%0 Conference Proceedings %T Cross-modal classification by completing unimodal representations %+ Département Intelligence Ambiante et Systèmes Interactifs (DIASI) %+ CEDRIC. Données complexes, apprentissage et représentations (CEDRIC - VERTIGO) %A Tran, Thi Quynh Nhi %A Le Borgne, Hervé %A Crucianu, M. %Z Conference of 2016 ACM Workshop on Vision and Language Integration Meets Multimedia Fusion, Iv and L-MM 2016 ; Conference Date: 16 October 2016; Conference Code:124317 %< avec comité de lecture %B iV&L-MM '16 Proceedings of the 2016 ACM workshop on Vision and Language Integration Meets Multimedia Fusion %C Amsterdam, Netherlands %I Association for Computing Machinery, Inc %P 17-25 %8 2016-10-16 %D 2016 %R 10.1145/2983563.2983570 %K Multimedia Retrieval %K Cross-modal %K Text processing %K Unimodal %K nocv2 %K Real applications %K Representation method %K Specific problems %Z Engineering Sciences [physics]Conference papers %X We argue that cross-modal classification, where models are trained on data from one modality (e.g. text) and applied to data from another (e.g. image), is a relevant problem in multimedia retrieval. We propose a method that addresses this specific problem, related to but different from cross-modal retrieval and bimodal classification. This method relies on a common latent space where both modalities have comparable representations and on an auxiliary dataset from which we build a more complete bimodal representation of any unimodal data. Evaluations on Pascal VOC07 and NUS-WIDE show that the novel representation method significantly improves the results compared to the use of a latent space alone. The level of performance achieved makes cross-modal classification a convincing choice for real applications. %G English %2 https://cea.hal.science/cea-01840417/document %2 https://cea.hal.science/cea-01840417/file/ivlm08-tranA.pdf %L cea-01840417 %U https://cea.hal.science/cea-01840417 %~ CEA %~ CNAM %~ OPENAIRE %~ DRT %~ CEA-UPSAY %~ UNIV-PARIS-SACLAY %~ CEA-UPSAY-SACLAY %~ LIST %~ CEDRIC-CNAM %~ GS-ENGINEERING %~ GS-COMPUTER-SCIENCE %~ HESAM-CNAM %~ HESAM