FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977731412> ?p ?o ?g. }

• W2977731412 abstract "Current state-of-the-art image captioning algorithms have achieved great progress via reinforcement learning or generative adversarial nets, with hand-craft metrics such as CIDEr as the reward for the former and signals from adversarial discriminative networks for the latter. Despite the high scores on metrics or improvement in diversity gained from the application of these methods, they suffer from distinction with human-written sentences and drop of ratings on metrics respectively.In this paper, we propose a novel training objective for image captioning that consists of two parts representing explicit and implicit knowledge respectively. Optimizing the new reward partially with imitation learning, we devise an algorithm in which the caption generator is trained to maximize the combination of CIDEr and predictions from adversarial discriminator. Experiments on MSCOCO dataset demonstrate that the proposed method can integrate the strengths of state-of-the-arts, producing more human-like captions while maintaining comparable performance on traditional metrics." @default.
• W2977731412 created "2019-10-10" @default.
• W2977731412 creator A5000013167 @default.
• W2977731412 creator A5006247366 @default.
• W2977731412 creator A5049100650 @default.
• W2977731412 creator A5060542294 @default.
• W2977731412 creator A5065063835 @default.
• W2977731412 creator A5081497081 @default.
• W2977731412 date "2019-07-01" @default.
• W2977731412 modified "2023-09-27" @default.
• W2977731412 title "Image Captioning with Partially Rewarded Imitation Learning" @default.
• W2977731412 cites W1514535095 @default.
• W2977731412 cites W1889081078 @default.
• W2977731412 cites W1895577753 @default.
• W2977731412 cites W1897761818 @default.
• W2977731412 cites W1905882502 @default.
• W2977731412 cites W1931639407 @default.
• W2977731412 cites W1999874108 @default.
• W2977731412 cites W2061562262 @default.
• W2977731412 cites W2064675550 @default.
• W2977731412 cites W2098774185 @default.
• W2977731412 cites W2099471712 @default.
• W2977731412 cites W2105103432 @default.
• W2977731412 cites W2112796928 @default.
• W2977731412 cites W2113023245 @default.
• W2977731412 cites W2123301721 @default.
• W2977731412 cites W2154652894 @default.
• W2977731412 cites W2194775991 @default.
• W2977731412 cites W2302086703 @default.
• W2977731412 cites W2463955103 @default.
• W2977731412 cites W2506483933 @default.
• W2977731412 cites W2512434509 @default.
• W2977731412 cites W2558533273 @default.
• W2977731412 cites W2604178507 @default.
• W2977731412 cites W2616969219 @default.
• W2977731412 cites W2962968835 @default.
• W2977731412 cites W2963014947 @default.
• W2977731412 cites W2963033554 @default.
• W2977731412 cites W2963248296 @default.
• W2977731412 cites W2963248348 @default.
• W2977731412 cites W2963277051 @default.
• W2977731412 cites W2963373786 @default.
• W2977731412 cites W2963448089 @default.
• W2977731412 cites W2963877622 @default.
• W2977731412 cites W2964018924 @default.
• W2977731412 cites W2964121744 @default.
• W2977731412 cites W2964201867 @default.
• W2977731412 cites W2964268978 @default.
• W2977731412 cites W3101313921 @default.
• W2977731412 doi "https://doi.org/10.1109/ijcnn.2019.8851721" @default.
• W2977731412 hasPublicationYear "2019" @default.
• W2977731412 type Work @default.
• W2977731412 sameAs 2977731412 @default.
• W2977731412 citedByCount "0" @default.
• W2977731412 crossrefType "proceedings-article" @default.
• W2977731412 hasAuthorship W2977731412A5000013167 @default.
• W2977731412 hasAuthorship W2977731412A5006247366 @default.
• W2977731412 hasAuthorship W2977731412A5049100650 @default.
• W2977731412 hasAuthorship W2977731412A5060542294 @default.
• W2977731412 hasAuthorship W2977731412A5065063835 @default.
• W2977731412 hasAuthorship W2977731412A5081497081 @default.
• W2977731412 hasConcept C115961682 @default.
• W2977731412 hasConcept C119857082 @default.
• W2977731412 hasConcept C121332964 @default.
• W2977731412 hasConcept C126388530 @default.
• W2977731412 hasConcept C13280743 @default.
• W2977731412 hasConcept C154945302 @default.
• W2977731412 hasConcept C15744967 @default.
• W2977731412 hasConcept C157657479 @default.
• W2977731412 hasConcept C163258240 @default.
• W2977731412 hasConcept C185798385 @default.
• W2977731412 hasConcept C204321447 @default.
• W2977731412 hasConcept C205649164 @default.
• W2977731412 hasConcept C2779803651 @default.
• W2977731412 hasConcept C2780992000 @default.
• W2977731412 hasConcept C28490314 @default.
• W2977731412 hasConcept C37736160 @default.
• W2977731412 hasConcept C41008148 @default.
• W2977731412 hasConcept C62520636 @default.
• W2977731412 hasConcept C76155785 @default.
• W2977731412 hasConcept C77805123 @default.
• W2977731412 hasConcept C94915269 @default.
• W2977731412 hasConcept C97541855 @default.
• W2977731412 hasConcept C97931131 @default.
• W2977731412 hasConceptScore W2977731412C115961682 @default.
• W2977731412 hasConceptScore W2977731412C119857082 @default.
• W2977731412 hasConceptScore W2977731412C121332964 @default.
• W2977731412 hasConceptScore W2977731412C126388530 @default.
• W2977731412 hasConceptScore W2977731412C13280743 @default.
• W2977731412 hasConceptScore W2977731412C154945302 @default.
• W2977731412 hasConceptScore W2977731412C15744967 @default.
• W2977731412 hasConceptScore W2977731412C157657479 @default.
• W2977731412 hasConceptScore W2977731412C163258240 @default.
• W2977731412 hasConceptScore W2977731412C185798385 @default.
• W2977731412 hasConceptScore W2977731412C204321447 @default.
• W2977731412 hasConceptScore W2977731412C205649164 @default.
• W2977731412 hasConceptScore W2977731412C2779803651 @default.
• W2977731412 hasConceptScore W2977731412C2780992000 @default.
• W2977731412 hasConceptScore W2977731412C28490314 @default.
• W2977731412 hasConceptScore W2977731412C37736160 @default.

• next