Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380994095> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4380994095 abstract "Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction. However, the task lacks annotated multimodal training data and artificially generated training data suffer from distribution shift from real-world data. In this paper, we propose Cross-modality Augmented Multimedia Event Learning (CAMEL), which successfully utilizes artificially generated multimodal training data and achieves state-of-the-art performance. We start with two labeled unimodal datasets in text and image respectively, and generate the missing modality using off-the-shelf image generators like Stable Diffusion and image captioners like BLIP. After that, we train the network on the resultant multimodal datasets. In order to learn robust features that are effective across domains, we devise an iterative and gradual training strategy. Substantial experiments show that CAMEL surpasses state-of-the-art (SOTA) baselines on the M2E2 benchmark. On multimedia events in particular, we outperform the prior SOTA by 4.2% F1 on event mention identification and by 9.8% F1 on argument identification, which indicates that CAMEL learns synergistic representations from the two modalities. Our work demonstrates a recipe to unleash the power of synthetic training data in structured prediction." @default.
- W4380994095 created "2023-06-17" @default.
- W4380994095 creator A5015215095 @default.
- W4380994095 creator A5019703861 @default.
- W4380994095 creator A5031458824 @default.
- W4380994095 creator A5049430074 @default.
- W4380994095 creator A5065154024 @default.
- W4380994095 date "2023-06-15" @default.
- W4380994095 modified "2023-09-25" @default.
- W4380994095 title "Training Multimedia Event Extraction With Generated Images and Captions" @default.
- W4380994095 doi "https://doi.org/10.48550/arxiv.2306.08966" @default.
- W4380994095 hasPublicationYear "2023" @default.
- W4380994095 type Work @default.
- W4380994095 citedByCount "0" @default.
- W4380994095 crossrefType "posted-content" @default.
- W4380994095 hasAuthorship W4380994095A5015215095 @default.
- W4380994095 hasAuthorship W4380994095A5019703861 @default.
- W4380994095 hasAuthorship W4380994095A5031458824 @default.
- W4380994095 hasAuthorship W4380994095A5049430074 @default.
- W4380994095 hasAuthorship W4380994095A5065154024 @default.
- W4380994095 hasBestOaLocation W43809940951 @default.
- W4380994095 hasConcept C108583219 @default.
- W4380994095 hasConcept C116834253 @default.
- W4380994095 hasConcept C119857082 @default.
- W4380994095 hasConcept C121332964 @default.
- W4380994095 hasConcept C13280743 @default.
- W4380994095 hasConcept C144024400 @default.
- W4380994095 hasConcept C154945302 @default.
- W4380994095 hasConcept C160920958 @default.
- W4380994095 hasConcept C162324750 @default.
- W4380994095 hasConcept C185798385 @default.
- W4380994095 hasConcept C187736073 @default.
- W4380994095 hasConcept C205649164 @default.
- W4380994095 hasConcept C2779662365 @default.
- W4380994095 hasConcept C2779903281 @default.
- W4380994095 hasConcept C2780226545 @default.
- W4380994095 hasConcept C2780451532 @default.
- W4380994095 hasConcept C36289849 @default.
- W4380994095 hasConcept C41008148 @default.
- W4380994095 hasConcept C49774154 @default.
- W4380994095 hasConcept C59822182 @default.
- W4380994095 hasConcept C62520636 @default.
- W4380994095 hasConcept C86803240 @default.
- W4380994095 hasConceptScore W4380994095C108583219 @default.
- W4380994095 hasConceptScore W4380994095C116834253 @default.
- W4380994095 hasConceptScore W4380994095C119857082 @default.
- W4380994095 hasConceptScore W4380994095C121332964 @default.
- W4380994095 hasConceptScore W4380994095C13280743 @default.
- W4380994095 hasConceptScore W4380994095C144024400 @default.
- W4380994095 hasConceptScore W4380994095C154945302 @default.
- W4380994095 hasConceptScore W4380994095C160920958 @default.
- W4380994095 hasConceptScore W4380994095C162324750 @default.
- W4380994095 hasConceptScore W4380994095C185798385 @default.
- W4380994095 hasConceptScore W4380994095C187736073 @default.
- W4380994095 hasConceptScore W4380994095C205649164 @default.
- W4380994095 hasConceptScore W4380994095C2779662365 @default.
- W4380994095 hasConceptScore W4380994095C2779903281 @default.
- W4380994095 hasConceptScore W4380994095C2780226545 @default.
- W4380994095 hasConceptScore W4380994095C2780451532 @default.
- W4380994095 hasConceptScore W4380994095C36289849 @default.
- W4380994095 hasConceptScore W4380994095C41008148 @default.
- W4380994095 hasConceptScore W4380994095C49774154 @default.
- W4380994095 hasConceptScore W4380994095C59822182 @default.
- W4380994095 hasConceptScore W4380994095C62520636 @default.
- W4380994095 hasConceptScore W4380994095C86803240 @default.
- W4380994095 hasLocation W43809940951 @default.
- W4380994095 hasLocation W43809940952 @default.
- W4380994095 hasOpenAccess W4380994095 @default.
- W4380994095 hasPrimaryLocation W43809940951 @default.
- W4380994095 hasRelatedWork W2012466265 @default.
- W4380994095 hasRelatedWork W2613123485 @default.
- W4380994095 hasRelatedWork W3176765321 @default.
- W4380994095 hasRelatedWork W4205137593 @default.
- W4380994095 hasRelatedWork W4223943233 @default.
- W4380994095 hasRelatedWork W4236838349 @default.
- W4380994095 hasRelatedWork W4312200629 @default.
- W4380994095 hasRelatedWork W4360585206 @default.
- W4380994095 hasRelatedWork W4364306694 @default.
- W4380994095 hasRelatedWork W4380075502 @default.
- W4380994095 isParatext "false" @default.
- W4380994095 isRetracted "false" @default.
- W4380994095 workType "article" @default.