Many real-world applications call for learning predictive relationships from multi-modal data. In particular, in multi-media and web applications, given a dataset of images and th...
Maps are artifacts often derived from multiple sources of data, e.g., sensors, and processed by multiple methods, e.g., gridding and smoothing algorithms. As a result, complex meta...
Nicholas Del Rio, Paulo Pinheiro da Silva, Ann Q. ...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...
Anomaly detection has received much attention within the literature as a means of determining, in an unsupervised manner, whether a learning domain has changed in a fundamental way...