AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

YouRefIt: Embodied Reference Understanding With Language and Gesture

Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Song-Chun Zhu, Tao Gao, Yixin Zhu, Siyuan Huang

ICCV 2021 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 41 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 gestural cues (original images instead of inpainted) (ablation)FAOA · YouRefIt Image ERU test (IoU=0.25, all sizes)accuracy (%): 23.4 -> 44.5Improved
add gestural cues (original images instead of inpainted) (ablation)ReSC · YouRefIt Image ERU test (IoU=0.25, all sizes)accuracy (%): 34.3 -> 49.2Improved
add gestural cues (original images instead of inpainted) (ablation)ReSC · YouRefIt Image ERU test (IoU=0.5, all sizes)accuracy (%): 25.7 -> 34.9Improved
add language input (ablation)Ours (gesture features) · YouRefIt Image ERU test (IoU=0.25, all sizes)accuracy (%): 41.4 -> 54.7Improved
add language input (ablation)Ours (gesture features) · YouRefIt Image ERU test (IoU=0.5, all sizes)accuracy (%): 30.6 -> 40.5Improved
add pointing saliency heatmap to PAF features (ablation)Ours · YouRefIt Image ERU test (IoU=0.5, all sizes)accuracy (%): 37.6 -> 40.5Improved
add pointing saliency heatmap to PAF features (ablation)Ours · YouRefIt Image ERU test (IoU=0.25, all sizes)accuracy (%): 52.6 -> 54.7Improved
add PAF gestural features to ReSC-style modelReSC · YouRefIt Image ERU test (IoU=0.5, all sizes)accuracy (%): 34.9 -> 37.6Improved
use pretrained REF models without embodied training dataReSC · YouRefIt Image ERU test (IoU=0.25, all sizes)accuracy (%): 49.2 -> 20.8Hurt
add temporal module (Transformer) vs frame-basedVideo ERU · YouRefIt Video ERU, ground-truth canonical frames (IoU=0.5, all sizes)accuracy (%): 41.7 -> 38.8No clear effect
add temporal module (ConvLSTM) vs frame-basedVideo ERU · YouRefIt Video ERU, canonical frame detectionaverage F1: 34.5 -> 45.4Improved
add temporal module (Transformer) vs frame-basedVideo ERU · YouRefIt Video ERU, canonical frame detectionaverage F1: 34.5 -> 39.1Improved

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