Home /Research /Learning a deeply supervised multi-modal RGB-D embedding for semantic scene and object category recognition
OTHER

Learning a deeply supervised multi-modal RGB-D embedding for semantic scene and object category recognition

Hasan Firdaus Mohd Zaki, Faisal Shafait, Ajmal Mian

Year
2017
Citations
20

Keywords

Computer scienceArtificial intelligenceConvolutional neural networkDiscriminative modelFeature (linguistics)RGB color modelEmbeddingPattern recognition (psychology)Benchmark (surveying)Feature learning

Related papers

Browse all OTHER papers