FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284696747> ?p ?o ?g. }

• W4284696747 endingPage "4706" @default.
• W4284696747 startingPage "4693" @default.
• W4284696747 abstract "The understanding of language plays a key role in video grounding, where a target moment is localized according to a text query. From a biological point of view, language is naturally hierarchical, with the main clause (predicate phrase) providing coarse semantics and modifiers providing detailed descriptions. In video grounding, moments described by the main clause may exist in multiple clips of a long video, including both the ground-truth and background clips. Therefore, in order to correctly discriminate the ground-truth clip from the background ones, this co-existence leads to the negligence of the main clause, and concentrate the model on the modifiers that provide discriminative information on distinguishing the target proposal from the others. We first demonstrate this phenomenon empirically, and propose a Hierarchical Language Network (HLN) that exploits the language hierarchy, as well as a new learning approach called Multi-Instance Positive-Unlabelled Learning (MI-PUL) to alleviate the above problem. Specifically, in HLN, the localization is performed on various layers of the language hierarchy, so that the attention can be paid to different parts of the sentences, rather than only discriminative ones. Furthermore, MI-PUL allows the model to localize background clips that can be possibly described by the main clause, even without manual annotations. Therefore, the union of the two proposed components enhances the learning of the main clause, which is of critical importance in video grounding. Finally, we evaluate that our proposed HLN can plug into the current methods and improve their performance. Extensive experiments on challenging datasets show HLN significantly improve the state-of-the-art methods, especially achieving 6.15% gain in terms of [Formula: see text] on the TACoS dataset." @default.
• W4284696747 created "2022-07-08" @default.
• W4284696747 creator A5020996610 @default.
• W4284696747 creator A5034814310 @default.
• W4284696747 creator A5042507268 @default.
• W4284696747 creator A5056569344 @default.
• W4284696747 creator A5065250332 @default.
• W4284696747 creator A5067652312 @default.
• W4284696747 creator A5075562531 @default.
• W4284696747 creator A5082388713 @default.
• W4284696747 date "2022-01-01" @default.
• W4284696747 modified "2023-10-18" @default.
• W4284696747 title "Exploring Language Hierarchy for Video Grounding" @default.
• W4284696747 cites W1522734439 @default.
• W4284696747 cites W1927052826 @default.
• W4284696747 cites W1936236220 @default.
• W4284696747 cites W2016053056 @default.
• W4284696747 cites W2064675550 @default.
• W4284696747 cites W2102245440 @default.
• W4284696747 cites W2107436459 @default.
• W4284696747 cites W2111078031 @default.
• W4284696747 cites W2125479168 @default.
• W4284696747 cites W2158379527 @default.
• W4284696747 cites W2167855619 @default.
• W4284696747 cites W2183341477 @default.
• W4284696747 cites W2250539671 @default.
• W4284696747 cites W2516035629 @default.
• W4284696747 cites W2565639579 @default.
• W4284696747 cites W2742033716 @default.
• W4284696747 cites W2798354744 @default.
• W4284696747 cites W2808647806 @default.
• W4284696747 cites W2884293275 @default.
• W4284696747 cites W2885775891 @default.
• W4284696747 cites W2890502146 @default.
• W4284696747 cites W2893119168 @default.
• W4284696747 cites W2894280539 @default.
• W4284696747 cites W2897628926 @default.
• W4284696747 cites W2904824998 @default.
• W4284696747 cites W2948958195 @default.
• W4284696747 cites W2951748488 @default.
• W4284696747 cites W2962709777 @default.
• W4284696747 cites W2962876901 @default.
• W4284696747 cites W2963017553 @default.
• W4284696747 cites W2963095467 @default.
• W4284696747 cites W2963393391 @default.
• W4284696747 cites W2963524571 @default.
• W4284696747 cites W2963662190 @default.
• W4284696747 cites W2963795951 @default.
• W4284696747 cites W2963916161 @default.
• W4284696747 cites W2964089981 @default.
• W4284696747 cites W2964214371 @default.
• W4284696747 cites W2964232540 @default.
• W4284696747 cites W2975813532 @default.
• W4284696747 cites W2984619425 @default.
• W4284696747 cites W2988098865 @default.
• W4284696747 cites W3005655588 @default.
• W4284696747 cites W3035232877 @default.
• W4284696747 cites W3035339529 @default.
• W4284696747 cites W3035635319 @default.
• W4284696747 cites W3035640828 @default.
• W4284696747 cites W3037109418 @default.
• W4284696747 cites W3092739351 @default.
• W4284696747 cites W3104893896 @default.
• W4284696747 cites W3130619535 @default.
• W4284696747 cites W3175082063 @default.
• W4284696747 cites W3175817778 @default.
• W4284696747 cites W3213436376 @default.
• W4284696747 cites W4214931087 @default.
• W4284696747 cites W76527192 @default.
• W4284696747 doi "https://doi.org/10.1109/tip.2022.3187288" @default.
• W4284696747 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35793294" @default.
• W4284696747 hasPublicationYear "2022" @default.
• W4284696747 type Work @default.
• W4284696747 citedByCount "4" @default.
• W4284696747 countsByYear W42846967472022 @default.
• W4284696747 countsByYear W42846967472023 @default.
• W4284696747 crossrefType "journal-article" @default.
• W4284696747 hasAuthorship W4284696747A5020996610 @default.
• W4284696747 hasAuthorship W4284696747A5034814310 @default.
• W4284696747 hasAuthorship W4284696747A5042507268 @default.
• W4284696747 hasAuthorship W4284696747A5056569344 @default.
• W4284696747 hasAuthorship W4284696747A5065250332 @default.
• W4284696747 hasAuthorship W4284696747A5067652312 @default.
• W4284696747 hasAuthorship W4284696747A5075562531 @default.
• W4284696747 hasAuthorship W4284696747A5082388713 @default.
• W4284696747 hasConcept C121332964 @default.
• W4284696747 hasConcept C137293760 @default.
• W4284696747 hasConcept C154945302 @default.
• W4284696747 hasConcept C162324750 @default.
• W4284696747 hasConcept C168993435 @default.
• W4284696747 hasConcept C184337299 @default.
• W4284696747 hasConcept C199360897 @default.
• W4284696747 hasConcept C204321447 @default.
• W4284696747 hasConcept C2776224158 @default.
• W4284696747 hasConcept C2778739407 @default.
• W4284696747 hasConcept C31170391 @default.
• W4284696747 hasConcept C34447519 @default.
• W4284696747 hasConcept C41008148 @default.

• next