Behaviour of Recent Aesthetics Assessment Models with Professional Photography

Abstract : Aesthetic quality assessment for photographs is an important research topic since it can be used by a number of applications, such as image database management or image browsing. In 2012, the Aesthetic Visual Analysis (AVA) dataset has been proposed. Those 255,000 aesthetically annotated images are a key ingredient for training and for testing new models for aesthetics prediction. As AVA dataset is mainly composed of competitive photographs, we evaluate whether or not those computational models of aesthetics generalize well and perform well over professional photographs. We notice that the different models we test behave quite differently. Besides, we fine-tune the model using professional photographs and the results show that this process is effective.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02374494
Contributor : Mathieu Chambe <>
Submitted on : Thursday, November 21, 2019 - 3:09:33 PM
Last modification on : Saturday, November 23, 2019 - 1:26:58 AM

File

Aesthetics_models_robustness.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02374494, version 1

Citation

Mathieu Chambe, Rémi Cozot, Olivier Le Meur. Behaviour of Recent Aesthetics Assessment Models with Professional Photography. 2019. ⟨hal-02374494⟩

Share

Metrics

Record views

29

Files downloads

42