Weixiong Lin
axiong
AI & ML interests
Multimodal Representation Learning, Foundation Model
Recent Activity
updated a dataset about 16 hours ago
axiong/MMEB-V3-other-tasks published a dataset about 16 hours ago
axiong/MMEB-V3-other-tasks updated a dataset about 16 hours ago
axiong/MMEB-V3-img-video-visdocOrganizations
datasets 21
axiong/MMEB-V3-other-tasks
Updated
axiong/MMEB-V3-img-video-visdoc
Updated
axiong/VideoMind-Ego4D-selected-1827
Viewer • Updated • 1.83k • 30
axiong/VideoMind-egoqa-train-annotations
Viewer • Updated • 10.7k • 36
axiong/VideoMind-HiREST-3fps-480-train
Viewer • Updated • 1 • 33
axiong/GroundVQA-data
Updated • 27
axiong/MultiHop-EgoQA-train-annotations
Viewer • Updated • 3.15k • 31
axiong/VideoChat2-webvid-caption-selected-03
Updated • 65
axiong/VideoChat2-webvid-qa-selected
Updated • 60
axiong/VideoChat2-webvid-caption-selected-02
Updated • 90