Seongsu Ha

seongsu0311's activity

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

authored 4 papers about 1 month ago

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models

Paper • 2408.11318 • Published Aug 21, 2024 • 57

Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space

Paper • 2409.05260 • Published Sep 9, 2024 • 1

Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation

Paper • 2411.01494 • Published Nov 3, 2024 • 1

SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence

Paper • 2605.31529 • Published May 29 • 7

upvoted a paper about 1 month ago

SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence

Paper • 2605.31529 • Published May 29 • 7

updated a dataset about 1 month ago

MVP-Group/SVI-Bench

Updated 6 days ago • 44

upvoted a paper 6 months ago

Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching

Paper • 2512.18184 • Published Dec 20, 2025 • 22

upvoted a paper almost 2 years ago

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models

Paper • 2408.11318 • Published Aug 21, 2024 • 57