-
Fish Movie Dataset
The dataset used in this paper is a collection of visual features extracted from a target fish movie using three methods: Slowfast-r50, SOE-Net, and 3D-SIFT. -
VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
A document layout analysis model, VTLayout, based on the fusion of deep visual, shallow visual, and text features, is proposed to solve the low recognition rate of different... -
Holidays dataset
The Holidays dataset is used for testing the performance of the HAE on visual feature translation.