Instance Segmentation

Miran Heo, Sukjun Hwang, Jeongseok Hyun, Hanjung Kim, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

CVPR 2023

Propose a framework unifying online, semi-online, and offline VIS with a novel training method that bridges the gap between the training and inference stages

paper | code

Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker

Jeongseok Hyun, Myunggu Kang, Dongyoon Wee, Dit-Yan Yeung

WACV 2023

Propose a GNN-based joint detection and tracking method that can track low-scored detections, which were previously filtered out to avoid false positive tracking, by exploiting multi-hop relational features.

paper | code