![]() In Proceedings IEEE International Conference on Computer Vision, (pp. Poselets: Body part detectors trained using 3d human pose annotations. In Proceedings European Conference on Computer Vision, (pp. Food-101 mining discriminative components with random forests. Wiley Interdisc Review: Data Mining and Knowledge Discovery, 2(6), 437–456.īossard, L., Guillaumin, M., & Gool, L. IEEE Transactions Pattern Analysis and Machine Intelligence, 38(9),1790–1802.īansal, A., Shrivastava, A., Doersch, C., & Gupta, A. Factors of transferability for a generic convnet representation. S., Sullivan, J., Maki, A., & Carlsson, S. In Proceedings Annual ACM SIGIR Conference, 33(2), p. Painting-to-3d model alignment via discriminative visual elements. In Proceedings of IEEE Conference on Computer Vision Pattern Recognition, (pp. (2014a) Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models. In Proceedings International Conference Very Large Databases, (pp. Fast algorithms for mining association rules in large databases. Analyzing the performance of multilayer neural networks for object recognition. International Journal of Computer Vision, 78(1), 15–27.Īgrawal, P., Girshick, R., & Malik, J. Multilevel image coding with hyperfeatures. We evaluate the two encoding methods on object and scene classification tasks, and demonstrate that our approach outperforms or matches the performance of the state-of-the-arts on these tasks.Īgarwal, A., & Triggs, B. The second relies on mid-level visual elements to construct a Bag-of-Elements representation. We thus label this a Bag-of-Patterns representation. The first encoding method uses the patterns as codewords in a dictionary in a manner similar to the Bag-of-Visual-Words model. ![]() Given the patterns and retrieved mid-level visual elements, we propose two methods to generate image feature representations. The marriage between CNN activations and a pattern mining technique leads to fast and effective discovery of representative and discriminative patterns from a huge number of image patches, from which mid-level elements are retrieved. We show that Convolutional Neural Network (CNN) activations extracted from image patches typical possess two appealing properties that enable seamless integration with pattern mining techniques. Here we propose a pattern-mining approach to the problem of identifying mid-level elements within images, motivated by the observation that such techniques have been very effective, and efficient, in achieving similar goals when applied to other data types. The purpose of mid-level visual element discovery is to find clusters of image patches that are representative of, and which discriminate between, the contents of the relevant images.
0 Comments
Leave a Reply. |