Attribute and simile classifiers for face verification
Citations
14,799 citations
Cites background or methods from "Attribute and simile classifiers fo..."
...27% accuracy on the LFW task even when the centre of the image is masked (Kumar et al., 2009)....
[...]
...During discriminative fine-tuning, we use a subset of the Pubfig face dataset (Kumar et al., 2009) as a validation set for selecting the model architecture and for...
[...]
...During discriminative fine-tuning, we use a subset of the Pubfig face dataset (Kumar et al., 2009) as a validation set for selecting the model architecture and for early stopping....
[...]
...The two current best LFW results are 0.8683± 0.0034 (Wolf et al., 2009), and 0.8529±0.0123 (Kumar et al., 2009)....
[...]
...Recently it has been found that humans are able to get 94.27% accuracy on the LFW task even when the centre of the image is masked (Kumar et al., 2009)....
[...]
6,273 citations
Cites background from "Attribute and simile classifiers fo..."
...[15] predicted face attributes by extracting hand-crafted features from ten face parts....
[...]
...Face attributes are beneficial for multiple applications such as face verification [15, 2, 24], identification [20], and retrieval....
[...]
...[15] extracted HOG-like features on various face regions to tackle attribute classification and face verification....
[...]
...Extracting hand-crafted features at pre-defined landmarks has become a standard step in attribute recognition [9, 15, 4, 2]....
[...]
...Recent local models [15, 4, 5, 2, 19, 32] first detect object parts and extract features from each part....
[...]
6,132 citations
Additional excerpts
...5% [20]....
[...]
2,822 citations
2,366 citations
References
46,906 citations
37,861 citations
"Attribute and simile classifiers fo..." refers methods in this paper
...Automatically determining the gender of a face has been an active area of research since at least 1990 [15, 9], and includes more recent work [24] using Support Vector Machines (SVMs) [8]....
[...]
14,708 citations
"Attribute and simile classifiers fo..." refers background in this paper
...Our low-level features are designed following a great deal of work in face recognition (and the larger recognition community) which has identified gradient direction and local descriptors around fiducial features as effective first steps toward dealing with illumination [6, 28, 22, 23, 10]....
[...]
7,601 citations
"Attribute and simile classifiers fo..." refers methods in this paper
...Training requires a set of positive and negative example images for each attribute, and uses a simplified version of adaboost [12] to choose from the set of low-level features described in the previous section....
[...]