VLDeformer: Vision–Language Decomposed Transformer for fast cross-modal retrieval
Lisai Zhang, Hongfa Wu, Qingcai Chen, Yimeng Deng, Joanna Siebert, Zhonghua Li, Yunpeng Han, Dejiang Kong, Zhao Cao
Topics & Concepts
TransformerComputer scienceModalSearch engine indexingArtificial intelligenceEncoderInferenceEmbeddingPairwise comparisonNatural language processingPattern recognition (psychology)Speech recognitionVoltageEngineeringOperating systemChemistryElectrical engineeringPolymer chemistryMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning