Learnable box filters and precomputed summed-area tables enable efficient arbitrarily large kernel convolutions in fully-convolutional networks while maintaining constant parameters per filter and competitive performance on human pose estimation.
Simple baselines for human pose estimation and tracking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating Large-Kernel Convolution Using Summed-Area Tables
Learnable box filters and precomputed summed-area tables enable efficient arbitrarily large kernel convolutions in fully-convolutional networks while maintaining constant parameters per filter and competitive performance on human pose estimation.