Multimedia Semantic Analytics Lab
Multimedia Semantic Analytics Lab
Home
People
Publications
Contact
Xia Li
Latest
VG4D: Vision-Language Model Goes 4D Video Recognition
Towards robust referring image segmentation
Towards open vocabulary learning: A survey
Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation
Towards efficient scene understanding via squeeze reasoning
PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
Improving semantic segmentation via decoupled body and edge supervision
Cite
×