8 citations · 15 across the 5 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2022
Efficient Motion Modelling with Variable-sized blocks from Hierarchical Cuboidal Partitioning
Priyabrata Karmakar, Manzur Murshed, Manoranjan Paul +1
Motion modelling with block-based architecture has been widely used in video coding where a frame is divided into fixed-sized blocks that are motion compensated independently. This…
cs.CV2020★ 5 cited
Transform Quantization for CNN (Convolutional Neural Network) Compression
Sean I. Young, Wang Zhe, David Taubman +1
In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization. Previous CNN quantization techniques tend to ignore the joint statis…