The model, training, and evaluation data of EarthMind.
Yan Shu
sy1998
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
7 days ago
UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
upvoted
a
paper
10 days ago
Dense Motion Captioning
updated
a dataset
14 days ago
sy1998/tempsports
Organizations
-
sy1998/Video_XL
Updated • 18 -
sy1998/Video_XL_Training
Preview • Updated • 33 • 7 -
MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding
Paper • 2406.04264 • Published • 2 -
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
Paper • 2409.14485 • Published • 2
The model, training, and evaluation data of EarthMind.
-
sy1998/Video_XL
Updated • 18 -
sy1998/Video_XL_Training
Preview • Updated • 33 • 7 -
MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding
Paper • 2406.04264 • Published • 2 -
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
Paper • 2409.14485 • Published • 2
datasets
15
sy1998/tempsports
Preview
•
Updated
•
49
sy1998/Multisensor_RS_Data
Preview
•
Updated
•
19
sy1998/EarthMind-Bench
Viewer
•
Updated
•
4.17k
•
46
•
2
sy1998/VTP_Bench
Viewer
•
Updated
•
1.09k
•
21
•
1
sy1998/EarthMind-data
Updated
•
1.31k
•
1
sy1998/VidText
Viewer
•
Updated
•
3.15k
•
1.17k
•
2
sy1998/TextHalu-Bench
Updated
•
6
sy1998/MLVU_dev
Viewer
•
Updated
•
2.17k
•
9.92k
sy1998/MLVU_Test
Viewer
•
Updated
•
502
•
2.74k
sy1998/movie
Preview
•
Updated
•
12