An Adversarial Learning and Canonical Correlation Analysis Based Cross-Modal Retrieval Model
| Autor: | Tri-Thanh Nguyen, Thanh-Huyen Pham, Quang-Thuy Ha, Thi-Hong Vuong |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Modality (human–computer interaction)
Computer science business.industry Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Adversarial system Modal Similarity (network science) 0202 electrical engineering electronic engineering information engineering Key (cryptography) Embedding 020201 artificial intelligence & image processing Artificial intelligence Canonical correlation business Subspace topology 0105 earth and related environmental sciences |
| Zdroj: | Intelligent Information and Database Systems ISBN: 9783030147983 ACIIDS (1) |
| DOI: | 10.1007/978-3-030-14799-0_13 |
| Popis: | The key of cross-modal retrieval approaches is to find a maximally correlated subspace among multiple datasets. This paper introduces a novel Adversarial Learning and Canonical Correlation Analysis based Cross-Modal Retrieval (ALCCA-CMR) model. For each modality, the ALCCA phase finds an effective common subspace and calculates the similarity by canonical correlation analysis embedding for cross-modal retrieval. We demonstrate an application of ALCCA-CMR model implemented for the dataset of two modalities. Experimental results on real music data show the efficacy of the proposed method in comparison with other existing ones. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|