FocusedAD: Character-centric Movie Audio Description
Paper
•
2504.12157
•
Published
•
9
VLM
-
-
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
Paper • 2504.10465 • Published • 28 -
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Paper • 2504.13180 • Published • 17 -
OS-Copilot/OS-Atlas-Base-7B
Image-Text-to-Text • Updated • 2.54k • 38 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • Updated • 7.25M • 536