Class agnostic repetition counting in video(s) utilizing a temporal self-similarity matrix
AssigneeGoogle Inc.
InventorsDebidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Andrew Zisserman, Pierre Sermanet
Life of this patent
Estimating the term…
Loading patent…
AssigneeGoogle Inc.
InventorsDebidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Andrew Zisserman, Pierre Sermanet
Estimating the term…
Techniques are disclosed that enable processing a video capturing a periodic activity using a repetition network to generate periodic output (e.g., a period length of the periodic activity captured in the video and/or a frame wise periodicity indication of the video capturing the periodic activity). Various implementations include a class agnostic repetition network which can be used to generate periodic output for a wide variety of periodic activities. Additional or alternative implementations include generating synthetic repetition videos which can be utilized to train the repetition network.
A method implemented by one or more processors, the method comprising:
A method implemented by one or more processors, the method comprising:
A method implemented by one or more processors, the method comprising:
22-25. (canceled)
Dependencies are inferred from the claim text.