Identifying and controlling bias is a key problem in empirical sciences. Causal diagram theory provides graphical criteria for deciding whether and how causal effects can be iden...
Prior use of machine learning in genre classification used a list of labels as classification categories. However, genre classes are often organised into hierarchies, e.g., coveri...
We show that document image decoding (DID) supervised training algorithms, as a result of recent refinements, achieve high accuracy with low manual effort even under conditions o...
In our previous work, we introduced Spatially Varying Transforms (SVT) for video coding, where the location of the transform block within the macroblock is not fixed but varying. ...
Cixun Zhang, Kemal Ugur, Jani Lainema, Moncef Gabb...
This work introduces two complementary techniques to improve the packet loss resilience of scalable video coding systems. First, a “switch per-pixel” error concealment (SPEC) ...