Dawn-LX/OpenVoc-VidVRD
Official code for the ICLR2023 paper Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Python
Issues
- 3
About VidOR dataset
#8 opened - 8
About VidOR dataset
#7 opened - 1
GPU
#6 opened - 0
VidOR data results
#5 opened - 5
- 4
How to extract RoI features
#3 opened - 1
- 5
object tracking代码
#1 opened