Evaluating visual aesthetics in photographic portraiture
CAe '12 Proceedings of the Eighth Annual Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging
Enhancing semantic features with compositional analysis for scene recognition
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Salient object detection using a fuzzy theoretic approach
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Semantic indexing and computational aesthetics: interactions, bridgesand boundaries
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
Intelligent photographing interface with on-device aesthetic quality assessment
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Size does matter: how image size affects aesthetic perception?
Proceedings of the 21st ACM international conference on Multimedia
Visual interestingness in image sequences
Proceedings of the 21st ACM international conference on Multimedia
We are not equally negative: fine-grained labeling for multimedia event detection
Proceedings of the 21st ACM international conference on Multimedia
Relative spatial features for image memorability
Proceedings of the 21st ACM international conference on Multimedia
Beauty is here: evaluating aesthetics in videos using multimodal features and free training data
Proceedings of the 21st ACM international conference on Multimedia
Rare is interesting: connecting spatio-temporal behavior patterns with subjective image appeal
Proceedings of the 2nd ACM international workshop on Geotagging and its applications in multimedia
Proceedings of the 23rd international conference on World wide web
Hi-index | 0.00 |
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".