AI Paper Atlas

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

Placing Objects in Gesture Space: Toward Incremental Interpretation of Multimodal Spatial Descriptions

Ting Han, Casey Kennington, David Schlangen

AAAI 2018 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 6 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
Replace rule-based utterance segmenter with LSTMutterance segmenter · Utterance segmentationaccuracy: 0.85 -> 0.92Improved
Replace rule-based utterance segmenter with LSTMutterance segmenter · Utterance segmentationF1: 0.84 -> 0.89Improved
Replace rule-based utterance segmenter with LSTMutterance segmenter · Utterance segmentationstd of accuracy across participants: 0.23 -> 0.10Improved
Use Gaussian KDE gesture interpretation instead of chancegesture interpretation · Object referenceaccuracy: 1/3 -> 0.81Improved
Use full system with speech only instead of random baselineOur System · Scene retrievalaccuracy: 0.17 -> 0.75Improved
Use gesture only (language weight 0) instead of random baselineOur System · Scene retrievalaccuracy: 0.17 -> 0.50Improved
Add gestures to speech in fusionOur System · Scene retrievalaccuracy: 0.75 -> 0.84Improved
Add gestures to speech in fusionOur System · Scene retrievalMRR: 0.79 -> 0.84Improved
Add gestures to speech for human crowd workershuman evaluation · Scene retrievalaccuracy: 0.86 -> 0.77Hurt
Add gestures to speech in incremental decisionOur System · Incremental evalaverage fc: 0.24 -> 0.24No clear effect
Add gestures to speech in incremental decisionOur System · Incremental evalaverage ff: 0.67 -> 0.65Improved
Add gestures to speech in incremental decisionOur System · Incremental evalaverage eo (edit overhead)Hurt

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