Matches in SemOpenAlex for { <https://semopenalex.org/work/W3145807616> ?p ?o ?g. }
- W3145807616 abstract "Video-Text Retrieval has been a hot research topic with the growth of multimedia data on the internet. Transformer for video-text learning has attracted increasing attention due to its promising performance. However, existing cross-modal transformer approaches typically suffer from two major limitations: 1) Exploitation of the transformer architecture where different layers have different feature characteristics is limited; 2) End-to-end training mechanism limits negative sample interactions in a mini-batch. In this paper, we propose a novel approach named Hierarchical Transformer (HiT) for video-text retrieval. HiT performs Hierarchical Cross-modal Contrastive Matching in both feature-level and semantic-level, achieving multi-view and comprehensive retrieval results. Moreover, inspired by MoCo, we propose Momentum Cross-modal Contrast for cross-modal learning to enable large-scale negative sample interactions on-the-fly, which contributes to the generation of more precise and discriminative representations. Experimental results on the three major Video-Text Retrieval benchmark datasets demonstrate the advantages of our method." @default.
- W3145807616 created "2021-04-13" @default.
- W3145807616 creator A5014295844 @default.
- W3145807616 creator A5022792966 @default.
- W3145807616 creator A5022926037 @default.
- W3145807616 creator A5029625647 @default.
- W3145807616 creator A5069622043 @default.
- W3145807616 creator A5073601707 @default.
- W3145807616 date "2021-10-01" @default.
- W3145807616 modified "2023-10-10" @default.
- W3145807616 title "HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval" @default.
- W3145807616 cites W1832693441 @default.
- W3145807616 cites W1957706851 @default.
- W3145807616 cites W1964073652 @default.
- W3145807616 cites W2078238240 @default.
- W3145807616 cites W2425121537 @default.
- W3145807616 cites W2526050071 @default.
- W3145807616 cites W2565656701 @default.
- W3145807616 cites W2765440071 @default.
- W3145807616 cites W2798991696 @default.
- W3145807616 cites W2808399042 @default.
- W3145807616 cites W2883429621 @default.
- W3145807616 cites W2885775891 @default.
- W3145807616 cites W2888329843 @default.
- W3145807616 cites W2897152025 @default.
- W3145807616 cites W2897439619 @default.
- W3145807616 cites W2946417913 @default.
- W3145807616 cites W2950784811 @default.
- W3145807616 cites W2956018683 @default.
- W3145807616 cites W2963420686 @default.
- W3145807616 cites W2963916161 @default.
- W3145807616 cites W2965848243 @default.
- W3145807616 cites W2970231061 @default.
- W3145807616 cites W2971033911 @default.
- W3145807616 cites W2975813532 @default.
- W3145807616 cites W2981586349 @default.
- W3145807616 cites W2981851019 @default.
- W3145807616 cites W2984008963 @default.
- W3145807616 cites W2987468995 @default.
- W3145807616 cites W2998356391 @default.
- W3145807616 cites W3034781633 @default.
- W3145807616 cites W3034882096 @default.
- W3145807616 cites W3035265375 @default.
- W3145807616 cites W3035356601 @default.
- W3145807616 cites W3035524453 @default.
- W3145807616 cites W3035747010 @default.
- W3145807616 cites W3156558703 @default.
- W3145807616 cites W3168640669 @default.
- W3145807616 doi "https://doi.org/10.1109/iccv48922.2021.01170" @default.
- W3145807616 hasPublicationYear "2021" @default.
- W3145807616 type Work @default.
- W3145807616 sameAs 3145807616 @default.
- W3145807616 citedByCount "57" @default.
- W3145807616 countsByYear W31458076162021 @default.
- W3145807616 countsByYear W31458076162022 @default.
- W3145807616 countsByYear W31458076162023 @default.
- W3145807616 crossrefType "proceedings-article" @default.
- W3145807616 hasAuthorship W3145807616A5014295844 @default.
- W3145807616 hasAuthorship W3145807616A5022792966 @default.
- W3145807616 hasAuthorship W3145807616A5022926037 @default.
- W3145807616 hasAuthorship W3145807616A5029625647 @default.
- W3145807616 hasAuthorship W3145807616A5069622043 @default.
- W3145807616 hasAuthorship W3145807616A5073601707 @default.
- W3145807616 hasBestOaLocation W31458076162 @default.
- W3145807616 hasConcept C119599485 @default.
- W3145807616 hasConcept C119857082 @default.
- W3145807616 hasConcept C127413603 @default.
- W3145807616 hasConcept C153180895 @default.
- W3145807616 hasConcept C154945302 @default.
- W3145807616 hasConcept C165801399 @default.
- W3145807616 hasConcept C185592680 @default.
- W3145807616 hasConcept C188027245 @default.
- W3145807616 hasConcept C23123220 @default.
- W3145807616 hasConcept C41008148 @default.
- W3145807616 hasConcept C52622490 @default.
- W3145807616 hasConcept C59404180 @default.
- W3145807616 hasConcept C66322947 @default.
- W3145807616 hasConcept C71139939 @default.
- W3145807616 hasConcept C97931131 @default.
- W3145807616 hasConceptScore W3145807616C119599485 @default.
- W3145807616 hasConceptScore W3145807616C119857082 @default.
- W3145807616 hasConceptScore W3145807616C127413603 @default.
- W3145807616 hasConceptScore W3145807616C153180895 @default.
- W3145807616 hasConceptScore W3145807616C154945302 @default.
- W3145807616 hasConceptScore W3145807616C165801399 @default.
- W3145807616 hasConceptScore W3145807616C185592680 @default.
- W3145807616 hasConceptScore W3145807616C188027245 @default.
- W3145807616 hasConceptScore W3145807616C23123220 @default.
- W3145807616 hasConceptScore W3145807616C41008148 @default.
- W3145807616 hasConceptScore W3145807616C52622490 @default.
- W3145807616 hasConceptScore W3145807616C59404180 @default.
- W3145807616 hasConceptScore W3145807616C66322947 @default.
- W3145807616 hasConceptScore W3145807616C71139939 @default.
- W3145807616 hasConceptScore W3145807616C97931131 @default.
- W3145807616 hasLocation W31458076161 @default.
- W3145807616 hasLocation W31458076162 @default.
- W3145807616 hasOpenAccess W3145807616 @default.
- W3145807616 hasPrimaryLocation W31458076161 @default.
- W3145807616 hasRelatedWork W2285052147 @default.
- W3145807616 hasRelatedWork W2404514746 @default.