WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2872
Volume 17, 2018
Shots Temporal Prediction Rules for High-Dimensional Data of Semantic Video Retrieval
Authors: , ,
Abstract: Some research in Semantic video retrieval is concerned with predicting the temporal existence of certain concepts. Most of the used methods in those studies depend on rules defined by experts and use ground-truth annotation. The Ground-truth annotation is time consuming and labour intensive. Additionally, it involves a limited number of annotated concepts, and a limited number of annotated shots . Video concepts have interrelated relations, so the extracted temporal rules from ground-truth annotation are often inaccurate and incomplete. However concept detections scores are a large high-dimensional continuous valued dataset, and generated automatically. Temporal association rules algorithms are efficient methods in revealing temporal relations, but they have some limitations when applied on high-dimensional and continuous-valued data. These constraints have led to a lack of research used temporal association rules. So, we propose a novel framework to encode the high-dimensional continuousvalued concept detection scores data into a single stream of characters without loss of important information and to predict a temporal shot behavior by generating temporal association rules.
Search Articles
Keywords: "Semantic Video Retrieval, Temporal Association Rules, Principle Component Analysis, Guassian Mixture Model Clustering, Expectation Maximization Algorithm, Sequential Pattern Discovery Algorithm"
Pages: 163-172
WSEAS Transactions on Computers, ISSN / E-ISSN: 1109-2750 / 2224-2872, Volume 17, 2018, Art. #20