Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900205851> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W2900205851 abstract "The paper dives into the topic of image captioning with the soft attention algorithm. We first review relevant works on the captioned topic in terms of background introduction and then explains the original model in details. On top of the plain soft attention model, we propose two approaches for further improvements: SE attention model which adds an extra channel-wise activation layer, and bi-directional attention model that explores two-way attention order feasibility. We implement both methods under limited experiment conditions and in addition swap the original encoder with state-of-art structure. Quantitative results and example demonstrations show that our proposed methods have achieved better performance than baselines. In the end, some suggestions of future work on top of proposed are summarized for a purpose of completeness." @default.
- W2900205851 created "2018-11-16" @default.
- W2900205851 creator A5076278380 @default.
- W2900205851 date "2018-08-27" @default.
- W2900205851 modified "2023-09-23" @default.
- W2900205851 title "Improvement of Embedding Channel-Wise Activation in Soft-Attention Neural Image Captioning" @default.
- W2900205851 cites W1895577753 @default.
- W2900205851 cites W1905882502 @default.
- W2900205851 cites W2064675550 @default.
- W2900205851 cites W2101105183 @default.
- W2900205851 cites W2128272608 @default.
- W2900205851 cites W2131774270 @default.
- W2900205851 cites W2154071538 @default.
- W2900205851 cites W2339652278 @default.
- W2900205851 cites W2752782242 @default.
- W2900205851 cites W2963758027 @default.
- W2900205851 cites W3000226596 @default.
- W2900205851 doi "https://doi.org/10.1145/3271553.3271592" @default.
- W2900205851 hasPublicationYear "2018" @default.
- W2900205851 type Work @default.
- W2900205851 sameAs 2900205851 @default.
- W2900205851 citedByCount "0" @default.
- W2900205851 crossrefType "proceedings-article" @default.
- W2900205851 hasAuthorship W2900205851A5076278380 @default.
- W2900205851 hasConcept C115961682 @default.
- W2900205851 hasConcept C127162648 @default.
- W2900205851 hasConcept C154945302 @default.
- W2900205851 hasConcept C157657479 @default.
- W2900205851 hasConcept C28490314 @default.
- W2900205851 hasConcept C31972630 @default.
- W2900205851 hasConcept C41008148 @default.
- W2900205851 hasConcept C41608201 @default.
- W2900205851 hasConcept C76155785 @default.
- W2900205851 hasConceptScore W2900205851C115961682 @default.
- W2900205851 hasConceptScore W2900205851C127162648 @default.
- W2900205851 hasConceptScore W2900205851C154945302 @default.
- W2900205851 hasConceptScore W2900205851C157657479 @default.
- W2900205851 hasConceptScore W2900205851C28490314 @default.
- W2900205851 hasConceptScore W2900205851C31972630 @default.
- W2900205851 hasConceptScore W2900205851C41008148 @default.
- W2900205851 hasConceptScore W2900205851C41608201 @default.
- W2900205851 hasConceptScore W2900205851C76155785 @default.
- W2900205851 hasLocation W29002058511 @default.
- W2900205851 hasOpenAccess W2900205851 @default.
- W2900205851 hasPrimaryLocation W29002058511 @default.
- W2900205851 hasRelatedWork W2005185696 @default.
- W2900205851 hasRelatedWork W2092957489 @default.
- W2900205851 hasRelatedWork W2130228941 @default.
- W2900205851 hasRelatedWork W2161229648 @default.
- W2900205851 hasRelatedWork W2235753890 @default.
- W2900205851 hasRelatedWork W2366116130 @default.
- W2900205851 hasRelatedWork W2795359650 @default.
- W2900205851 hasRelatedWork W2923366293 @default.
- W2900205851 hasRelatedWork W2945836425 @default.
- W2900205851 hasRelatedWork W2993674027 @default.
- W2900205851 isParatext "false" @default.
- W2900205851 isRetracted "false" @default.
- W2900205851 magId "2900205851" @default.
- W2900205851 workType "article" @default.