AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

David Harwath, Adria Recasens, Didac Suris, Galen Chuang, Antonio Torralba, James Glass

ECCV 2018 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 177 citations (OpenAlex)

Read the paperCheck 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 max over image regions (MISA) instead of average (SISA) (ablation)matchmap speech model, random init · Places val 1k caption-to-imageR@10: .274 -> .314Improved
use MISA instead of SIMA (ablation)matchmap speech model, random init · Places val 1k caption-to-imageR@10: .284 -> .314Improved
use SIMA instead of MISA for image-to-caption (ablation)matchmap speech model, random init · Places val 1k image-to-captionR@1: .057 -> .065Mixed
pretrain image branch on ImageNet (ablation)MISA speech model · Places val 1k caption-to-imageR@10: .314 -> .604Improved
pretrain image branch on ImageNet (ablation)MISA speech model · Places val 1k image-to-captionR@10: .291 -> .528Improved
pretrain image branch on ImageNet (ablation)MISA speech model · ADE20k speech-prompted localizationIoU: .1795 -> .2324Improved
use MISA instead of average similarity for localization (ablation)speech model, random init · ADE20k speech-prompted localizationIoU: .1637 -> .1795Improved
use SIMA instead of MISA for localization (ablation)speech model, pretrained · ADE20k speech-prompted localizationIoU: .2324 -> .1857Hurt
replace ASR text input with raw speechMISA pretrained · Places val 1k caption-to-imageR@10: .701 -> .604Hurt
replace ASR text input with raw speechMISA pretrained · ADE20k speech-prompted localizationIoU: .2413 -> .2324Hurt

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