Project
zootracer
Use consumer video equipment to trace animal movement. Zootracer is software developed at Microsoft Research, capable of accurately tracking multiple, unmarked, interacting individuals in arbitrary video footage. As the software is independent of recording devices,…
Project
Filter Forests for Learning Data-Dependent Convolutional Kernels
We propose ‘filter forests’ (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context. FF can be used for general signal restoration tasks that can be tackled via convolutional…