Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284693480> ?p ?o ?g. }
- W4284693480 abstract "Moment retrieval in videos is a challenging task that aims to retrieve the most relevant video moment in an untrimmed video given a sentence description. Previous methods tend to perform self-modal learning and cross-modal interaction in a coarse manner, which neglect fine-grained clues contained in video content, query context, and their alignment. To this end, we propose a novel Multi-Granularity Perception Network (MGPN) that perceives intra-modality and inter-modality information at a multi-granularity level. Specifically, we formulate moment retrieval as a multi-choice reading comprehension task and integrate human reading strategies into our framework. A coarse-grained feature encoder and a co-attention mechanism are utilized to obtain a preliminary perception of intra-modality and inter-modality information. Then a fine-grained feature encoder and a conditioned interaction module are introduced to enhance the initial perception inspired by how humans address reading comprehension problems. Moreover, to alleviate the huge computation burden of some existing methods, we further design an efficient choice comparison module and reduce the hidden size with imperceptible quality loss. Extensive experiments on Charades-STA, TACoS, and ActivityNet Captions datasets demonstrate that our solution outperforms existing state-of-the-art methods." @default.
- W4284693480 created "2022-07-08" @default.
- W4284693480 creator A5001694472 @default.
- W4284693480 creator A5007348590 @default.
- W4284693480 creator A5012301761 @default.
- W4284693480 creator A5013385600 @default.
- W4284693480 creator A5076814111 @default.
- W4284693480 date "2022-07-06" @default.
- W4284693480 modified "2023-10-05" @default.
- W4284693480 title "You Need to Read Again" @default.
- W4284693480 cites W1522734439 @default.
- W4284693480 cites W2072222992 @default.
- W4284693480 cites W2111078031 @default.
- W4284693480 cites W2250539671 @default.
- W4284693480 cites W2606964149 @default.
- W4284693480 cites W2798354744 @default.
- W4284693480 cites W2885775891 @default.
- W4284693480 cites W2890502146 @default.
- W4284693480 cites W2894280539 @default.
- W4284693480 cites W2912904516 @default.
- W4284693480 cites W2948958195 @default.
- W4284693480 cites W2953874899 @default.
- W4284693480 cites W2962677524 @default.
- W4284693480 cites W2962869524 @default.
- W4284693480 cites W2963017553 @default.
- W4284693480 cites W2963091558 @default.
- W4284693480 cites W2963323070 @default.
- W4284693480 cites W2963393391 @default.
- W4284693480 cites W2963524571 @default.
- W4284693480 cites W2963748441 @default.
- W4284693480 cites W2963916161 @default.
- W4284693480 cites W2964089981 @default.
- W4284693480 cites W2964214371 @default.
- W4284693480 cites W2997429269 @default.
- W4284693480 cites W2998579922 @default.
- W4284693480 cites W2998582438 @default.
- W4284693480 cites W3025323587 @default.
- W4284693480 cites W3034743747 @default.
- W4284693480 cites W3035640828 @default.
- W4284693480 cites W3043840704 @default.
- W4284693480 cites W3088154886 @default.
- W4284693480 cites W3092739351 @default.
- W4284693480 cites W3093174808 @default.
- W4284693480 cites W3095206982 @default.
- W4284693480 cites W3171999262 @default.
- W4284693480 cites W3174364033 @default.
- W4284693480 cites W3176201273 @default.
- W4284693480 cites W3176763654 @default.
- W4284693480 cites W3202944637 @default.
- W4284693480 cites W3211953751 @default.
- W4284693480 doi "https://doi.org/10.1145/3477495.3532083" @default.
- W4284693480 hasPublicationYear "2022" @default.
- W4284693480 type Work @default.
- W4284693480 citedByCount "6" @default.
- W4284693480 countsByYear W42846934802023 @default.
- W4284693480 crossrefType "proceedings-article" @default.
- W4284693480 hasAuthorship W4284693480A5001694472 @default.
- W4284693480 hasAuthorship W4284693480A5007348590 @default.
- W4284693480 hasAuthorship W4284693480A5012301761 @default.
- W4284693480 hasAuthorship W4284693480A5013385600 @default.
- W4284693480 hasAuthorship W4284693480A5076814111 @default.
- W4284693480 hasBestOaLocation W42846934802 @default.
- W4284693480 hasConcept C111472728 @default.
- W4284693480 hasConcept C111919701 @default.
- W4284693480 hasConcept C118505674 @default.
- W4284693480 hasConcept C121332964 @default.
- W4284693480 hasConcept C138885662 @default.
- W4284693480 hasConcept C151730666 @default.
- W4284693480 hasConcept C154945302 @default.
- W4284693480 hasConcept C162324750 @default.
- W4284693480 hasConcept C169760540 @default.
- W4284693480 hasConcept C17744445 @default.
- W4284693480 hasConcept C177774035 @default.
- W4284693480 hasConcept C179254644 @default.
- W4284693480 hasConcept C187736073 @default.
- W4284693480 hasConcept C199360897 @default.
- W4284693480 hasConcept C199539241 @default.
- W4284693480 hasConcept C204321447 @default.
- W4284693480 hasConcept C26760741 @default.
- W4284693480 hasConcept C2776401178 @default.
- W4284693480 hasConcept C2777530160 @default.
- W4284693480 hasConcept C2778780117 @default.
- W4284693480 hasConcept C2779343474 @default.
- W4284693480 hasConcept C2779530757 @default.
- W4284693480 hasConcept C2780226545 @default.
- W4284693480 hasConcept C2780451532 @default.
- W4284693480 hasConcept C41008148 @default.
- W4284693480 hasConcept C41895202 @default.
- W4284693480 hasConcept C511192102 @default.
- W4284693480 hasConcept C554936623 @default.
- W4284693480 hasConcept C74650414 @default.
- W4284693480 hasConcept C86803240 @default.
- W4284693480 hasConceptScore W4284693480C111472728 @default.
- W4284693480 hasConceptScore W4284693480C111919701 @default.
- W4284693480 hasConceptScore W4284693480C118505674 @default.
- W4284693480 hasConceptScore W4284693480C121332964 @default.
- W4284693480 hasConceptScore W4284693480C138885662 @default.
- W4284693480 hasConceptScore W4284693480C151730666 @default.
- W4284693480 hasConceptScore W4284693480C154945302 @default.
- W4284693480 hasConceptScore W4284693480C162324750 @default.