• Miss. Mrunmayi Patil
• Dr.Vinod Wadne

Hash methods are proven useful for a variety of tasks and have sparked great attention in recent years. They have proposed several approaches to capture the similarities between textual, visual, and cross-cultural hashing. However, most existing bag of words methods used to represent textual information. Because words with different shapes can they have a similar meaning, semantic text similarities cannot be well elaborated in these methods. To address these challenges in this paper, introduce a new hashing method, which uses continuous representations of proposed words by capturing the semantic textual similarity level and using a deep conviction network (DBN) to build correlation between different modes. In order to demonstrate the effectiveness of the proposed method, three methods commonly used are to be considered background set in this workbook is used. The experimental results show that the proposed method achieves significantly better results in addition, the effectiveness of the proposed method is similar or superior some other hashing methods.

Fisher vector, SCMH, SIFT Descriptor, Word Embedding, Ranking, Mapping.

"Efficient Cross Media Retrieval Using Mixed Generative Based Hashing Method", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.579-582, June 2019, Available :http://www.jetir.org/papers/JETIR1906M86.pdf

"Efficient Cross Media Retrieval Using Mixed Generative Based Hashing Method", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp579-582, June 2019, Available at : http://www.jetir.org/papers/JETIR1906M86.pdf