FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174441232> ?p ?o ?g. }

• W3174441232 endingPage "2055" @default.
• W3174441232 startingPage "2047" @default.
• W3174441232 abstract "Recent video captioning work improves greatly due to the invention of various elaborate model architectures. If multiple captioning models are combined into a unified framework not only by simple more ensemble, and each model can benefit from each other, the final captioning might be boosted further. Jointly training of multiple model have not been explored in previous works. In this paper, we propose a novel Augmented Partial Mutual Learning (APML) training method where multiple decoders are trained jointly with mimicry losses between different decoders and different input variations. Another problem of training captioning model is the one-to-many mapping problem which means that one identical video input is mapped to multiple caption annotations. To address this problem, we propose an annotation-wise frame masking approach to convert the one-to-many mapping to one-to-one mapping. The experiments performed on MSR-VTT and MSVD datasets demonstrate our proposed algorithm achieves the state-of-the-art performance." @default.
• W3174441232 created "2021-07-05" @default.
• W3174441232 creator A5041724690 @default.
• W3174441232 creator A5041890622 @default.
• W3174441232 creator A5055723755 @default.
• W3174441232 date "2021-05-18" @default.
• W3174441232 modified "2023-09-30" @default.
• W3174441232 title "Augmented Partial Mutual Learning with Frame Masking for Video Captioning" @default.
• W3174441232 cites W1566289585 @default.
• W3174441232 cites W1601567445 @default.
• W3174441232 cites W1895577753 @default.
• W3174441232 cites W1956340063 @default.
• W3174441232 cites W2101105183 @default.
• W3174441232 cites W2110933980 @default.
• W3174441232 cites W2130942839 @default.
• W3174441232 cites W2133459682 @default.
• W3174441232 cites W2139501017 @default.
• W3174441232 cites W2154652894 @default.
• W3174441232 cites W2552161745 @default.
• W3174441232 cites W2554906389 @default.
• W3174441232 cites W2556388456 @default.
• W3174441232 cites W2579549467 @default.
• W3174441232 cites W2618127004 @default.
• W3174441232 cites W2621571501 @default.
• W3174441232 cites W2745461083 @default.
• W3174441232 cites W2890531016 @default.
• W3174441232 cites W2891955747 @default.
• W3174441232 cites W2904698318 @default.
• W3174441232 cites W2905145027 @default.
• W3174441232 cites W2948358897 @default.
• W3174441232 cites W2951390634 @default.
• W3174441232 cites W2962681491 @default.
• W3174441232 cites W2962990649 @default.
• W3174441232 cites W2963341956 @default.
• W3174441232 cites W2963351113 @default.
• W3174441232 cites W2963403868 @default.
• W3174441232 cites W2963971014 @default.
• W3174441232 cites W2984862483 @default.
• W3174441232 cites W2988753485 @default.
• W3174441232 cites W3025796084 @default.
• W3174441232 cites W3034221024 @default.
• W3174441232 cites W3035365026 @default.
• W3174441232 cites W3035392611 @default.
• W3174441232 cites W3096935578 @default.
• W3174441232 cites W3099999560 @default.
• W3174441232 doi "https://doi.org/10.1609/aaai.v35i3.16301" @default.
• W3174441232 hasPublicationYear "2021" @default.
• W3174441232 type Work @default.
• W3174441232 sameAs 3174441232 @default.
• W3174441232 citedByCount "8" @default.
• W3174441232 countsByYear W31744412322021 @default.
• W3174441232 countsByYear W31744412322022 @default.
• W3174441232 countsByYear W31744412322023 @default.
• W3174441232 crossrefType "journal-article" @default.
• W3174441232 hasAuthorship W3174441232A5041724690 @default.
• W3174441232 hasAuthorship W3174441232A5041890622 @default.
• W3174441232 hasAuthorship W3174441232A5055723755 @default.
• W3174441232 hasBestOaLocation W31744412321 @default.
• W3174441232 hasConcept C115961682 @default.
• W3174441232 hasConcept C126042441 @default.
• W3174441232 hasConcept C142362112 @default.
• W3174441232 hasConcept C153349607 @default.
• W3174441232 hasConcept C154945302 @default.
• W3174441232 hasConcept C157657479 @default.
• W3174441232 hasConcept C2776321320 @default.
• W3174441232 hasConcept C2777402240 @default.
• W3174441232 hasConcept C28490314 @default.
• W3174441232 hasConcept C41008148 @default.
• W3174441232 hasConcept C76155785 @default.
• W3174441232 hasConceptScore W3174441232C115961682 @default.
• W3174441232 hasConceptScore W3174441232C126042441 @default.
• W3174441232 hasConceptScore W3174441232C142362112 @default.
• W3174441232 hasConceptScore W3174441232C153349607 @default.
• W3174441232 hasConceptScore W3174441232C154945302 @default.
• W3174441232 hasConceptScore W3174441232C157657479 @default.
• W3174441232 hasConceptScore W3174441232C2776321320 @default.
• W3174441232 hasConceptScore W3174441232C2777402240 @default.
• W3174441232 hasConceptScore W3174441232C28490314 @default.
• W3174441232 hasConceptScore W3174441232C41008148 @default.
• W3174441232 hasConceptScore W3174441232C76155785 @default.
• W3174441232 hasIssue "3" @default.
• W3174441232 hasLocation W31744412321 @default.
• W3174441232 hasOpenAccess W3174441232 @default.
• W3174441232 hasPrimaryLocation W31744412321 @default.
• W3174441232 hasRelatedWork W2384117792 @default.
• W3174441232 hasRelatedWork W2783914607 @default.
• W3174441232 hasRelatedWork W2901467237 @default.
• W3174441232 hasRelatedWork W2911868273 @default.
• W3174441232 hasRelatedWork W2923366293 @default.
• W3174441232 hasRelatedWork W3008515501 @default.
• W3174441232 hasRelatedWork W3045015651 @default.
• W3174441232 hasRelatedWork W4307856881 @default.
• W3174441232 hasRelatedWork W4312095940 @default.
• W3174441232 hasRelatedWork W4320016117 @default.
• W3174441232 hasVolume "35" @default.
• W3174441232 isParatext "false" @default.
• W3174441232 isRetracted "false" @default.
• W3174441232 magId "3174441232" @default.

• next