Hyun, Jeongseok

js-hyun's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 3 days ago

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Paper • 2510.19592 • Published 4 days ago • 8

authored 2 papers 4 months ago

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

Paper • 2407.12987 • Published Jul 17, 2024

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

Paper • 2507.07990 • Published Jul 10 • 45

authored 2 papers 6 months ago

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

Paper • 2407.07024 • Published Jul 9, 2024

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

Paper • 2205.00968 • Published May 2, 2022