Learning beautiful (and ugly) attributes

49 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Recognizing Image Style (2013, methodology): “Using images from this dataset, Marchesotti and Peronnin [20] gathered bi-grams from user comments on the website, and used a simple sparse feature selection method to ﬁnd ones predictive of aesthetic rating.”
Label-Embedding for Image Classification (2015, neutral): “Several works have also considered the problem of discovering a vocabulary of attributes [5], [16], [36].”
Image Aesthetic Assessment: An experimental survey (2016, methodology): “The more general image features like Bagof-Visual Words (BOV) [44] and Fisher Vector (FV) [45] are explored in [20], [21], [22].”
Re-id: Hunting Attributes in the Wild (2014, methodology): “[26], we calculate the similarity between the frequency of the unigrams and bigrams rather than using the Levenshtein distance on the second gram within each bigram.”