No abstract

For content-based 3D model retrieval, an improved depth image-based feature extraction algorithm is proposed. First, a 3-D model is preprocessed. Secondly, six depth images are generated in three principal directions in the normalized coordinate system. Thirdly, the eigenvectors of 3D model are obtained through 2D Fourier Transform of the depth images. Finally a new method is used for low-frequency sampling. Experiments show that the approach performed quite well despite its apparently simple approach. In our large 3D database, our approach is well for variant resolution models and holds satisfied computational costs.

The purpose of designing recommender systems is to help individual users find relevant information. However, many recommender systems have been facing the challenges of finding niche objects, which users may like but difficult to find due to the lack of sufficient data. In this paper, we propose a recommendation algorithm which takes a niche object as input and outputs a list of users who may be interested it. By this approach, every niche object can be recommended at least one time. Further analysis indicates that those niche objects are usually collected by active users and the owners who are very similar to each other. Therefore, this work has outlined the significant relevance with the challenge, the Long Tail problem, and provided a different perspective to solve it in the field of information filtering.