High level semantic concept retrieval using a hybrid similarity method
In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level feature...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Book Section |
| Published: |
Springer
2012
|
| _version_ | 1796970877912350720 |
|---|---|
| author | Kouchehbagh, Sara Memar Affendey, Lilly Suriani Mustapha, Norwati C. Doraisamy, Shyamala Ektefa, Mohammadreza |
| author2 | Lukose, Dickson |
| author_facet | Lukose, Dickson Kouchehbagh, Sara Memar Affendey, Lilly Suriani Mustapha, Norwati C. Doraisamy, Shyamala Ektefa, Mohammadreza |
| author_sort | Kouchehbagh, Sara Memar |
| collection | UPM |
| description | In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level features, the semantic meaning of the query cannot be expressed in this way. Moreover, the limitation of retrieval using desirable concept detectors is providing annotations for each concept. However, providing annotation for every concept in real world is very challenging and time consuming, and it is not possible to provide annotation for every concept in the real world. In this study, in order to improve the effectiveness of the retrieval, a method for similarity computation is proposed and experimented for mapping concepts whose annotations are not available onto the annotated and known concepts. The TRECVID 2005 data set is used to evaluate the effectiveness of the concept-based video retrieval model by applying the proposed similarity method. Results are also compared with previous similarity measures used in the same domain. The proposed similarity measure approach outperforms other methods with the Mean Average Precision (MAP) of 26.84% in concept retrieval. |
| first_indexed | 2024-03-06T08:04:37Z |
| format | Book Section |
| id | upm.eprints-26091 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T08:04:37Z |
| publishDate | 2012 |
| publisher | Springer |
| record_format | dspace |
| spelling | upm.eprints-260912016-01-19T04:29:40Z http://psasir.upm.edu.my/id/eprint/26091/ High level semantic concept retrieval using a hybrid similarity method Kouchehbagh, Sara Memar Affendey, Lilly Suriani Mustapha, Norwati C. Doraisamy, Shyamala Ektefa, Mohammadreza In video search and retrieval, user’s need is expressed in terms of query. Early video retrieval systems usually matched video clips with such low-level features as color, shape, texture, and motion. In spite of the fact that retrieval is done accurately and automatically with such low-level features, the semantic meaning of the query cannot be expressed in this way. Moreover, the limitation of retrieval using desirable concept detectors is providing annotations for each concept. However, providing annotation for every concept in real world is very challenging and time consuming, and it is not possible to provide annotation for every concept in the real world. In this study, in order to improve the effectiveness of the retrieval, a method for similarity computation is proposed and experimented for mapping concepts whose annotations are not available onto the annotated and known concepts. The TRECVID 2005 data set is used to evaluate the effectiveness of the concept-based video retrieval model by applying the proposed similarity method. Results are also compared with previous similarity measures used in the same domain. The proposed similarity measure approach outperforms other methods with the Mean Average Precision (MAP) of 26.84% in concept retrieval. Springer Lukose, Dickson Ahmad, Abdul Rahim Suliman, Azizah 2012 Book Section PeerReviewed Kouchehbagh, Sara Memar and Affendey, Lilly Suriani and Mustapha, Norwati and C. Doraisamy, Shyamala and Ektefa, Mohammadreza (2012) High level semantic concept retrieval using a hybrid similarity method. In: Knowledge Technology. Communications in Computer and Information Science (295). Springer, Berlin, pp. 262-271. ISBN 9783642328251; EISBN: 9783642328268 10.1007/978-3-642-32826-8_27 |
| spellingShingle | Kouchehbagh, Sara Memar Affendey, Lilly Suriani Mustapha, Norwati C. Doraisamy, Shyamala Ektefa, Mohammadreza High level semantic concept retrieval using a hybrid similarity method |
| title | High level semantic concept retrieval using a hybrid similarity method |
| title_full | High level semantic concept retrieval using a hybrid similarity method |
| title_fullStr | High level semantic concept retrieval using a hybrid similarity method |
| title_full_unstemmed | High level semantic concept retrieval using a hybrid similarity method |
| title_short | High level semantic concept retrieval using a hybrid similarity method |
| title_sort | high level semantic concept retrieval using a hybrid similarity method |
| work_keys_str_mv | AT kouchehbaghsaramemar highlevelsemanticconceptretrievalusingahybridsimilaritymethod AT affendeylillysuriani highlevelsemanticconceptretrievalusingahybridsimilaritymethod AT mustaphanorwati highlevelsemanticconceptretrievalusingahybridsimilaritymethod AT cdoraisamyshyamala highlevelsemanticconceptretrievalusingahybridsimilaritymethod AT ektefamohammadreza highlevelsemanticconceptretrievalusingahybridsimilaritymethod |