Skip-Convolutions for Efficient Video Processing with Amir Habibian - #496

47:59
 
Share
 

Manage episode 296153016 series 2355587
By TWIML and Sam Charrington. Discovered by Player FM and our community — copyright is owned by the publisher, not Player FM, and audio is streamed directly from their servers. Hit the Subscribe button to track updates in Player FM, or paste the feed URL into other podcast apps.

Today we kick off our CVPR coverage joined by Amir Habibian, a senior staff engineer manager at Qualcomm Technologies.

In our conversation with Amir, whose research primarily focuses on video perception, we discuss a few papers they presented at the event. We explore the paper Skip-Convolutions for Efficient Video Processing, which looks at training discrete variables to end to end into visual neural networks. We also discuss his work on his FrameExit paper, which proposes a conditional early exiting framework for efficient video recognition.

The complete show notes for this episode can be found at twimlai.com/go/496.

537 episodes