It this section, we provide qualitative examples and plots for the experiment “2D-3D Matching as an Object Detector” (Sect. 6.2 in the main paper). To recapitulate, we run our ensemble of NZ-WHO templates on the 3DObject Classes dataset [2], without the finetuning stage. Fig. 1 gives the corresponding detection average precision, average viewpoint precision, viewpoint confusion matrix and mean ...

Nowadays, most documents are created and stored in electronic files both in intranet and internet. Documents are the source of knowledge. To manage documents in user’s point of view, users must read and cluster a group of document by themselves. For achieving their viewpoints, they lost much time to acquire their knowledge. Users have their own viewpoints that are different such as viewpoint of...