Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval
Most existing cross-modal retrieval approaches learn the same couple of projection matrices for different sub-retrieval tasks (such as, image retrieves text and text retrieves image) and various queries. They ignore the important fact that, different sub-retrieval tasks and queries have unique chara...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8352779/ |
| _version_ | 1818927454733991936 |
|---|---|
| author | Li Wang Lei Zhu En Yu Jiande Sun Huaxiang Zhang |
| author_facet | Li Wang Lei Zhu En Yu Jiande Sun Huaxiang Zhang |
| author_sort | Li Wang |
| collection | DOAJ |
| description | Most existing cross-modal retrieval approaches learn the same couple of projection matrices for different sub-retrieval tasks (such as, image retrieves text and text retrieves image) and various queries. They ignore the important fact that, different sub-retrieval tasks and queries have unique characteristics themselves in real practice. To tackle the problem, we propose a task-dependent and query-dependent subspace learning approach for cross-modal retrieval. Specifically, we first develop a unified cross-modal learning framework, where task-specific and category-specific subspaces can be learned simultaneously via an efficient iterative optimization. Based on this step, a task-category-projection mapping table is built. Subsequently, an efficient linear classifier is trained to learn a semantic mapping function between multimedia documents and their potential categories. In the online retrieval stage, the task-dependent and query-dependent matching subspace is adaptively identified by considering the specific sub-retrieval task type, the potential semantic category of the query, and the task-category-projection mapping table. Experimental results demonstrate the superior performance of the proposed approach compared with several state-of-the-art techniques. |
| first_indexed | 2024-12-20T03:13:16Z |
| format | Article |
| id | doaj.art-3d494034b8b04750b50d995deebea0b3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T03:13:16Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3d494034b8b04750b50d995deebea0b32022-12-21T19:55:25ZengIEEEIEEE Access2169-35362018-01-016270912710210.1109/ACCESS.2018.28316758352779Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal RetrievalLi Wang0Lei Zhu1https://orcid.org/0000-0002-2993-7142En Yu2Jiande Sun3https://orcid.org/0000-0001-6157-2051Huaxiang Zhang4https://orcid.org/0000-0001-6259-7533School of Information Science and Engineering, Shandong Normal University, Jinan, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan, ChinaMost existing cross-modal retrieval approaches learn the same couple of projection matrices for different sub-retrieval tasks (such as, image retrieves text and text retrieves image) and various queries. They ignore the important fact that, different sub-retrieval tasks and queries have unique characteristics themselves in real practice. To tackle the problem, we propose a task-dependent and query-dependent subspace learning approach for cross-modal retrieval. Specifically, we first develop a unified cross-modal learning framework, where task-specific and category-specific subspaces can be learned simultaneously via an efficient iterative optimization. Based on this step, a task-category-projection mapping table is built. Subsequently, an efficient linear classifier is trained to learn a semantic mapping function between multimedia documents and their potential categories. In the online retrieval stage, the task-dependent and query-dependent matching subspace is adaptively identified by considering the specific sub-retrieval task type, the potential semantic category of the query, and the task-category-projection mapping table. Experimental results demonstrate the superior performance of the proposed approach compared with several state-of-the-art techniques.https://ieeexplore.ieee.org/document/8352779/Cross-modal retrievaltask- and query-dependent subspace learningtask-category-projection mapping tablesemantic mapping function |
| spellingShingle | Li Wang Lei Zhu En Yu Jiande Sun Huaxiang Zhang Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval IEEE Access Cross-modal retrieval task- and query-dependent subspace learning task-category-projection mapping table semantic mapping function |
| title | Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval |
| title_full | Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval |
| title_fullStr | Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval |
| title_full_unstemmed | Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval |
| title_short | Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval |
| title_sort | task dependent and query dependent subspace learning for cross modal retrieval |
| topic | Cross-modal retrieval task- and query-dependent subspace learning task-category-projection mapping table semantic mapping function |
| url | https://ieeexplore.ieee.org/document/8352779/ |
| work_keys_str_mv | AT liwang taskdependentandquerydependentsubspacelearningforcrossmodalretrieval AT leizhu taskdependentandquerydependentsubspacelearningforcrossmodalretrieval AT enyu taskdependentandquerydependentsubspacelearningforcrossmodalretrieval AT jiandesun taskdependentandquerydependentsubspacelearningforcrossmodalretrieval AT huaxiangzhang taskdependentandquerydependentsubspacelearningforcrossmodalretrieval |