A method for enhancing image retrieval based on annotation using modified WUP similarity in WordNet
AIKED'12 Proceedings of the 11th WSEAS international conference on Artificial Intelligence, Knowledge Engineering and Data Bases
Improving Image Classification Using Semantic Attributes
International Journal of Computer Vision
Proceedings of the 2012 international workshop on Socially-aware multimedia
On shape and the computability of emotions
Proceedings of the 20th ACM international conference on Multimedia
Joint statistical analysis of images and keywords with applications in semantic image enhancement
Proceedings of the 20th ACM international conference on Multimedia
Towards indexing representative images on the web
Proceedings of the 20th ACM international conference on Multimedia
Proceedings of the 21st ACM international conference on Information and knowledge management
Dog breed classification using part localization
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Measuring image distances via embedding in a semantic manifold
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Semi-Supervised learning on a budget: scaling up to large datasets
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Proceedings of the 21st ACM international conference on Multimedia
Picture tags and world knowledge: learning tag relations from visual semantic sources
Proceedings of the 21st ACM international conference on Multimedia
Hi-index | 0.00 |
Many computer vision approaches take for granted positive answers to questions such as "Are semantic categories visually separable?" and "Is visual similarity correlated to semantic similarity?". In this paper, we study experimentally whether these assumptions hold and show parallels to questions investigated in cognitive science about the human visual system. The insights gained from our analysis enable building a novel distance function between images assessing whether they are from the same basic-level category. This function goes beyond direct visual distance as it also exploits semantic similarity measured through ImageNet. We demonstrate experimentally that it outperforms purely visual distances.