2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSS-15.5
Paper Title LATENT SPACE MOTION ANALYSIS FOR COLLABORATIVE INTELLIGENCE
Authors Mateen Ulhaq, Ivan Bajic, Simon Fraser University, Canada
SessionSS-15: Signal Processing for Collaborative Intelligence
LocationGather.Town
Session Time:Friday, 11 June, 13:00 - 13:45
Presentation Time:Friday, 11 June, 13:00 - 13:45
Presentation Poster
Topic Special Sessions: Signal Processing for Collaborative Intelligence
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract When the input to a deep neural network (DNN) is a video signal, a sequence of feature tensors is produced at the intermediate layers of the model. If neighboring frames of the input video are related through motion, a natural question is, ``what is the relationship between the corresponding feature tensors?'' By analyzing the effect of common DNN operations on optical flow, we show that the motion present in each channel of a feature tensor is approximately equal to the scaled version of the input motion. The analysis is validated through experiments utilizing common motion models.