Information salience

In this paper, we have proposed a simple and effective method to produce accurate saliency map for the purpose of salient object segmentation. The method uses deep learning to predict the depth map from the input image and incorporate such information to compute the saliency values. The experimental results demonstrated that the additional depth information is useful in improving the performance of object segmentation.

10p trinhthamhodang9 10-12-2020 14 1   Download

Football clubs listed on Istanbul Stock Exchange suggests an interesting way of testing stock price behaviors to different types of news about both sportive success related and non-sports related events. Strong football club stock price reactions to surprising game results and the lack of reaction to betting odds is related with the dominated structure of Turkish Football League by the big four; Galatasaray (GS), Fenerbahce (FB), Besiktas (BJK) and Trabzonspor (TS). Coherent with this idea we conclude that GS and FB stocks react strongly to unexpected game results and derby matches.

12p 035522894 13-04-2020 21 6   Download

We investigate the connection between part of speech (POS) distribution and content in language. We define POS blocks to be groups of parts of speech. We hypothesise that there exists a directly proportional relation between the frequency of POS blocks and their content salience. We also hypothesise that the class membership of the parts of speech within such blocks reflects the content load of the blocks, on the basis that open class parts of speech are more content-bearing than closed class parts of speech.

8p hongvang_1 16-04-2013 58 1   Download