Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319300466> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4319300466 abstract "An audio-visual event (AVE) is denoted by the correspondence of the visual and auditory signals in a video segment. Precise localization of the AVEs is very challenging since it demands effective multi-modal feature correspondence to ground the short and long range temporal interactions. Existing approaches struggle in capturing the different scales of multi-modal interaction due to ineffective multi-modal training strategies. To overcome this limitation, we introduce AVE-CLIP, a novel framework that integrates the AudioCLIP pre-trained on large-scale audio-visual data with a multi-window temporal transformer to effectively operate on different temporal scales of video frames. Our contributions are three-fold: (1) We introduce a multi-stage training framework to incorporate AudioCLIP pre-trained with audio-image pairs into the AVE localization task on video frames through contrastive fine-tuning, effective mean video feature extraction, and multi-scale training phases. (2) We propose a multi-domain attention mechanism that operates on both temporal and feature domains over varying timescales to fuse the local and global feature variations. (3) We introduce a temporal refining scheme with event-guided attention followed by a simple-yet-effective post processing step to handle significant variations of the background over diverse events. Our method achieves state-of-the-art performance on the publicly available AVE dataset with 5.9% mean accuracy improvement which proves its superiority over existing approaches." @default.
- W4319300466 created "2023-02-07" @default.
- W4319300466 creator A5014251585 @default.
- W4319300466 creator A5065985595 @default.
- W4319300466 date "2023-01-01" @default.
- W4319300466 modified "2023-09-30" @default.
- W4319300466 title "AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization" @default.
- W4319300466 cites W2108598243 @default.
- W4319300466 cites W2526050071 @default.
- W4319300466 cites W2796238456 @default.
- W4319300466 cites W2953127211 @default.
- W4319300466 cites W2964198573 @default.
- W4319300466 cites W2977259558 @default.
- W4319300466 cites W2990113535 @default.
- W4319300466 cites W2997909293 @default.
- W4319300466 cites W3015925607 @default.
- W4319300466 cites W3089887959 @default.
- W4319300466 cites W3093287838 @default.
- W4319300466 cites W3118366136 @default.
- W4319300466 cites W3161253965 @default.
- W4319300466 cites W3175630806 @default.
- W4319300466 cites W3176445421 @default.
- W4319300466 cites W3198371949 @default.
- W4319300466 cites W3201065055 @default.
- W4319300466 cites W3201927751 @default.
- W4319300466 cites W4212847156 @default.
- W4319300466 cites W4312818263 @default.
- W4319300466 cites W4312971576 @default.
- W4319300466 doi "https://doi.org/10.1109/wacv56688.2023.00513" @default.
- W4319300466 hasPublicationYear "2023" @default.
- W4319300466 type Work @default.
- W4319300466 citedByCount "1" @default.
- W4319300466 countsByYear W43193004662023 @default.
- W4319300466 crossrefType "proceedings-article" @default.
- W4319300466 hasAuthorship W4319300466A5014251585 @default.
- W4319300466 hasAuthorship W4319300466A5065985595 @default.
- W4319300466 hasBestOaLocation W43193004662 @default.
- W4319300466 hasConcept C119599485 @default.
- W4319300466 hasConcept C121332964 @default.
- W4319300466 hasConcept C127413603 @default.
- W4319300466 hasConcept C138885662 @default.
- W4319300466 hasConcept C153180895 @default.
- W4319300466 hasConcept C154945302 @default.
- W4319300466 hasConcept C165801399 @default.
- W4319300466 hasConcept C185592680 @default.
- W4319300466 hasConcept C188027245 @default.
- W4319300466 hasConcept C2776401178 @default.
- W4319300466 hasConcept C2779662365 @default.
- W4319300466 hasConcept C28490314 @default.
- W4319300466 hasConcept C31972630 @default.
- W4319300466 hasConcept C36464697 @default.
- W4319300466 hasConcept C41008148 @default.
- W4319300466 hasConcept C41895202 @default.
- W4319300466 hasConcept C52622490 @default.
- W4319300466 hasConcept C62520636 @default.
- W4319300466 hasConcept C66322947 @default.
- W4319300466 hasConcept C71139939 @default.
- W4319300466 hasConceptScore W4319300466C119599485 @default.
- W4319300466 hasConceptScore W4319300466C121332964 @default.
- W4319300466 hasConceptScore W4319300466C127413603 @default.
- W4319300466 hasConceptScore W4319300466C138885662 @default.
- W4319300466 hasConceptScore W4319300466C153180895 @default.
- W4319300466 hasConceptScore W4319300466C154945302 @default.
- W4319300466 hasConceptScore W4319300466C165801399 @default.
- W4319300466 hasConceptScore W4319300466C185592680 @default.
- W4319300466 hasConceptScore W4319300466C188027245 @default.
- W4319300466 hasConceptScore W4319300466C2776401178 @default.
- W4319300466 hasConceptScore W4319300466C2779662365 @default.
- W4319300466 hasConceptScore W4319300466C28490314 @default.
- W4319300466 hasConceptScore W4319300466C31972630 @default.
- W4319300466 hasConceptScore W4319300466C36464697 @default.
- W4319300466 hasConceptScore W4319300466C41008148 @default.
- W4319300466 hasConceptScore W4319300466C41895202 @default.
- W4319300466 hasConceptScore W4319300466C52622490 @default.
- W4319300466 hasConceptScore W4319300466C62520636 @default.
- W4319300466 hasConceptScore W4319300466C66322947 @default.
- W4319300466 hasConceptScore W4319300466C71139939 @default.
- W4319300466 hasFunder F4320337345 @default.
- W4319300466 hasLocation W43193004661 @default.
- W4319300466 hasLocation W43193004662 @default.
- W4319300466 hasOpenAccess W4319300466 @default.
- W4319300466 hasPrimaryLocation W43193004661 @default.
- W4319300466 hasRelatedWork W1504288058 @default.
- W4319300466 hasRelatedWork W2017205855 @default.
- W4319300466 hasRelatedWork W2048505601 @default.
- W4319300466 hasRelatedWork W2146076056 @default.
- W4319300466 hasRelatedWork W2167293474 @default.
- W4319300466 hasRelatedWork W2331674254 @default.
- W4319300466 hasRelatedWork W2546942002 @default.
- W4319300466 hasRelatedWork W2811390910 @default.
- W4319300466 hasRelatedWork W2979079341 @default.
- W4319300466 hasRelatedWork W3042897387 @default.
- W4319300466 isParatext "false" @default.
- W4319300466 isRetracted "false" @default.
- W4319300466 workType "article" @default.