tailieunhanh - High Level Describable Attributes for Predicting Aesthetics and Interestingness

The philosophy of art tends towards analysing the relations between art and such matters as the True and the Good, matters which are beyond the formal qualities of works of art. It is perhaps worth emphasizing that practices similar to those of Western art criticism and philosophy are to be found in other cultures. These practices are worthy of study in their own right. According to the terminology adopted in this essay, however, they are not the aesthetics of a society, but its art criticism or its philosophy. . | High Level Describable Attributes for Predicting Aesthetics and Interestingness Sagnik Dhar Vicente Ordonez Tamara L Berg Stony Brook University Stony Brook NY 11794 UsA tlberg@ Abstract With the rise in popularity of digital cameras the amount of visual data available on the web is growing exponentially. Some of these pictures are extremely beautiful and aesthetically pleasing but the vast majority are uninteresting or of low quality. This paper demonstrates a simple yet powerful method to automatically select high aesthetic quality images from large image collections. Our aesthetic quality estimation method explicitly predicts some of the possible image cues that a human might use to evaluate an image and then uses them in a discriminative approach. These cues or high level describable image attributes fall into three broad types 1 compositional attributes related to image layout or configuration 2 content attributes related to the objects or scene types depicted and 3 sky-illumination attributes related to the natural lighting conditions. We demonstrate that an aesthetics classifier trained on these describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments. We also demonstrate our method for predicting the interestingness of Flickr photos and introduce a novel problem of estimating query specific interestingness . 1. Introduction Automating general image understanding is a very difficult and far from solved problem. There are many subproblems and possible intermediate goals on the way toward a complete solution including producing descriptions of what objects are present in an image including their spatial arrangements and interactions what general scene type is shown . a beach office street etc. or general visual qualities of the image such as whether a picture was captured indoors or outside on a sunny day . While none of these are solved problems either progress has been made

crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.