Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
Source code, driver data and user manual for the Madingley model, as described in Harfoot, M.B.J., Newbold, T., Tittensor, D.P., Emmott, S., Hutton, J., Lyutsarev, V., Smith, M.J., Scharlemann, J.P.W. & Purves, D.W. (2014) Emergent…
Smart selection is the task of predicting the span of text that a user intended to select after they touched on a single word on a touch-enabled device. The Smart Selection Dataset consists of crowd-sourced…
This data includes a sequence of 100 images captured from 8 cameras showing the breakdancing and ballet scenes from the paper “High-quality video view interpolation using a layered representation”, Zitnick et al., SIGGRAPH 2004. Depth…
