AI Paper Atlas

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

Emotion Recognition in Context

Ronak Kosti, Jose M. Alvarez, Adria Recasens, Agata Lapedriza

CVPR 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling · 207 citations (OpenAlex)

Check 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
Use body and whole-image inputs together instead of body input alone (ablation)EMOTIC CNN · EMOTIC testAverage precision (AP): 25.44 -> 28.33Improved
Use body and whole-image inputs together instead of image input alone (ablation)EMOTIC CNN · EMOTIC testAverage precision (AP): 22.48 -> 28.33Improved
Add whole-image context to body input (ablation)EMOTIC CNN · EMOTIC testMean error rate: 1.0 -> 1.0No clear effect
Add whole-image context to image-only input (ablation)EMOTIC CNN · EMOTIC testMean error rate: 1.2 -> 1.0Improved
Add continuous-dimension training loss alongside discrete-category loss (ablation)Body + Image EMOTIC CNN · EMOTIC testAverage precision (AP): 24.18 -> 28.33Improved
Add discrete-category training loss alongside continuous-dimension loss (ablation)Body + Image EMOTIC CNN · EMOTIC testMean error rate: 1.1 -> 1.0Improved
Use body and image together instead of body alone (ablation)EMOTIC CNN · EMOTIC test, ValenceMean error rate: 0.9 -> 0.9No clear effect
Use body and image together instead of image alone (ablation)EMOTIC CNN · EMOTIC test, ValenceMean error rate: 0.9 -> 0.9No clear effect
Use body and image together instead of body alone (ablation)EMOTIC CNN · EMOTIC test, ArousalMean error rate: 1.1 -> 1.2Hurt
Use body and image together instead of image alone (ablation)EMOTIC CNN · EMOTIC test, ArousalMean error rate: 1.9 -> 1.2Improved
Use body and image together instead of body alone (ablation)EMOTIC CNN · EMOTIC test, DominanceMean error rate: 1.0 -> 0.9Improved
Use body and image together instead of image alone (ablation)EMOTIC CNN · EMOTIC test, DominanceMean error rate: 0.8 -> 0.9Hurt

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