263 citations · 265 across the 4 of their papers we have counts for
Showing 2022 · cs.CVShow all
2 papers · 2 filters
cs.CV2022
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos
Mathias Parger, Chengcheng Tang, Thomas Neff +4
Convolutional neural network inference on video input is computationally expensive and requires high memory bandwidth. Recently, DeltaCNN managed to reduce the cost by only process…
cs.CV2022★ 2 cited
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
Mathias Parger, Chengcheng Tang, Christopher D. Twigg +3
Convolutional neural network inference on video data requires powerful hardware for real-time processing. Given the inherent coherence across consecutive frames, large parts of a v…