Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213453379> ?p ?o ?g. }
- W4213453379 endingPage "2977" @default.
- W4213453379 startingPage "2966" @default.
- W4213453379 abstract "A high-quality image description requires not only the logic and fluency of language but also the richness and accuracy ofcontent. However, due to the semantic gap between vision and language, most existing image captioning approaches thatdirectly learn the cross-modal mapping from vision to language are difficult to meet these two requirements simultaneously. Inspired by the progressive learning mechanism, we trace the “generating + refining” route and propose a novel Text-GuidedGeneration and Refinement (dubbed as TGGAR) model with assistance from the guide text to improve the quality of captions.The guide text is selected from the training set according to content similarity, then utilized to explore salient objects andextend candidate words. Specifically, we follow the encoderdecoder architecture, and design a Text-Guided Relation Encoder(TGRE) to learn the visual representation that is more consistent with human visual cognition. Besides, we divide the decoderpart into two sub-modules: a Generator for the primary sentence generation and a Refiner for the sentence refinement.Generator, consisting of a standard LSTM and a Gate on Attention (GOA) module, aims to generate the primary sentencelogically and fluently. Refiner contains a caption encoder module, an attentionbased LSTM and a GOA module, whichiteratively modifies the details in the primary caption to make captions rich and accurate. Extensive experiments on theMSCOCO captioning dataset demonstrate our framework with fewer parameters remains comparable to transformer-basedmethods, and achieves state-of-the-art performance compared with other relevant approaches." @default.
- W4213453379 created "2022-02-25" @default.
- W4213453379 creator A5025436570 @default.
- W4213453379 creator A5036726873 @default.
- W4213453379 creator A5040235604 @default.
- W4213453379 creator A5051332325 @default.
- W4213453379 creator A5080852084 @default.
- W4213453379 date "2023-01-01" @default.
- W4213453379 modified "2023-10-17" @default.
- W4213453379 title "A Text-Guided Generation and Refinement Model for Image Captioning" @default.
- W4213453379 cites W1895577753 @default.
- W4213453379 cites W1905882502 @default.
- W4213453379 cites W1956340063 @default.
- W4213453379 cites W1969616664 @default.
- W4213453379 cites W2064675550 @default.
- W4213453379 cites W2101105183 @default.
- W4213453379 cites W2119717200 @default.
- W4213453379 cites W2125849446 @default.
- W4213453379 cites W2157331557 @default.
- W4213453379 cites W2194775991 @default.
- W4213453379 cites W2277195237 @default.
- W4213453379 cites W2302086703 @default.
- W4213453379 cites W2506483933 @default.
- W4213453379 cites W2520274358 @default.
- W4213453379 cites W2552161745 @default.
- W4213453379 cites W2575842049 @default.
- W4213453379 cites W2578190051 @default.
- W4213453379 cites W2745461083 @default.
- W4213453379 cites W2754689878 @default.
- W4213453379 cites W2754927243 @default.
- W4213453379 cites W2795151422 @default.
- W4213453379 cites W2798734500 @default.
- W4213453379 cites W2886641317 @default.
- W4213453379 cites W2887585070 @default.
- W4213453379 cites W2890531016 @default.
- W4213453379 cites W2962886331 @default.
- W4213453379 cites W2962935746 @default.
- W4213453379 cites W2963084599 @default.
- W4213453379 cites W2963101956 @default.
- W4213453379 cites W2964165364 @default.
- W4213453379 cites W2967045987 @default.
- W4213453379 cites W2981040192 @default.
- W4213453379 cites W2986433113 @default.
- W4213453379 cites W2986670728 @default.
- W4213453379 cites W2987327987 @default.
- W4213453379 cites W3034316193 @default.
- W4213453379 cites W3034642912 @default.
- W4213453379 cites W3035284526 @default.
- W4213453379 cites W3035323998 @default.
- W4213453379 cites W3099884890 @default.
- W4213453379 cites W3104681546 @default.
- W4213453379 cites W3175824375 @default.
- W4213453379 cites W3210150990 @default.
- W4213453379 cites W639708223 @default.
- W4213453379 cites W825973156 @default.
- W4213453379 doi "https://doi.org/10.1109/tmm.2022.3154149" @default.
- W4213453379 hasPublicationYear "2023" @default.
- W4213453379 type Work @default.
- W4213453379 citedByCount "1" @default.
- W4213453379 countsByYear W42134533792023 @default.
- W4213453379 crossrefType "journal-article" @default.
- W4213453379 hasAuthorship W4213453379A5025436570 @default.
- W4213453379 hasAuthorship W4213453379A5036726873 @default.
- W4213453379 hasAuthorship W4213453379A5040235604 @default.
- W4213453379 hasAuthorship W4213453379A5051332325 @default.
- W4213453379 hasAuthorship W4213453379A5080852084 @default.
- W4213453379 hasConcept C111919701 @default.
- W4213453379 hasConcept C115961682 @default.
- W4213453379 hasConcept C118505674 @default.
- W4213453379 hasConcept C121332964 @default.
- W4213453379 hasConcept C154945302 @default.
- W4213453379 hasConcept C157657479 @default.
- W4213453379 hasConcept C163258240 @default.
- W4213453379 hasConcept C165801399 @default.
- W4213453379 hasConcept C204321447 @default.
- W4213453379 hasConcept C2777530160 @default.
- W4213453379 hasConcept C2780992000 @default.
- W4213453379 hasConcept C28490314 @default.
- W4213453379 hasConcept C41008148 @default.
- W4213453379 hasConcept C62520636 @default.
- W4213453379 hasConcept C66322947 @default.
- W4213453379 hasConceptScore W4213453379C111919701 @default.
- W4213453379 hasConceptScore W4213453379C115961682 @default.
- W4213453379 hasConceptScore W4213453379C118505674 @default.
- W4213453379 hasConceptScore W4213453379C121332964 @default.
- W4213453379 hasConceptScore W4213453379C154945302 @default.
- W4213453379 hasConceptScore W4213453379C157657479 @default.
- W4213453379 hasConceptScore W4213453379C163258240 @default.
- W4213453379 hasConceptScore W4213453379C165801399 @default.
- W4213453379 hasConceptScore W4213453379C204321447 @default.
- W4213453379 hasConceptScore W4213453379C2777530160 @default.
- W4213453379 hasConceptScore W4213453379C2780992000 @default.
- W4213453379 hasConceptScore W4213453379C28490314 @default.
- W4213453379 hasConceptScore W4213453379C41008148 @default.
- W4213453379 hasConceptScore W4213453379C62520636 @default.
- W4213453379 hasConceptScore W4213453379C66322947 @default.
- W4213453379 hasFunder F4320321001 @default.
- W4213453379 hasFunder F4320335787 @default.