Optimizing learning in image retrieval
By Yong Rui, Thomas S. Huang. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000
410 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/f762a30f17a3a1e2844d2c919491bd846e476657
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
- Dacheng Tao
- Luc Van Gool
- Yi Yang
- Xiaogang Wang
- Ming-Hsuan Yang
- Trevor Darrell
- Jitendra Malik
- Li Fei-Fei
Citations in the corpus
- Semantic manifold learning for image retrieval (2005, methodology): “The commonly-indexed features in CBIR are comprehensive, such as shape, texture [9, 10, 24], color, wavelet coefficients [12, 23, 29], and color coherence vectors [19].”
- A Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback (2012, methodology): “RF has been proven helpful for multimedia content analysis and retrieval [6], [15], [16], [37], [20], [26], [46].”
- Content-based image retrieval: approaches and trends of the new age (2005, positive): “multiple visual features has been studied and an optimized learning strategy suggested in [85].”
- Image Retrieval from the World Wide Web: Issues, Techniques, and Systems (2004, background): “However, it has been observed that this measure is less meaningful in the context of image retrieval since recall is consistently low [Rui and Huang 2000; Huang et al. 1997].”
- Content-based visual search learned from social media (2012, background): “The optimal distance varies in terms of tasks [41, 94].”
- A survey of content-based image retrieval with high-level semantics (2007, methodology): “Some researchers think that Corel image dataset meets all the requirements to evaluate an image retrieval system, because of its large size, heterogeneous content and human annotated ground truth available [101].”
- Small sample learning during multimedia retrieval using BiasMap (2001, methodology): “Up to 20 rounds (or until convergence) of feedback are performed for each query under each of the four relevance feedback schemes: twolevel optimal whitening transform (with partial independence assumption) on positive examples [8]TWT, FDA, MDA, and BDA.”
- Boosting Image Retrieval (2000, background): “Progress has also been made in formalizing the image retrieval problem with regard to learning and relevance feedback ( Rui and Huang, 2000; Vasconcelos and Lippman, 2000).”