Deep Neural Networks (DNNs) have recently outperformed traditional object recognition algorithms on multiple largescale datasets, such as ImageNet. However, the model trained on ImageNet fails on recognising the sketches, because the data source is dominated by photos and all kinds of sketches are roughly labelled as ‘cartoon’ rather than their own categorises (e.g., ‘cat’). Most of sketch reco...

We present a new sketch for summarizing network data. The sketch has the following properties which make it useful in communication-efficient aggregation in distributed streaming scenarios, such as sensor networks: the sketch is duplicate insensitive, i.e., reinsertions of the same data will not affect the sketch and hence the estimates of aggregates. Unlike previous duplicate-insensitive sketc...

The tradeoff between the ease of sketching a mechanical system on paper and the power of representing it on a computer is too great, as evidenced by the fact that mechanical designers typically begin by sketching their designs on paper, then transfer them to the computer only after the initial design process is complete. To bring early design to the computer, we must develop a tool that allows ...