FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3154682722> ?p ?o ?g. }

• W3154682722 abstract "Due to the popularity of video contents on the Internet, the information retrieval between videos and texts has attracted broad interest from researchers, which is a challenging cross-modal retrieval task. A common solution is to learn a joint embedding space to measure the cross-modal similarity. However, many existing approaches either pay more attention to textual information, video information, or cross-modal matching methods, but less to all three. We believe that a good video-text retrieval system should take into account all three points, fully exploiting the semantic information of both modalities and considering a comprehensive match. In this paper, we propose a Hierarchical Cross-Modal Graph Consistency Learning Network (HCGC) for video-text retrieval task, which considers multi-level graph consistency for video-text matching. Specifically, we first construct a hierarchical graph representation for the video, which includes three levels from global to local: video, clips and objects. Similarly, the corresponding text graph is constructed according to the semantic relationships among sentence, actions and entities. Then, in order to learn a better match between the video and text graph, we design three types of graph consistency (both direct and indirect): inter-graph parallel consistency, inter-graph cross consistency and intra-graph cross consistency. Extensive experimental results on different video-text datasets demonstrate the effectiveness of our approach on both text-to-video and video-to-text retrieval." @default.
• W3154682722 created "2021-04-26" @default.
• W3154682722 creator A5008666077 @default.
• W3154682722 creator A5048669373 @default.
• W3154682722 creator A5051494566 @default.
• W3154682722 creator A5065143660 @default.
• W3154682722 creator A5079260216 @default.
• W3154682722 creator A5083350101 @default.
• W3154682722 date "2021-07-11" @default.
• W3154682722 modified "2023-10-11" @default.
• W3154682722 title "Hierarchical Cross-Modal Graph Consistency Learning for Video-Text Retrieval" @default.
• W3154682722 cites W1573040851 @default.
• W3154682722 cites W1905882502 @default.
• W3154682722 cites W1964073652 @default.
• W3154682722 cites W1982795953 @default.
• W3154682722 cites W2070753207 @default.
• W3154682722 cites W2086842362 @default.
• W3154682722 cites W2127944900 @default.
• W3154682722 cites W2139009685 @default.
• W3154682722 cites W2139501017 @default.
• W3154682722 cites W2142900973 @default.
• W3154682722 cites W2157331557 @default.
• W3154682722 cites W2194775991 @default.
• W3154682722 cites W2250539671 @default.
• W3154682722 cites W2425121537 @default.
• W3154682722 cites W2616994964 @default.
• W3154682722 cites W2745461083 @default.
• W3154682722 cites W2808399042 @default.
• W3154682722 cites W2885775891 @default.
• W3154682722 cites W2956018683 @default.
• W3154682722 cites W2963293463 @default.
• W3154682722 cites W2963467339 @default.
• W3154682722 cites W2964187781 @default.
• W3154682722 cites W2975813532 @default.
• W3154682722 cites W3034882096 @default.
• W3154682722 cites W3035309251 @default.
• W3154682722 cites W3035356601 @default.
• W3154682722 cites W3035605030 @default.
• W3154682722 cites W3102887392 @default.
• W3154682722 cites W3201371131 @default.
• W3154682722 cites W4296262844 @default.
• W3154682722 cites W877909479 @default.
• W3154682722 doi "https://doi.org/10.1145/3404835.3462974" @default.
• W3154682722 hasPublicationYear "2021" @default.
• W3154682722 type Work @default.
• W3154682722 sameAs 3154682722 @default.
• W3154682722 citedByCount "18" @default.
• W3154682722 countsByYear W31546827222021 @default.
• W3154682722 countsByYear W31546827222022 @default.
• W3154682722 countsByYear W31546827222023 @default.
• W3154682722 crossrefType "proceedings-article" @default.
• W3154682722 hasAuthorship W3154682722A5008666077 @default.
• W3154682722 hasAuthorship W3154682722A5048669373 @default.
• W3154682722 hasAuthorship W3154682722A5051494566 @default.
• W3154682722 hasAuthorship W3154682722A5065143660 @default.
• W3154682722 hasAuthorship W3154682722A5079260216 @default.
• W3154682722 hasAuthorship W3154682722A5083350101 @default.
• W3154682722 hasConcept C105795698 @default.
• W3154682722 hasConcept C132525143 @default.
• W3154682722 hasConcept C154945302 @default.
• W3154682722 hasConcept C165064840 @default.
• W3154682722 hasConcept C185592680 @default.
• W3154682722 hasConcept C188027245 @default.
• W3154682722 hasConcept C23123220 @default.
• W3154682722 hasConcept C2776436953 @default.
• W3154682722 hasConcept C2778493491 @default.
• W3154682722 hasConcept C33923547 @default.
• W3154682722 hasConcept C41008148 @default.
• W3154682722 hasConcept C71139939 @default.
• W3154682722 hasConcept C80444323 @default.
• W3154682722 hasConceptScore W3154682722C105795698 @default.
• W3154682722 hasConceptScore W3154682722C132525143 @default.
• W3154682722 hasConceptScore W3154682722C154945302 @default.
• W3154682722 hasConceptScore W3154682722C165064840 @default.
• W3154682722 hasConceptScore W3154682722C185592680 @default.
• W3154682722 hasConceptScore W3154682722C188027245 @default.
• W3154682722 hasConceptScore W3154682722C23123220 @default.
• W3154682722 hasConceptScore W3154682722C2776436953 @default.
• W3154682722 hasConceptScore W3154682722C2778493491 @default.
• W3154682722 hasConceptScore W3154682722C33923547 @default.
• W3154682722 hasConceptScore W3154682722C41008148 @default.
• W3154682722 hasConceptScore W3154682722C71139939 @default.
• W3154682722 hasConceptScore W3154682722C80444323 @default.
• W3154682722 hasFunder F4320321001 @default.
• W3154682722 hasLocation W31546827221 @default.
• W3154682722 hasOpenAccess W3154682722 @default.
• W3154682722 hasPrimaryLocation W31546827221 @default.
• W3154682722 hasRelatedWork W1621183734 @default.
• W3154682722 hasRelatedWork W2086064646 @default.
• W3154682722 hasRelatedWork W2115485936 @default.
• W3154682722 hasRelatedWork W2119135658 @default.
• W3154682722 hasRelatedWork W2349174110 @default.
• W3154682722 hasRelatedWork W2353865532 @default.
• W3154682722 hasRelatedWork W2357241418 @default.
• W3154682722 hasRelatedWork W2380556669 @default.
• W3154682722 hasRelatedWork W3022131925 @default.
• W3154682722 hasRelatedWork W64465677 @default.
• W3154682722 isParatext "false" @default.
• W3154682722 isRetracted "false" @default.
• W3154682722 magId "3154682722" @default.

• next