Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360890450> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4360890450 abstract "Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution issues that tail-predicates are more costly to train and hard to distinguish due to a small amount of annotated data compared to frequent predicates. Existing re-balancing strategies try to handle it via prior rules but are still confined to pre-defined conditions, which are not scalable for various models and datasets. In this paper, we propose a Cross-modal prediCate boosting (CaCao) framework, where a visually-prompted language model is learned to generate diverse fine-grained predicates in a low-resource way. The proposed CaCao can be applied in a plug-and-play fashion and automatically strengthen existing SGG to tackle the long-tailed problem. Based on that, we further introduce a novel Entangled cross-modal prompt approach for open-world predicate scene graph generation (Epic), where models can generalize to unseen predicates in a zero-shot manner. Comprehensive experiments on three benchmark datasets show that CaCao consistently boosts the performance of multiple scene graph generation models in a model-agnostic way. Moreover, our Epic achieves competitive performance on open-world predicate prediction. The data and code for this paper are publicly available." @default.
- W4360890450 created "2023-03-25" @default.
- W4360890450 creator A5003866126 @default.
- W4360890450 creator A5008666077 @default.
- W4360890450 creator A5023991621 @default.
- W4360890450 creator A5032248858 @default.
- W4360890450 creator A5063062444 @default.
- W4360890450 creator A5067078797 @default.
- W4360890450 date "2023-03-23" @default.
- W4360890450 modified "2023-09-25" @default.
- W4360890450 title "Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World" @default.
- W4360890450 doi "https://doi.org/10.48550/arxiv.2303.13233" @default.
- W4360890450 hasPublicationYear "2023" @default.
- W4360890450 type Work @default.
- W4360890450 citedByCount "0" @default.
- W4360890450 crossrefType "posted-content" @default.
- W4360890450 hasAuthorship W4360890450A5003866126 @default.
- W4360890450 hasAuthorship W4360890450A5008666077 @default.
- W4360890450 hasAuthorship W4360890450A5023991621 @default.
- W4360890450 hasAuthorship W4360890450A5032248858 @default.
- W4360890450 hasAuthorship W4360890450A5063062444 @default.
- W4360890450 hasAuthorship W4360890450A5067078797 @default.
- W4360890450 hasBestOaLocation W43608904501 @default.
- W4360890450 hasConcept C115519274 @default.
- W4360890450 hasConcept C124952713 @default.
- W4360890450 hasConcept C132525143 @default.
- W4360890450 hasConcept C140146324 @default.
- W4360890450 hasConcept C142362112 @default.
- W4360890450 hasConcept C154945302 @default.
- W4360890450 hasConcept C179372163 @default.
- W4360890450 hasConcept C185592680 @default.
- W4360890450 hasConcept C188027245 @default.
- W4360890450 hasConcept C199360897 @default.
- W4360890450 hasConcept C205711294 @default.
- W4360890450 hasConcept C41008148 @default.
- W4360890450 hasConcept C48044578 @default.
- W4360890450 hasConcept C71139939 @default.
- W4360890450 hasConcept C77088390 @default.
- W4360890450 hasConcept C80444323 @default.
- W4360890450 hasConceptScore W4360890450C115519274 @default.
- W4360890450 hasConceptScore W4360890450C124952713 @default.
- W4360890450 hasConceptScore W4360890450C132525143 @default.
- W4360890450 hasConceptScore W4360890450C140146324 @default.
- W4360890450 hasConceptScore W4360890450C142362112 @default.
- W4360890450 hasConceptScore W4360890450C154945302 @default.
- W4360890450 hasConceptScore W4360890450C179372163 @default.
- W4360890450 hasConceptScore W4360890450C185592680 @default.
- W4360890450 hasConceptScore W4360890450C188027245 @default.
- W4360890450 hasConceptScore W4360890450C199360897 @default.
- W4360890450 hasConceptScore W4360890450C205711294 @default.
- W4360890450 hasConceptScore W4360890450C41008148 @default.
- W4360890450 hasConceptScore W4360890450C48044578 @default.
- W4360890450 hasConceptScore W4360890450C71139939 @default.
- W4360890450 hasConceptScore W4360890450C77088390 @default.
- W4360890450 hasConceptScore W4360890450C80444323 @default.
- W4360890450 hasLocation W43608904501 @default.
- W4360890450 hasOpenAccess W4360890450 @default.
- W4360890450 hasPrimaryLocation W43608904501 @default.
- W4360890450 hasRelatedWork W1525643724 @default.
- W4360890450 hasRelatedWork W2067938758 @default.
- W4360890450 hasRelatedWork W2333420780 @default.
- W4360890450 hasRelatedWork W2364921833 @default.
- W4360890450 hasRelatedWork W2368437561 @default.
- W4360890450 hasRelatedWork W2375199418 @default.
- W4360890450 hasRelatedWork W2382623646 @default.
- W4360890450 hasRelatedWork W2953365189 @default.
- W4360890450 hasRelatedWork W2989786123 @default.
- W4360890450 hasRelatedWork W3087771547 @default.
- W4360890450 isParatext "false" @default.
- W4360890450 isRetracted "false" @default.
- W4360890450 workType "article" @default.