Coarse-to-Fine Semantic Alignment for Cross-Modal Moment Localization

Video moment localization, as an important branch of video content analysis, has attracted extensive attention in recent years. However, it is still in its infancy due to the following challenges: cross-modal semantic alignment and localization efficiency. To address these impediments, we present a...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 24., Seite 5933-5943
1. Verfasser: Hu, Yupeng (VerfasserIn)
Weitere Verfasser: Nie, Liqiang, Liu, Meng, Wang, Kun, Wang, Yinglong, Hua, Xian-Sheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM32713402X
003 DE-627
005 20231225200113.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2021.3090521  |2 doi 
028 5 2 |a pubmed24n1090.xml 
035 |a (DE-627)NLM32713402X 
035 |a (NLM)34166192 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Hu, Yupeng  |e verfasserin  |4 aut 
245 1 0 |a Coarse-to-Fine Semantic Alignment for Cross-Modal Moment Localization 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 30.06.2021 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Video moment localization, as an important branch of video content analysis, has attracted extensive attention in recent years. However, it is still in its infancy due to the following challenges: cross-modal semantic alignment and localization efficiency. To address these impediments, we present a cross-modal semantic alignment network. To be specific, we first design a video encoder to generate moment candidates, learn their representations, as well as model their semantic relevance. Meanwhile, we design a query encoder for diverse query intention understanding. Thereafter, we introduce a multi-granularity interaction module to deeply explore the semantic correlation between multi-modalities. Thereby, we can effectively complete target moment localization via sufficient cross-modal semantic understanding. Moreover, we introduce a semantic pruning strategy to reduce cross-modal retrieval overhead, improving localization efficiency. Experimental results on two benchmark datasets have justified the superiority of our model over several state-of-the-art competitors 
650 4 |a Journal Article 
700 1 |a Nie, Liqiang  |e verfasserin  |4 aut 
700 1 |a Liu, Meng  |e verfasserin  |4 aut 
700 1 |a Wang, Kun  |e verfasserin  |4 aut 
700 1 |a Wang, Yinglong  |e verfasserin  |4 aut 
700 1 |a Hua, Xian-Sheng  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 30(2021) vom: 24., Seite 5933-5943  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:30  |g year:2021  |g day:24  |g pages:5933-5943 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2021.3090521  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 30  |j 2021  |b 24  |h 5933-5943