Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
Jul 1, 2018
In recent years machine learning methods for human activity recognition have been found very effective. These classify discriminative features generated from raw input sequences acquired from body-worn inertial sensors. However, it involves an explic...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Apr 1, 2018
Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, long short-term memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynami...
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
Aug 1, 2016
Existing smart environment based alert solutions have adopted a relatively complex and tailored approach to supporting individuals. These solutions have involved sensor based monitoring, activity recognition and assistance provisioning. Traditionally...
IEEE transactions on pattern analysis and machine intelligence
Jan 1, 2016
An important aspect of human perception is anticipation, which we use extensively in our day-to-day activities when interacting with other humans as well as with our surroundings. Anticipating which activities will a human do next (and how) can enabl...
IEEE transactions on pattern analysis and machine intelligence
Jul 1, 2015
Systems based on bag-of-words models from image features collected at maxima of sparse interest point operators have been used successfully for both computer visual object and action recognition tasks. While the sparse, interest-point based approach ...
IEEE transactions on pattern analysis and machine intelligence
Jan 1, 2015
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient c...