Main Article Content


Most of the users pay large attention only in top ranked portion of returned search results .So it is very essential to achieve high accuracy on top ranked documents there are so many methods to boost video search performance, they either pay less attention to the above factor or encounter difficulties in practical applications. In order to develop retrieval effectiveness, We should present This paper the on a flexible and effective re ranking method, called CR-Re ranking. For the purpose of fusing multimodal cues CR-Re ranking employs a cross-reference (CR) it is used to offer high accuracy on top ranked results Specifically, multimodal features are first utilized separately to re rank the initial returned results at the cluster level, and then all the ranked clusters from different modalities are cooperatively used to infer the shots with high relevance. Experimental results show that the search quality, especially on the top-ranked results, is improved significantly

Article Details

How to Cite
R.Navinkumar, & T.Sathishkumar. (2017). Multimodal fusion for video search re ranking . International Journal of Intellectual Advancements and Research in Engineering Computations, 5(2), 1550–1557. Retrieved from