Searched for: subject%3A%223D%255C+Convolutions%22
(1 - 2 of 2)
document
Tahur, Nishad (author)
Color information has been shown to provide useful information during image classification. Yet current popular deep convolutional neural networks use 2-dimensional convolutional layers. The first 2-dimensional convolutional layer in the network combines the color channels of the input images, which produces feature maps per channel with only...
master thesis 2022
document
Ballan, Luca (author), Strafforello, O. (author), Schutte, Klamer (author)
Long-Term activities involve humans performing complex, minutes-long actions. Differently than in traditional action recognition, complex activities are normally composed of a set of sub-actions, that can appear in different order, duration, and quantity. These aspects introduce a large intra-class variability, that can be hard to model. Our...
conference paper 2021