Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200924860> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3200924860 abstract "We address the problem of temporal sentence localization in videos (TSLV). Traditional methods follow a top-down framework which localizes the target segment with pre-defined segment proposals. Although they have achieved decent performance, the proposals are handcrafted and redundant. Recently, bottom-up framework attracts increasing attention due to its superior efficiency. It directly predicts the probabilities for each frame as a boundary. However, the performance of bottom-up model is inferior to the top-down counterpart as it fails to exploit the segment-level interaction. In this paper, we propose an Adaptive Proposal Generation Network (APGN) to maintain the segment-level interaction while speeding up the efficiency. Specifically, we first perform a foreground-background classification upon the video and regress on the foreground frames to adaptively generate proposals. In this way, the handcrafted proposal design is discarded and the redundant proposals are decreased. Then, a proposal consolidation module is further developed to enhance the semantics of the generated proposals. Finally, we locate the target moments with these generated proposals following the top-down framework. Extensive experiments show that our proposed APGN significantly outperforms previous state-of-the-art methods on three challenging benchmarks." @default.
- W3200924860 created "2021-09-27" @default.
- W3200924860 creator A5008417257 @default.
- W3200924860 creator A5045685496 @default.
- W3200924860 creator A5065871371 @default.
- W3200924860 creator A5078220957 @default.
- W3200924860 date "2021-01-01" @default.
- W3200924860 modified "2023-10-16" @default.
- W3200924860 title "Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos" @default.
- W3200924860 cites W1686810756 @default.
- W3200924860 cites W1924770834 @default.
- W3200924860 cites W2111078031 @default.
- W3200924860 cites W2250539671 @default.
- W3200924860 cites W2516035629 @default.
- W3200924860 cites W2890502146 @default.
- W3200924860 cites W2894280539 @default.
- W3200924860 cites W2963017553 @default.
- W3200924860 cites W2963393391 @default.
- W3200924860 cites W2963403868 @default.
- W3200924860 cites W2963524571 @default.
- W3200924860 cites W2963668159 @default.
- W3200924860 cites W2963916161 @default.
- W3200924860 cites W2964051675 @default.
- W3200924860 cites W2964089981 @default.
- W3200924860 cites W2970401629 @default.
- W3200924860 cites W2970898753 @default.
- W3200924860 cites W2975813532 @default.
- W3200924860 cites W2979750740 @default.
- W3200924860 cites W2997429269 @default.
- W3200924860 cites W2997762001 @default.
- W3200924860 cites W2998495542 @default.
- W3200924860 cites W3025323587 @default.
- W3200924860 cites W3034743747 @default.
- W3200924860 cites W3035339529 @default.
- W3200924860 cites W3035640828 @default.
- W3200924860 cites W3046947115 @default.
- W3200924860 cites W3092739351 @default.
- W3200924860 cites W3093174808 @default.
- W3200924860 cites W3152619510 @default.
- W3200924860 cites W3174490084 @default.
- W3200924860 cites W3175082063 @default.
- W3200924860 doi "https://doi.org/10.18653/v1/2021.emnlp-main.732" @default.
- W3200924860 hasPublicationYear "2021" @default.
- W3200924860 type Work @default.
- W3200924860 sameAs 3200924860 @default.
- W3200924860 citedByCount "11" @default.
- W3200924860 countsByYear W32009248602022 @default.
- W3200924860 countsByYear W32009248602023 @default.
- W3200924860 crossrefType "proceedings-article" @default.
- W3200924860 hasAuthorship W3200924860A5008417257 @default.
- W3200924860 hasAuthorship W3200924860A5045685496 @default.
- W3200924860 hasAuthorship W3200924860A5065871371 @default.
- W3200924860 hasAuthorship W3200924860A5078220957 @default.
- W3200924860 hasBestOaLocation W32009248601 @default.
- W3200924860 hasConcept C115903868 @default.
- W3200924860 hasConcept C126042441 @default.
- W3200924860 hasConcept C135798126 @default.
- W3200924860 hasConcept C154945302 @default.
- W3200924860 hasConcept C165696696 @default.
- W3200924860 hasConcept C184337299 @default.
- W3200924860 hasConcept C199360897 @default.
- W3200924860 hasConcept C2777530160 @default.
- W3200924860 hasConcept C38652104 @default.
- W3200924860 hasConcept C41008148 @default.
- W3200924860 hasConcept C76155785 @default.
- W3200924860 hasConceptScore W3200924860C115903868 @default.
- W3200924860 hasConceptScore W3200924860C126042441 @default.
- W3200924860 hasConceptScore W3200924860C135798126 @default.
- W3200924860 hasConceptScore W3200924860C154945302 @default.
- W3200924860 hasConceptScore W3200924860C165696696 @default.
- W3200924860 hasConceptScore W3200924860C184337299 @default.
- W3200924860 hasConceptScore W3200924860C199360897 @default.
- W3200924860 hasConceptScore W3200924860C2777530160 @default.
- W3200924860 hasConceptScore W3200924860C38652104 @default.
- W3200924860 hasConceptScore W3200924860C41008148 @default.
- W3200924860 hasConceptScore W3200924860C76155785 @default.
- W3200924860 hasLocation W32009248601 @default.
- W3200924860 hasLocation W32009248602 @default.
- W3200924860 hasOpenAccess W3200924860 @default.
- W3200924860 hasPrimaryLocation W32009248601 @default.
- W3200924860 hasRelatedWork W1596397513 @default.
- W3200924860 hasRelatedWork W1607315280 @default.
- W3200924860 hasRelatedWork W2035950535 @default.
- W3200924860 hasRelatedWork W2331043530 @default.
- W3200924860 hasRelatedWork W2351555819 @default.
- W3200924860 hasRelatedWork W2373012867 @default.
- W3200924860 hasRelatedWork W2374725260 @default.
- W3200924860 hasRelatedWork W2383403914 @default.
- W3200924860 hasRelatedWork W2393933887 @default.
- W3200924860 hasRelatedWork W2997512100 @default.
- W3200924860 isParatext "false" @default.
- W3200924860 isRetracted "false" @default.
- W3200924860 magId "3200924860" @default.
- W3200924860 workType "article" @default.