Method for implementing decussation retrieval between mediums through amalgamating different modality information

Abstract

The invention discloses a method for realizing the interaction searching between medias by integrating different modal information which includes the following steps: 1) building relation graphs to hypermedias and obtaining corresponding relative coefficient matrixes; 2) using media objects or the hypermedias inside or outside a database submitted by a user as a searching example to mark the initial matching degree; 3) utilizing the relative coefficient matrix between the hypermedias to repeatedly iterate to a stable state and broadcasting the matching ability to the un-marked hypermedias and returning to the hypermedias or the media objects of special modal states in the hypermedias with the matching degree of the searching example larger than 0.6; 4) periodically carrying out adjustment on the relation graphs of the hypermedia according to a searching example set and a positive example set. The invention integrates the bottom layer characteristics of various media objects and broadcasts the semanteme by the sibship between the media objects, thereby having a better searching effect; as the searching example and the state of a returning result can be different and are broadcasted by utilizing the semanteme, the searching is more accurate and the adaptation is broader.

Description

technical field [0001] The present invention relates to cross-retrieval of media between different modalities, in particular to a method for merging information of different modalities to realize cross-retrieval between media. Background technique [0002] The development of the Web is accompanied by a sharp increase in the amount of information. Faced with such a huge amount of data, retrieval has become an important means for people to obtain information. Simple text retrieval can no longer meet the increasingly complex needs of users. Just text data also includes data of different modalities such as images, videos, audios, and slides in Microsoft PowerPoint format. However, the retrieval of existing multimedia objects is generally achieved through manual labeling and matching of underlying features. The multimedia search is only suitable for use in a small area with a limited amount of data; although the matching retrieval based on the underlying features of multimedia o...

AI Technical Summary

Problems solved by technology

[0002] The development of the Web is accompanied by a sharp increase in the amount of information. Faced with such a huge amount of data, retrieval has become an important means for people to obtain information. Simple text retrieval can no longer meet the increasingly complex needs of users. Just text data also includes data in different modes such as images, videos, audios, slides in Microsoft PowerPoint format

However, the retrieval of existing multimedia objects is generally achieved through manual labeling and matching of underlying features. The multimedia search is only suitable for use in a small area with a limited amount of data; although the matching retrieval based on the underlying features of multimedia objects does not require a lot of manual input, due to the gap between the underlying features and semantics, for example, visually similar images may Represents completely different semantics, and semantically the same image may look completely different, so the retrieval method that integrates the underlying features and semantics is of great significance

[0003] At present, there is no way to directly obtain the semantics of media objects, so we can only make full use of the semantic relationship between media objects to realize retrieval based on semantics and features

Images