AHN DONGHOON
sunovivid
AI & ML interests
image & video generation, author of PAG
Recent Activity
upvoted a paper 3 days ago
Grounding World Simulation Models in a Real-World Metropolis upvoted a paper 3 days ago
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting updated a dataset about 2 months ago
sunovivid/mevis-point-trackingOrganizations
datasets 54
sunovivid/mevis-point-tracking
Viewer • Updated • 291k • 9
sunovivid/youtubevis-point-tracking
Viewer • Updated • 375k • 9
sunovivid/youtube-vis-2022
Viewer • Updated • 3.47k • 19
sunovivid/mevis
Viewer • Updated • 23.7k • 11
sunovivid/kubric_pairs_latent_1M
Updated • 7
sunovivid/kubric_pairs_latent
Viewer • Updated • 1 • 920
sunovivid/pixel_pairs_64_crop0.5_min_dist0.1__center_bias1.0_margin0.05_q012
Viewer • Updated • 13.7k • 8
sunovivid/pixel_pairs_64_crop0.5_min_dist0.2_q012
Viewer • Updated • 8.45k • 7
sunovivid/output_pairs_64_crop0.5_15K
Viewer • Updated • 15.2k • 6
sunovivid/output_pairs_64_crop0.6
Viewer • Updated • 13.3k • 11