Efficient image signatures and similarities using tensor products of local descriptors |
| |
| Authors: | David Picard Philippe-Henri Gosselin |
| |
| Affiliation: | 1. College of Engineering and Computer Science, Computational Imaging Lab, University of Central Florida, 4000 Central Florida Blvd., Orlando, FL 32816, USA;2. Advanced Micro Devices, Quadrangle Blvd., Orlando, FL 32817, USA;3. State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;4. Department of EECS, Computational Imaging Laboratory, University of Central Florida, Orlando, FL 32816, USA;1. Purdue University, 465 Northwestern Ave., West Lafayette, IN 47906, United States;2. Oak Ridge National Labs, Oak Ridge, TN 37831, United States;1. Faculty of Computer Science, Dalhousie University, Halifax, Nova Scotia, Canada;2. Neuroeconomics Laboratory, University of Victoria, Victoria, British Columbia, Canada |
| |
| Abstract: | In this paper, we introduce a novel image signature effective in both image retrieval and image classification. Our approach is based on the aggregation of tensor products of discriminant local features, named VLATs (vector of locally aggregated tensors). We also introduce techniques for the packing and the fast comparison of VLATs. We present connections between VLAT and methods like kernel on bags and Fisher vectors. Finally, we show the ability of our method to be effective for two different retrieval problems, thanks to experiments carried out on similarity search and classification datasets. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
