Search

Amazon, Netflix, and other e-commerce sites allow users to read reviews of products before buying them. Some reviews can be trusted, while others can be quite misleading. The reviews of the people are generally quite diverse. The e-commerce boom has increased the need for Recommendation systems now more than ever. In light of this, the Recommendation system should be improved. It is important to consider the review's aspects for a clear understanding of the reviews. Most of the baseline models do not give enough importance to the aspect of the review. In this paper, the idea of incorporating social relation-item interaction along with the user-item interaction by understanding the aspect of the user review is incorporated to improve rating prediction. Simple linear transformations Fast Fourier Transform (FFT) are used in the proposed Recommendation system to model heterogeneous semantic relationships in texts. The attention mechanism used in traditional baseline models is not used here for representing feature learning and understanding them. The proposed model is investigated to overcome some of the limitations addressed in attention mechanism-based models. An investigative analysis is done on standard datasets: SemEval 2014 laptop reviews, and restaurant reviews. Analysis of the proposed model is also done on a real-world dataset: Yelp showing an accuracy of 80.01%. [ABSTRACT FROM AUTHOR]

The spread of surveillance cameras has necessitated the monitoring of large quantities of surveillance video feeds. A manual monitoring system is near impossible due to the large man-hour requirements. Recently, automatic abnormal activity detection has been an area of interest among researchers. A spatio-temporal feature, histogram of optical flow orientation and magnitude (HOFM), has produced impressive ability in detecting abnormal activities. The authors propose a novel non-uniform spatio-temporal region resembling parallelepipeds, from which they extract the HOFM features. Autoencoders can be configured to detect abnormal patterns. The authors have used these abilities of the autoencoders to detect abnormalities in the HOFM features extracted from their novel spatio-temporal regions of the video feeds. The autoencoders are trained on the HOFM features of the videos containing no abnormalities. The autoencoders are then fed with the HOFM features of the videos to be tested for abnormal activities, and these are detected based on the abilities of the autoencoders to reconstruct these features. The proposed method is tested on the standard abnormality detection datasets: UCSD Ped1, UCSD Ped2, Subway Entrance, Subway Exit, and UMN. [ABSTRACT FROM AUTHOR]