You've both done an excellent job in clarifying various issues. It really helped me use this work better!
Just a quick question - Consider a ground-truth annotation scheme where a person is given the same ID throughout the entire video. What happens when they leave the Field of View for t frames, and re-enter back at the t+1 th frame?
They'll have the same GT ID, but might have a different hypothesis ID assigned. What errors does this lead to?
Hello @cheind and @jvlmdr,
You've both done an excellent job in clarifying various issues. It really helped me use this work better!
Just a quick question - Consider a ground-truth annotation scheme where a person is given the same ID throughout the entire video. What happens when they leave the Field of View for t frames, and re-enter back at the t+1 th frame? They'll have the same GT ID, but might have a different hypothesis ID assigned. What errors does this lead to?
Thanks in advance.