# Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding

> Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2021) · cited 27× · AI/ML

**Wikidata**: [openalex:W3119746927](https://www.wikidata.org/wiki/openalex:W3119746927)  
**Source**: https://4ort.xyz/entity/efficient-object-level-visual-context-modeling-for-multimodal-machine-translation-masking-irrelevant-objects-helps-groun