Shape-Based Autotagging of 3D Models for Retrieval

This paper describes an automatic annotation, or autotagging, algorithm that attaches textual tags to 3D models based on their shape and semantic classes. The proposed method employs Manifold Ranking by Zhou et al, an algorithm that takes into account both local and global distributions of feature points, for tag relevance computation. Using Manifold Ranking, our method propagates multiple tags attached to a training subset of models in a database to the other tag-less models. After the relevance values for multiple tags are computed for tag-less points, the method selects, based on the distribution of feature points for each tag, the threshold at which the tag is selected or discarded for the points. Experimental evaluation of the method using a text-based 3D model retrieval setting showed that the proposed method is effective in autotagging 3D shape models.