Picture for Mingxiang Liao

Mingxiang Liao

Evaluation of Text-to-Video Generation Models: A Dynamics Perspective

Add code
Jul 01, 2024
Viaarxiv icon

DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution

Add code
May 25, 2024
Figure 1 for DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Figure 2 for DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Figure 3 for DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Figure 4 for DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Viaarxiv icon