AI Paper Atlas

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

Understanding Embodied Reference with Touch-Line Transformer

Yang Li, Xiaoxue Chen, Hao Zhao, Jiangtao Gong, Guyue Zhou, Federico Rossano, Yixin Zhu

ICLR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal and affective interaction modeling · 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
Add VTL prediction and use the virtual touch line as gestural information (ablation)Touch-Line Transformer · YouRefIt testprecision (IoU=0.75): 37.2 -> 39.0Improved
Add VTL prediction instead of predicting no gestural line (ablation)Touch-Line Transformer · YouRefIt testprecision (IoU=0.25): 64.9 -> 71.1Improved
Add VTL prediction instead of predicting no gestural line (ablation)Touch-Line Transformer · YouRefIt testprecision (IoU=0.50): 57.4 -> 63.5Improved
Predict EWL instead of no gestural line (ablation)Touch-Line Transformer · YouRefIt testprecision across IoU thresholds: 64.9 -> 69.5; 57.4 -> 60.7; 37.2 -> 35.5Mixed
Replace EWL with VTL prediction (ablation)Touch-Line Transformer · YouRefIt testprecision across IoU thresholds: 69.5 -> 71.1; 60.7 -> 63.5; 35.5 -> 39.0Improved
Remove human context from input images using inpainting (ablation)Touch-Line Transformer · YouRefIt testprecision across IoU thresholds: 64.9 -> 59.1; 57.4 -> 51.3; 37.2 -> 32.4Hurt
Add the reference alignment loss to encourage co-linearity (ablation)Touch-Line Transformer with VTL · YouRefIt testprecision across IoU thresholds: 67.1 -> 71.1; 59.0 -> 63.5; 36.4 -> 39.0Improved
Add the reference alignment loss to encourage co-linearity (ablation)Touch-Line Transformer with VTL · YouRefIt testpredicted-box cosine similarity: 0.9815 -> 0.9878Improved
Use VTL rather than EWL as the pointing-line representationTouch-Line Transformer · YouRefIt testtarget-box cosine similarity: 0.9580 -> 0.9901Improved

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