-
Notifications
You must be signed in to change notification settings - Fork 76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A question about person_box and action_predictor #38
Comments
Thank you for your attention! As shown in the paper, our model takes the bounding box on the center frame to do RoIAlign on all frames of the input video clips. This is mainly following previous works, but also because AVA dataset only provides boxes annotated on the center frame. Of course, we could use a tracking algorithm to generate more accurate bounding boxes on every single frame, and then use them to get more robust results. Actually, there are some previous works [link] trying that. However, we did not find a very robust tracker (especially for fast motion scenes), so we chose to use the current design in our method. |
Copy that,wish you to make greater success with the progress in the relevant fields!
|
Thanks for pointing out these problems! First, I have to admit that our current demo program is not well-designed. It could have some little bugs and is also hard to read. As to these two problems you mentioned above:
|
good job! 瑕不掩瑜 |
hi, best, |
hi, best, |
Wonderful job, as a researcher in the same field, I would like to express my appreciation to the author.
I have one question about the part "compute_prediction" of "sction_predictior.py", the inputs of calculate function are nearest list frames(just like self.frame_stack = self.frame_stack[-self.frame_buffer_numbers:]) and only the box of center frame, it is assumed that the pedestrian has little displacement in input frames? I wonder to konw if add the exact box of each frame (can be extracted from the tracking results) can make the finall result better?(for the big change range of motion, just like hit, fight?) or just I mistook the process ?
The text was updated successfully, but these errors were encountered: