CLUE: cluster-based retrieval of images by unsupervised learning
By Yixin Chen, James Ze Wang, Robert Krovetz. IEEE Transactions on Image Processing, 2005
387 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/7db898aadd5c0cbc3c98fd3e47a5657aab2260e0
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Yi Yang
- Dacheng Tao
- Luc Van Gool
- Xiaogang Wang
- Trevor Darrell
- Shuicheng Yan
- Ming-Hsuan Yang
- Jitendra Malik
Citations in the corpus
- Finding iconic images (2009, background): “Previous work addressing clustering search results in Content Based Image Retrieval (CBIR) clusters images by content [6] but usually does so after a query by example image (instead of text) and does not focus on an object region or emphasize images with a clear object as we do.”
- Color Image Segmentation Based on Mean Shift and Normalized Cuts (2007, methodology): “The Ncut method has been applied in video summarization, scene detection [17], and cluster-based image retrieval [18].”
- Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “As opposed to digital media, cultural artifacts and old paintings are subject to wear with time, and are also prone to disasters and vandalism [Chen et al. 2005].”
- Image Clustering Using Local Discriminant Models and Global Integration (2010, background): “Many works [4], [10], [18] have demonstrated that the performances of CBIR systems can be improved by adopting image clustering methods.”
- Discriminative Clustering by Regularized Information Maximization (2010, methodology): “We evaluated a number of other measures for comparing clusterings to ground truth including mutual information, normalized mutual information [12], and cluster impurity [13].”
- Content-based image retrieval: approaches and trends of the new age (2005, neutral): “Clustering has been applied to image retrieval to help improve interface design, visualization, and result pre-processing [19, 61, 116].”