Long-term activity forecasting is an especially challenging research pro...
In egocentric action recognition a single population model is typically
...
Understanding users' activities from head-mounted cameras is a fundament...
Supervised deep-embedding methods project inputs of a domain to a
repres...
We consider visual domains in which a class label specifies the content ...
The focus in machine learning has branched beyond training classifiers o...
Deep-embedding methods aim to discover representations of a domain that ...
With the resurgence of interest in neural networks, representation learn...