Spectrum normalization is a process shared by two saliency detection methods, Spectral Residual (SR) and Phase Fourier Transform (PFT). In this paper, we point out that the essence...
—With the proliferation of motion capture data, interest in removing noise and outliers from motion capture data has increased. In this paper, we introduce an efficient human mo...
Trajectory prediction (TP) of moving objects has grown rapidly to be a new exciting paradigm. However, existing prediction algorithms mainly employ kinematical models to approximat...
Semantic Web applications take off is being slower than expected, at least with respect to “real-world” applications and users. One of the main reasons for this lack of adoptio...
Structured output prediction is an important machine learning problem both in theory and practice, and the max-margin Markov network (M3 N) is an effective approach. All state-of-...