AI Paper Atlas

Research map / Video / Video-language understanding

Understanding Co-speech Gestures in-the-wild

Sindhu B Hegde, K R Prajwal, Taein Kwon, Andrew Zisserman

ICCV 2025 · Video › Video-language understanding · approach: Video-language pretraining · 5 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
add gesture-word coupling loss to sequence contrastive loss (ablation)JEGAL · AVS-Spotaccuracy: 20.83 -> 63.60Improved
add gesture-word coupling loss to sequence contrastive loss (ablation)JEGAL · AVS-Ret speech-text to gestureR@5: 12.20 -> 18.80Improved
add sequence contrastive loss to word coupling loss (ablation)JEGAL · AVS-Asd (6 speakers)accuracy: 14.8 -> 48.0Improved
add sequence contrastive loss to word coupling loss (ablation)JEGAL · AVS-Ret speech-text to gestureR@5: 8.50 -> 18.80Improved
concatenate rather than average speech and text embeddings (ablation)JEGAL · AVS-Spotaccuracy: 56.04 -> 63.60Improved
concatenate rather than average speech and text embeddings (ablation)JEGAL · AVS-Asd (6 speakers)accuracy: 41.2 -> 48.0Improved
fuse speech and text before a single contrastive head instead of pairwise text loss (ablation)JEGAL · AVS-Spotaccuracy: 34.31 -> 63.60Improved
fuse speech and text before a single contrastive head instead of pairwise audio loss (ablation)JEGAL · AVS-Spotaccuracy: 23.67 -> 63.60Improved
add audio to text input at inferenceJEGAL · AVS-Spotaccuracy: 61.00 -> 63.60Improved
add text to audio input at inferenceJEGAL · AVS-Ret speech-text to gestureR@5: 11.00 -> 18.80Improved
raise modality drop rate from 30% to 50% in training (text only inference) (ablation)JEGAL · AVS-Spotaccuracy: 52.2 -> 61.0Improved
raise modality drop rate from 50% to 70% in training (ablation)JEGAL · AVS-Spot (text+audio)accuracy: 63.6 -> 62.6Hurt

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