A novel method for image captioning using multimodal feature fusion employing mask RNN and LSTM models
Kumaravel Thangavel, Natesan Palanisamy, Suresh Muthusamy, Om Prava Mishra, Suma Christal Mary Sundararajan, Hitesh Panchal, Ashok Kumar Loganathan, Ponarun Ramamoorthi
Topics & Concepts
Closed captioningComputer scienceArtificial intelligenceConvolutional neural networkDeep learningFeature (linguistics)Recurrent neural networkCoding (social sciences)Decoding methodsPattern recognition (psychology)SalientFeature extractionMachine learningArtificial neural networkImage (mathematics)Natural language processingPhilosophyTelecommunicationsMathematicsLinguisticsStatisticsMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesAdvanced Neural Network Applications