In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effo...
Abstract-- Traditional methods of spoken utterance classification (SUC) adopt two independently trained phases. In the first phase, an automatic speech recognition (ASR) module ret...
Sibel Yaman, Li Deng, Dong Yu, Ye-Yi Wang, Alex Ac...
It has been shown in prior work in management science, statistics and machine learning that using an ensemble of models often results in better performance than using a single ‘...
Abstract--This paper considers the automatic design of fuzzyrule-based classification systems from labeled data. The performance of classifiers and the interpretability of generate...
Eghbal G. Mansoori, Mansoor J. Zolghadri, Seraj D....
Abstract This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classifica...