Abstract: A principled, probabilistic approach to meta-learning acts as a go-between for a ‘black-box’ image annotation system and its users. Inspired by inductive transfer, the approach harnesses available information, including the black-box model's performance, the image representations, and a semantic lexicon ontology. Being computationally ‘lightweight.’ the meta-learner efficiently re-trains over time, to improve and/or adapt to changes. The black-box annotation model is not required to be re-trained, allowing computationally intensive algorithms to be used. Both batch and online annotation settings are accommodated. A “tagging over time” approach produces progressively better annotation, significantly outperforming the black-box as well as the static form of the meta-learner, on real-world data.

Abstract: The aesthetic quality of a picture is automatically inferred using visual content as a machine learning problem using, for example, a peer-rated, on-line photo sharing Website as data source. Certain visual features of images are extracted based on the intuition that they can discriminate between aesthetically pleasing and displeasing images. A one-dimensional support vector machine is used to identify features that have noticeable correlation with the community-based aesthetics ratings. Automated classifiers are constructed using the support vector machines and classification trees, with a simple feature selection heuristic being applied to eliminate irrelevant features. Linear regression on polynomial terms of the features is also applied to infer numerical aesthetics ratings.

Abstract: A method and system for generating and searching a tree-structured index of window vectors that represent database sequences comprise a window vector generation module, a tree-structured index generation module, a query sequence partitioning module, and a retrieval component. The window vector generation module partitions a database sequence into a plurality of overlapping windows. Each window has a fixed length W comprising a fixed number of nucleotides, and the offset among windows is determined by a parameter &Dgr;. The window vector generation module then maps each database sequence window into a window vector. The database sequence window vector indicates the frequency of appearance of each k-tuple in the corresponding database sequence window. The tree-structured index generation module then generates a tree-structured index using the database sequence window vectors.