AI Paper Atlas

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

FL-MSRE: A Few-Shot Learning based Approach to Multimodal Social Relation Extraction

Hai Wan, Manrong Zhang, Jianfeng Du, Ziling Huang, Yufei Yang, Jeff Z. Pan

AAAI 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 19 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 face-image features to the BERT text model, using same-image facesProto (BERT) · FC-TF, 3 way 1 shotaccuracy: 40.00±0.11 -> 58.44±0.21Improved
Add face-image features to the BERT text model, using different-image facesProto (BERT) · FC-TF, 3 way 3 shotaccuracy: 51.29±0.16 -> 77.29±0.54Improved
Add face-image features to the BERT text model, using same-image facesProto (BERT) · DRC-TF, 3 way 1 shotaccuracy: 46.28±0.15 -> 54.16±0.22Improved
Add face-image features to the BERT text model, using different-image facesProto (BERT) · DRC-TF, 3 way 3 shotaccuracy: 48.35±0.43 -> 62.30±0.39Improved
Add face-image features to the BERT text model, using same-image facesProto (BERT) · OM-TF, 3 way 1 shotaccuracy: 40.00±0.11 -> 58.44±0.21Improved
Add face-image features to the BERT text model, using different-image facesProto (BERT) · OM-TF, 3 way 3 shotaccuracy: 51.29±0.16 -> 77.29±0.54Improved
Collect the two faces from different rather than the same imageFL-MSRE · FC-TF, DRC-TF, and OM-TFaccuracy: -0.44±0.10; 0.36±0.12; 0.63±0.15; -0.26±0.22; 3.60±0.22; 5.33±0.39; 0.36±0.66; 0.63±0.25Mixed
Train on one dataset and test on another, using multimodal facesFL-MSRE versus Proto (BERT) · DRC-TF trained on OM-TF; OM-TF trained on DRC-TFaccuracy: 38.38±0.16 -> 50.69±0.81; 40.74±0.18 -> 63.83±0.42; 37.27±0.69 -> 55.82±0.76; 44.09±0.69 -> 58.50±0.45Improved

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