Users are generally interested in the edge-ranked section of returning search results, according to an analysis of click-through data from a very big search engine log. As a result, search engines must achieve great accuracy with top-ranked documents. While there are many methods for improving video search performance, they either ignore the above factor or have difficulties in practical applications. In this paper, we introduce CR Re-Rating, a flexible and effective re-rating approach for improving recovery efficiency. CR Re-Rating employs a cross-referencing (CR) technique to integrate multimodal data in order to deliver high accuracy for top-rated outcomes. Test findings reveal that search quality has greatly improved, particularly for top-ranked results.

Clustering, image/video retrieval, multimedia databases

In this study, we describe a new reclassification approach that uses a cross-referencing mechanism to integrate multimodal characteristics. It can handle first search results in modal spaces such as color and text separately. The early search results, in particular, are separated into numerous unique groups in various feature spaces. Each space's clusters are then assigned to predetermined ranks depending on their relevance to the inquiry. The cross-referencing technique may integrate ranked clusters of all feature spaces hierarchically into a single enhanced result rating using ranked clusters of all feature spaces. Test findings reveal that search performance has greatly improved, particularly for top-ranked results.

-

S. Purushothaman (2023). Improvisation of Retrieval Effectiveness by CR-Reranking Method. International Journal on Emerging Technologies, 14(2): 06–12.