An integrated semantic-based approach in concept based video retrieval

Abstract

Multimedia content has been growing quickly and video retrieval is regarded as one of the most famous issues in multimedia research. In order to retrieve a desirable video, users express their needs in terms of queries. Queries can be on object, motion, texture, color, audio, etc. Low-level representations of video are different from the higher level concepts which a user associates with video. Therefore, query based on semantics is more realistic and tangible for end user. Comprehending the semantics of query has opened a new insight in video retrieval and bridging the semantic gap. However, the problem is that the video needs to be manually annotated in order to support queries expressed in terms of semantic concepts. Annotating semantic concepts which appear in video shots is a challenging and time-consuming task. Moreover, it is not possible to provide annotation for every concept in the real world. In this study, an integrated semantic-based approach for similarity computation is proposed with respect to enhance the retrieval effectiveness in concept-based video retrieval. The proposed method is based on the integration of knowledge-based and corpus-based semantic word similarity measures in order to retrieve video shots for concepts whose annotations are not available for the system. The TRECVID 2005 dataset is used for evaluation purpose, and the results of applying proposed method are then compared against the individual knowledgebased and corpus-based semantic word similarity measures which were utilized in previous studies in the same domain. The superiority of integrated similarity method is shown and evaluated in terms of Mean Average Precision (MAP).

Semantic Based Video Retrieval System: Survey

“…Memar et al [74] are proposed method that is based on the integration of knowledge-based and corpus-based semantic word similarity measures in order to retrieve video shots for concepts whose annotations are not available for the system. Mean Average Precision (MAP) is used with TRECVID 2005 dataset to evaluate the superiority of integrated similarity method and the results show that the combined corpus based and knowledge based measures is better than each of the methods alone.…”

A Comparative Study of Local Features in Face-based Video Retrieval

“…Content-based methods [1] overcome this manual burden by automatically recognizing colors and textures, and have become an active arena of multimedia research [6]. Semantic-based methods [7] aim to derive the meaning behind the scenes and perform matching based on meaning rather than physical traits, i.e., crossing the semantic gap in video retrieval [4]. In this paper, we combine the contentbased and semantic-based methods; that is, we extract key faces using content analysis and derive face profiles of a video fragment as its semantic representation.…”

Semantic Enriched Lecture Video Retrieval System Using Feature Mixture and Hybrid Classification

“…The use of the multi-modal data in the system makes the video retrieval less accurate. Sara Memar et al [6] have proposed an approach which combines the knowledge-based and corpus-based semantic word similarity measures. This method allows the effective retrieval of the video files through the finding of the semantic similarity.…”

“…The text based video retrieval method retrieves the text video files present in the database. The content-based video retrieval method allows the retrieval of the video files with small amount of the text data [6]. The content-based video retrieval method finds a wide application since most of the video files have a small amount of the text data.…”