Dawn-LX/VidSGG-BIG
Pytorch implementation of our paper Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs, which is accepted by CVPR2022
Python
Issues
- 2
轨迹提取的模型和细节
#22 opened by wangyongqi558 - 3
Pre-prepared cache data for VidOR
#21 opened by Chango-G - 4
Make the qualitative results
#20 opened by tuanmanh1410 - 13
About the prepared data
#12 opened by Passenger33 - 2
About inference results
#9 opened by ZiyueWu59 - 5
About the pre-prepared cache data for VidOR
#10 opened by ZiyueWu59 - 9
The generation of .npy in prepared_data folder
#13 opened by Awenjie10 - 2
请问,可以提供一下用于提取I3D特征的I3D模型吗
#19 opened by whyang78 - 5
About classme feature
#7 opened by MinamiKotoka - 4
classeme features
#3 opened by Dawn-LX - 0
Box shifting: some boxes may appear as background after tracking (when using dataloader_vidor.py)
#17 opened by foollinkie - 4
tracklets with features link expired
#18 opened by iSenya - 5
Mis-matching between Trajectory and gt_graph
#16 opened by ZiyueWu59 - 3
About the prepared data for Vidor
#14 opened by Passenger33 - 2
Tracklet Data of VidVRD
#15 opened by ComeOnComeOnTurnYourRadioOn - 3
DEBUG model
#8 opened by aries-young - 1
- 1
About the pre-prepared cache data for VidOR
#11 opened by ZiyueWu59 - 2
Classification stage and grounding stage
#5 opened by guanw-pku - 3
Device information
#4 opened by guanw-pku - 22
No such file or directory
#2 opened by MinamiKotoka - 3
About VidVRD dataset
#1 opened by ZiyueWu59