We describe a digital music distribution system which fixes current problems in prevailing economic models for selling digital music. Our system aims to address the perverse incentives in the current digital music market, in which music buyers and music creators have incompatible goals and desired outcomes. The model gives users an added buying incentive: when a user buys a song, that user has ...

Instance-level video segmentation requires a solid integration of spatial and temporal information. However, current methods rely mostly on domain-specific information (online learning) to produce accurate instance-level segmentations. We propose novel approach that relies exclusively the generic spatio-temporal attention cues. Our strategy, named Multi-Attention Instance Network (MAIN), overco...