3 papers
cs.CV2019
Texel-Att: Representing and Classifying Element-based Textures by Attributes
Marco Godi, Christian Joppi, Andrea Giachetti +2
Element-based textures are a kind of texture formed by nameable elements, the texels [1], distributed according to specific statistical distributions; it is of primary importance i…
cs.CV2019
Texture Retrieval in the Wild through detection-based attributes
Christian Joppi, Marco Godi, Andrea Giachetti +2
Capturing the essence of a textile image in a robust way is important to retrieve it in a large repository, especially if it has been acquired in the wild (by taking a photo of the…
cs.CV2019
SIMCO: SIMilarity-based object COunting
Marco Godi, Christian Joppi, Andrea Giachetti +1
We present SIMCO, the first agnostic multi-class object counting approach. SIMCO starts by detecting foreground objects through a novel Mask RCNN-based architecture trained beforeh…