You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Because the query points can be sampled any where within the video (not just in the first frame), do we have to track them backward in time or just need to track them forward?
For example, if the query point is sample at frame T, do we have to find its position in frames 0->(T-1), or just need to track it in (T+1)->Max_Frame?
The text was updated successfully, but these errors were encountered:
Hej, in the first query mode, only the future time steps need to be tracked. This setting is particularly relevant in an online context. However, in the strided mode, all frames are evaluated. For a more detailed understanding, you can refer to the evaluation code snippet below or check appendix section H of the the TAP-Vid paper. Hope this helps!
I would like to clarify the evaluation setting.
Because the query points can be sampled any where within the video (not just in the first frame), do we have to track them backward in time or just need to track them forward?
For example, if the query point is sample at frame T, do we have to find its position in frames 0->(T-1), or just need to track it in (T+1)->Max_Frame?
The text was updated successfully, but these errors were encountered: