XRCE ’ s participation to ImagEval
By Stéphane Clinchant, Gabriella Csurka, Florent Perronnin. 2007
Subfields: Computer Vision and Pattern Recognition
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
- Luc Van Gool
- Bernt Schiele
- Andrea Vedaldi
- Andrew Zisserman
- Cordelia Schmid
- Dacheng Tao
- Trevor Darrell
- Ming-Hsuan Yang
Citations in the corpus
- Do ImageNet Classifiers Generalize to ImageNet? (2019, background): “[6] Stephane Clinchant, Gabriela Csurka, Florent Perronnin, and Jean-Michel Renders.”
- Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost (2013, unknown): “We represent each image with a Fisher vector (FV) [16] computed over densely extracted 128D SIFT descriptors [42] and 96D local color features [43], both projected with PCA to 64 dimensions.”
- Fisher vectors meet Neural Networks: A hybrid classification architecture (2015, methodology): “From each patch we extract two types of local descriptors: 128-dim SIFT descriptors [32] and 96-dim Local Color Statistics (LCS) [8].”
- Author manuscript, published in "International Journal of Computer Vision (2013)" International Journal of Computer Vision manuscript No. (will be inserted by the editor) Image Classification with the Fisher Vector: Theory and Practice (2013, unknown): “We consider two types of patch descriptors in this work: the 128-dim SIFT descriptors of Lowe (2004) and the 96-dim Local Color Statistic (LCS) descriptors of Clinchant et al (2007).”
- Transformation Pursuit for Image Classification (2014, methodology): “We extract SIFT [17] and color [8] descriptors on a dense grid at multiple scales.”
- Scalable Multitask Representation Learning for Scene Classification (2014, methodology): “Our feature extraction pipeline follows the one described in [8] and uses SIFT [6] as well as Local Color Statistic (LCS) [2] as the low-level image descriptors.”