AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Visual Grounding in Video for Unsupervised Word Translation

Gunnar A. Sigurdsson, Jean-Baptiste Alayrac, Aida Nematzadeh, Lucas Smaira, Mateusz Malinowski, Joao Carreira, Phil Blunsom, Andrew Zisserman

CVPR 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 7 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use MUVE instead of VecMap for unsupervised word mappingEnglish-French word translation · English-French Dictionary, AllRecall@1: 28.4 -> 28.9Improved
Use MUVE instead of VecMap for unsupervised word mappingEnglish-Korean word translation · English-Korean DictionaryRecall@1: 13.0 -> 17.7Improved
Use MUVE instead of VecMap for unsupervised word mappingEnglish-Japanese word translation · English-Japanese DictionaryRecall@1: 13.7 -> 15.1Improved
Use the shared visual-grounding Base Model instead of video retrieval to create word mappingsEnglish-French word translation · English-French Dictionary, AllRecall@1: 6.3 -> 9.1Improved
Use the shared visual-grounding Base Model instead of video retrieval to create word mappingsEnglish-French word translation · English-French Simple Words, AllRecall@1: 12.5 -> 28.0Improved
Add the MUVE visual initialization to text-based word mappingEnglish-French Dictionary, All · English-French DictionaryRecall@1: 28.4 -> 28.9Improved
Add the MUVE visual initialization to text-based word mappingEnglish-French Simple Words, All · English-French Simple WordsRecall@1: 28.0 -> 58.3Improved
Add the MUVE visual initialization to text-based word mappingEnglish-French Simple Words, Visual · English-French Simple Words, VisualRecall@1: 45.3 -> 67.5Improved
Add the orthogonal constraint to the AdaptLayer (ablation)MUVE · English-French DictionaryRecall@1: 16.6 -> 28.9Improved
Use visual grounding instead of text-only alignment when English and French training corpora differMUVE versus text-based methods · English-French Dictionary, Wiki-En and HowToW-FrRecall@10: 32.6; text-based methods less than 0.5Improved
Reduce the amount of French training dataMUVE versus MUSE and VecMap · English-French Dictionary, reduced training dataRecall@10Improved
Reduce the French vocabulary sizeMUVE versus MUSE and VecMap · English-French Dictionary, reduced vocabularyRecall@10Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy