FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3101313921> ?p ?o ?g. }

• W3101313921 endingPage "8150" @default.
• W3101313921 startingPage "8142" @default.
• W3101313921 abstract "In this paper, we propose a novel conditional-generativeadversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent evaluation problem among different objective language metrics, we are motivated to design some “discriminator” networks to automatically and progressively determine whether generated caption is human described or machine generated. Two kinds of discriminator architectures (CNN and RNNbased structures) are introduced since each has its own advantages. The proposed algorithm is generic so that it can enhance any existing RL-based image captioning framework and we show that the conventional RL training method is just a special case of our approach. Empirically, we show consistent improvements over all language evaluation metrics for different state-of-the-art image captioning models. In addition, the well-trained discriminators can also be viewed as objective image captioning evaluators." @default.
• W3101313921 created "2020-11-23" @default.
• W3101313921 creator A5035270433 @default.
• W3101313921 creator A5056790957 @default.
• W3101313921 creator A5066439149 @default.
• W3101313921 creator A5071290194 @default.
• W3101313921 creator A5082959853 @default.
• W3101313921 creator A5086850966 @default.
• W3101313921 date "2019-07-17" @default.
• W3101313921 modified "2023-10-04" @default.
• W3101313921 title "Improving Image Captioning with Conditional Generative Adversarial Nets" @default.
• W3101313921 cites W1522301498 @default.
• W3101313921 cites W1775434803 @default.
• W3101313921 cites W1861492603 @default.
• W3101313921 cites W1895577753 @default.
• W3101313921 cites W1905882502 @default.
• W3101313921 cites W1956340063 @default.
• W3101313921 cites W2099471712 @default.
• W3101313921 cites W2101105183 @default.
• W3101313921 cites W2121863487 @default.
• W3101313921 cites W2123301721 @default.
• W3101313921 cites W2125389028 @default.
• W3101313921 cites W2155027007 @default.
• W3101313921 cites W2159243025 @default.
• W3101313921 cites W2176263492 @default.
• W3101313921 cites W2194775991 @default.
• W3101313921 cites W2506483933 @default.
• W3101313921 cites W2552161745 @default.
• W3101313921 cites W2575842049 @default.
• W3101313921 cites W2607151106 @default.
• W3101313921 cites W2729842244 @default.
• W3101313921 cites W2745461083 @default.
• W3101313921 cites W2885013662 @default.
• W3101313921 cites W2887585070 @default.
• W3101313921 cites W2949376505 @default.
• W3101313921 cites W2950672580 @default.
• W3101313921 cites W2962760898 @default.
• W3101313921 cites W2962968835 @default.
• W3101313921 cites W2963084599 @default.
• W3101313921 cites W2964268978 @default.
• W3101313921 cites W648786980 @default.
• W3101313921 doi "https://doi.org/10.1609/aaai.v33i01.33018142" @default.
• W3101313921 hasPublicationYear "2019" @default.
• W3101313921 type Work @default.
• W3101313921 sameAs 3101313921 @default.
• W3101313921 citedByCount "65" @default.
• W3101313921 countsByYear W31013139212019 @default.
• W3101313921 countsByYear W31013139212020 @default.
• W3101313921 countsByYear W31013139212021 @default.
• W3101313921 countsByYear W31013139212022 @default.
• W3101313921 countsByYear W31013139212023 @default.
• W3101313921 crossrefType "journal-article" @default.
• W3101313921 hasAuthorship W3101313921A5035270433 @default.
• W3101313921 hasAuthorship W3101313921A5056790957 @default.
• W3101313921 hasAuthorship W3101313921A5066439149 @default.
• W3101313921 hasAuthorship W3101313921A5071290194 @default.
• W3101313921 hasAuthorship W3101313921A5082959853 @default.
• W3101313921 hasAuthorship W3101313921A5086850966 @default.
• W3101313921 hasBestOaLocation W31013139211 @default.
• W3101313921 hasConcept C111919701 @default.
• W3101313921 hasConcept C115961682 @default.
• W3101313921 hasConcept C118505674 @default.
• W3101313921 hasConcept C119857082 @default.
• W3101313921 hasConcept C154945302 @default.
• W3101313921 hasConcept C157657479 @default.
• W3101313921 hasConcept C204321447 @default.
• W3101313921 hasConcept C2779803651 @default.
• W3101313921 hasConcept C28490314 @default.
• W3101313921 hasConcept C39890363 @default.
• W3101313921 hasConcept C41008148 @default.
• W3101313921 hasConcept C76155785 @default.
• W3101313921 hasConcept C94915269 @default.
• W3101313921 hasConcept C97541855 @default.
• W3101313921 hasConceptScore W3101313921C111919701 @default.
• W3101313921 hasConceptScore W3101313921C115961682 @default.
• W3101313921 hasConceptScore W3101313921C118505674 @default.
• W3101313921 hasConceptScore W3101313921C119857082 @default.
• W3101313921 hasConceptScore W3101313921C154945302 @default.
• W3101313921 hasConceptScore W3101313921C157657479 @default.
• W3101313921 hasConceptScore W3101313921C204321447 @default.
• W3101313921 hasConceptScore W3101313921C2779803651 @default.
• W3101313921 hasConceptScore W3101313921C28490314 @default.
• W3101313921 hasConceptScore W3101313921C39890363 @default.
• W3101313921 hasConceptScore W3101313921C41008148 @default.
• W3101313921 hasConceptScore W3101313921C76155785 @default.
• W3101313921 hasConceptScore W3101313921C94915269 @default.
• W3101313921 hasConceptScore W3101313921C97541855 @default.
• W3101313921 hasIssue "01" @default.
• W3101313921 hasLocation W31013139211 @default.
• W3101313921 hasLocation W31013139212 @default.
• W3101313921 hasLocation W31013139213 @default.
• W3101313921 hasOpenAccess W3101313921 @default.
• W3101313921 hasPrimaryLocation W31013139211 @default.
• W3101313921 hasRelatedWork W2547835662 @default.
• W3101313921 hasRelatedWork W2769954154 @default.
• W3101313921 hasRelatedWork W2890653670 @default.
• W3101313921 hasRelatedWork W2962861439 @default.
• W3101313921 hasRelatedWork W2984518291 @default.

• next