Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308288720> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4308288720 abstract "Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately model global-local representation across video frames for caption generation, leaving plenty of room for improvement. In this work, we approach the video captioning task from a new perspective and propose a GL-RG framework for video captioning, namely a textbf{G}lobal-textbf{L}ocal textbf{R}epresentation textbf{G}ranularity. Our GL-RG demonstrates three advantages over the prior efforts: 1) we explicitly exploit extensive visual representations from different video ranges to improve linguistic expression; 2) we devise a novel global-local encoder to produce rich semantic vocabulary to obtain a descriptive granularity of video contents across frames; 3) we develop an incremental training strategy which organizes model learning in an incremental fashion to incur an optimal captioning behavior. Experimental results on the challenging MSR-VTT and MSVD datasets show that our DL-RG outperforms recent state-of-the-art methods by a significant margin. Code is available at url{https://github.com/ylqi/GL-RG}." @default.
- W4308288720 created "2022-11-10" @default.
- W4308288720 creator A5027961969 @default.
- W4308288720 creator A5040062188 @default.
- W4308288720 creator A5051107002 @default.
- W4308288720 creator A5051925942 @default.
- W4308288720 creator A5051997091 @default.
- W4308288720 creator A5055007304 @default.
- W4308288720 creator A5084853102 @default.
- W4308288720 date "2022-05-21" @default.
- W4308288720 modified "2023-09-28" @default.
- W4308288720 title "GL-RG: Global-Local Representation Granularity for Video Captioning" @default.
- W4308288720 doi "https://doi.org/10.48550/arxiv.2205.10706" @default.
- W4308288720 hasPublicationYear "2022" @default.
- W4308288720 type Work @default.
- W4308288720 citedByCount "0" @default.
- W4308288720 crossrefType "posted-content" @default.
- W4308288720 hasAuthorship W4308288720A5027961969 @default.
- W4308288720 hasAuthorship W4308288720A5040062188 @default.
- W4308288720 hasAuthorship W4308288720A5051107002 @default.
- W4308288720 hasAuthorship W4308288720A5051925942 @default.
- W4308288720 hasAuthorship W4308288720A5051997091 @default.
- W4308288720 hasAuthorship W4308288720A5055007304 @default.
- W4308288720 hasAuthorship W4308288720A5084853102 @default.
- W4308288720 hasBestOaLocation W43082887201 @default.
- W4308288720 hasConcept C111919701 @default.
- W4308288720 hasConcept C115961682 @default.
- W4308288720 hasConcept C118505674 @default.
- W4308288720 hasConcept C119857082 @default.
- W4308288720 hasConcept C138885662 @default.
- W4308288720 hasConcept C154945302 @default.
- W4308288720 hasConcept C157657479 @default.
- W4308288720 hasConcept C162324750 @default.
- W4308288720 hasConcept C177264268 @default.
- W4308288720 hasConcept C17744445 @default.
- W4308288720 hasConcept C177774035 @default.
- W4308288720 hasConcept C187736073 @default.
- W4308288720 hasConcept C195324797 @default.
- W4308288720 hasConcept C199360897 @default.
- W4308288720 hasConcept C199539241 @default.
- W4308288720 hasConcept C204321447 @default.
- W4308288720 hasConcept C2776359362 @default.
- W4308288720 hasConcept C2776760102 @default.
- W4308288720 hasConcept C2777601683 @default.
- W4308288720 hasConcept C2780451532 @default.
- W4308288720 hasConcept C41008148 @default.
- W4308288720 hasConcept C41895202 @default.
- W4308288720 hasConcept C774472 @default.
- W4308288720 hasConcept C94625758 @default.
- W4308288720 hasConceptScore W4308288720C111919701 @default.
- W4308288720 hasConceptScore W4308288720C115961682 @default.
- W4308288720 hasConceptScore W4308288720C118505674 @default.
- W4308288720 hasConceptScore W4308288720C119857082 @default.
- W4308288720 hasConceptScore W4308288720C138885662 @default.
- W4308288720 hasConceptScore W4308288720C154945302 @default.
- W4308288720 hasConceptScore W4308288720C157657479 @default.
- W4308288720 hasConceptScore W4308288720C162324750 @default.
- W4308288720 hasConceptScore W4308288720C177264268 @default.
- W4308288720 hasConceptScore W4308288720C17744445 @default.
- W4308288720 hasConceptScore W4308288720C177774035 @default.
- W4308288720 hasConceptScore W4308288720C187736073 @default.
- W4308288720 hasConceptScore W4308288720C195324797 @default.
- W4308288720 hasConceptScore W4308288720C199360897 @default.
- W4308288720 hasConceptScore W4308288720C199539241 @default.
- W4308288720 hasConceptScore W4308288720C204321447 @default.
- W4308288720 hasConceptScore W4308288720C2776359362 @default.
- W4308288720 hasConceptScore W4308288720C2776760102 @default.
- W4308288720 hasConceptScore W4308288720C2777601683 @default.
- W4308288720 hasConceptScore W4308288720C2780451532 @default.
- W4308288720 hasConceptScore W4308288720C41008148 @default.
- W4308288720 hasConceptScore W4308288720C41895202 @default.
- W4308288720 hasConceptScore W4308288720C774472 @default.
- W4308288720 hasConceptScore W4308288720C94625758 @default.
- W4308288720 hasLocation W43082887201 @default.
- W4308288720 hasOpenAccess W4308288720 @default.
- W4308288720 hasPrimaryLocation W43082887201 @default.
- W4308288720 hasRelatedWork W2547835662 @default.
- W4308288720 hasRelatedWork W2923366293 @default.
- W4308288720 hasRelatedWork W2962980738 @default.
- W4308288720 hasRelatedWork W3115399078 @default.
- W4308288720 hasRelatedWork W3119155061 @default.
- W4308288720 hasRelatedWork W3198730297 @default.
- W4308288720 hasRelatedWork W4281476091 @default.
- W4308288720 hasRelatedWork W4285600262 @default.
- W4308288720 hasRelatedWork W4287548803 @default.
- W4308288720 hasRelatedWork W4307348937 @default.
- W4308288720 isParatext "false" @default.
- W4308288720 isRetracted "false" @default.
- W4308288720 workType "article" @default.