Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385482837> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4385482837 abstract "An image usually contains not only visual information but also higher-level semantic information. Nevertheless, previous computer vision algorithms, such as target detection and image classification, use only the visual features of the image alone. Recently, the explosion of scene graphs in computer vision has led to the challenge of generating structured scene graphs with rich semantic information. This paper proposes a one-stage query-based end-to-end Transformer model and generates scene graphs using the Hungarian matching algorithm. We develop an anti-bias reasoner module to reduce the impact of the unbalanced data distribution. Time-division training strategy is proposed to improve model training efficiency and speed up model convergence while improving model training performance. Experiments on the large-scale dataset Visual Genome were conducted in order to confirm the validity of our method. Compared with the existing state-of-the-art method, our method guarantees inference speed while maintaining acceptable performance and is more suitable for tasks with high real-time performance. Our work demonstrates that the one-stage method has great potential for exploration in scene graph generation." @default.
- W4385482837 created "2023-08-03" @default.
- W4385482837 creator A5003841328 @default.
- W4385482837 creator A5057209439 @default.
- W4385482837 creator A5058072839 @default.
- W4385482837 creator A5059492103 @default.
- W4385482837 creator A5088018089 @default.
- W4385482837 date "2023-06-18" @default.
- W4385482837 modified "2023-09-26" @default.
- W4385482837 title "A Novel End-to-End Transformer for Scene Graph Generation" @default.
- W4385482837 cites W1689711448 @default.
- W4385482837 cites W2077069816 @default.
- W4385482837 cites W2194775991 @default.
- W4385482837 cites W2277195237 @default.
- W4385482837 cites W2579549467 @default.
- W4385482837 cites W2962716332 @default.
- W4385482837 cites W2962779575 @default.
- W4385482837 cites W2962785943 @default.
- W4385482837 cites W2963514444 @default.
- W4385482837 cites W2963536419 @default.
- W4385482837 cites W2963649796 @default.
- W4385482837 cites W2987919422 @default.
- W4385482837 cites W2992195701 @default.
- W4385482837 cites W2992478697 @default.
- W4385482837 cites W3035017890 @default.
- W4385482837 cites W3173181410 @default.
- W4385482837 cites W3181556077 @default.
- W4385482837 cites W4214617019 @default.
- W4385482837 cites W4214693531 @default.
- W4385482837 cites W4312563197 @default.
- W4385482837 cites W607748843 @default.
- W4385482837 doi "https://doi.org/10.1109/ijcnn54540.2023.10191798" @default.
- W4385482837 hasPublicationYear "2023" @default.
- W4385482837 type Work @default.
- W4385482837 citedByCount "0" @default.
- W4385482837 crossrefType "proceedings-article" @default.
- W4385482837 hasAuthorship W4385482837A5003841328 @default.
- W4385482837 hasAuthorship W4385482837A5057209439 @default.
- W4385482837 hasAuthorship W4385482837A5058072839 @default.
- W4385482837 hasAuthorship W4385482837A5059492103 @default.
- W4385482837 hasAuthorship W4385482837A5088018089 @default.
- W4385482837 hasConcept C119857082 @default.
- W4385482837 hasConcept C121332964 @default.
- W4385482837 hasConcept C132525143 @default.
- W4385482837 hasConcept C154945302 @default.
- W4385482837 hasConcept C165801399 @default.
- W4385482837 hasConcept C179372163 @default.
- W4385482837 hasConcept C205711294 @default.
- W4385482837 hasConcept C2776214188 @default.
- W4385482837 hasConcept C2779201187 @default.
- W4385482837 hasConcept C31258907 @default.
- W4385482837 hasConcept C31972630 @default.
- W4385482837 hasConcept C41008148 @default.
- W4385482837 hasConcept C62520636 @default.
- W4385482837 hasConcept C66322947 @default.
- W4385482837 hasConcept C74296488 @default.
- W4385482837 hasConcept C80444323 @default.
- W4385482837 hasConcept C9616225 @default.
- W4385482837 hasConceptScore W4385482837C119857082 @default.
- W4385482837 hasConceptScore W4385482837C121332964 @default.
- W4385482837 hasConceptScore W4385482837C132525143 @default.
- W4385482837 hasConceptScore W4385482837C154945302 @default.
- W4385482837 hasConceptScore W4385482837C165801399 @default.
- W4385482837 hasConceptScore W4385482837C179372163 @default.
- W4385482837 hasConceptScore W4385482837C205711294 @default.
- W4385482837 hasConceptScore W4385482837C2776214188 @default.
- W4385482837 hasConceptScore W4385482837C2779201187 @default.
- W4385482837 hasConceptScore W4385482837C31258907 @default.
- W4385482837 hasConceptScore W4385482837C31972630 @default.
- W4385482837 hasConceptScore W4385482837C41008148 @default.
- W4385482837 hasConceptScore W4385482837C62520636 @default.
- W4385482837 hasConceptScore W4385482837C66322947 @default.
- W4385482837 hasConceptScore W4385482837C74296488 @default.
- W4385482837 hasConceptScore W4385482837C80444323 @default.
- W4385482837 hasConceptScore W4385482837C9616225 @default.
- W4385482837 hasLocation W43854828371 @default.
- W4385482837 hasOpenAccess W4385482837 @default.
- W4385482837 hasPrimaryLocation W43854828371 @default.
- W4385482837 hasRelatedWork W1891287906 @default.
- W4385482837 hasRelatedWork W2355108509 @default.
- W4385482837 hasRelatedWork W2961085424 @default.
- W4385482837 hasRelatedWork W2982696980 @default.
- W4385482837 hasRelatedWork W3015286511 @default.
- W4385482837 hasRelatedWork W3084370450 @default.
- W4385482837 hasRelatedWork W4200202829 @default.
- W4385482837 hasRelatedWork W4288087689 @default.
- W4385482837 hasRelatedWork W4306674287 @default.
- W4385482837 hasRelatedWork W4385482837 @default.
- W4385482837 isParatext "false" @default.
- W4385482837 isRetracted "false" @default.
- W4385482837 workType "article" @default.