SOTAVerified

Multimodal Machine Translation

Multimodal machine translation is the task of doing machine translation with multiple data sources - for example, translating "a bird is flying over water" + an image of a bird over water to German text.

( Image credit: Findings of the Third Shared Task on Multimodal Machine Translation )

Papers

Showing 2130 of 108 papers

TitleStatusHype
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationCode1
Iterative Adversarial Attack on Image-guided Story Ending Generation0
Generalization algorithm of multimodal pre-training model based on graph-text self-supervised training0
Beyond Triplet: Leveraging the Most Data for Multimodal Machine TranslationCode0
Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive EvaluationCode1
ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation0
LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation0
Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective0
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine TranslationCode1
VALHALLA: Visual Hallucination for Machine TranslationCode1
Show:102550
← PrevPage 3 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1delMeteor (EN-FR)74.6Unverified
2ERNIE-UniX2BLEU (EN-DE)49.3Unverified
3IKD-MMTBLEU (EN-DE)41.28Unverified
4DCCNBLEU (EN-DE)39.7Unverified
5CaglayanBLEU (EN-DE)39.4Unverified
6Gumbel-Attention MMTBLEU (EN-DE)39.2Unverified
7Multimodal TransformerBLEU (EN-DE)38.7Unverified
8ImagiTBLEU (EN-DE)38.4Unverified
9del+objBLEU (EN-DE)38Unverified
10VMMTFBLEU (EN-DE)37.6Unverified
#ModelMetricClaimedVerifiedStatus
1ViTABLEU (EN-HI)51.6Unverified
#ModelMetricClaimedVerifiedStatus
1ViTABLEU (EN-HI)44.6Unverified