Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment
Ming Zhang, Ke Chang, Yunfang Wu
Topics & Concepts
Computer scienceArtificial intelligenceFeature (linguistics)Natural language processingSemantic featurePattern recognition (psychology)Semantics (computer science)Computer visionFocus (optics)Interpretation (philosophy)Matching (statistics)Feature matchingMultimodal Machine Learning ApplicationsSpeech and dialogue systemsTopic Modeling