AI Paper Atlas

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

Attention-Aware Polarity Sensitive Embedding for Affective Image Retrieval

Xingxu Yao, Dongyu She, Sicheng Zhao, Jie Liang, Yu-Kun Lai, Jufeng Yang

ICCV 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 44 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 N-pair loss with polarity-sensitive EP loss (ablation)ResNet-50 embedding · FImAP8: 0.5217 -> 0.5680Improved
replace N-pair loss with EP loss (ablation)ResNet-50 embedding · FImAP2: 0.8062 -> 0.8558Improved
add attention loss (AT) to EP loss (ablation)EP loss · FImAP8: 0.5680 -> 0.6225Improved
add attention loss (AT) to EP loss (ablation)EP loss · FImAP2: 0.8558 -> 0.7816Hurt
replace EP loss with attention-weighted WEP loss in the full model (ablation)APSE · FImAP8: 0.7190 -> 0.7344Improved
replace EP loss with WEP loss in the full model (ablation)APSE · FImAP2: 0.8912 -> 0.9079Improved
embedding losses instead of softmax fine-tuningResNet · FImAP8: 0.4380 -> 0.5217Improved
set trade-off lambda between WEP and attention loss to 0.5 (ablation)APSE · FImAP8 and mAP2Improved

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