AI Paper Atlas

Research map / Video / Action recognition

An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos

Sicheng Zhao, Yunsheng Ma, Yang Gu, Jufeng Yang, Tengfei Xing, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer

AAAI 2020 · Video › Action recognition · approach: Contrastive video representation learning · 131 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
use VAANet instead of the strongest baselineVideo emotion recognition · VideoEmotion-8accuracy: 52.5 -> 54.5Improved
use VAANet instead of the strongest baselineVideo emotion recognition · Ekman-6accuracy: 54.4 -> 55.3Improved
add visual channel-wise attention to visual spatial attention (ablation)VAANet · VideoEmotion-8average accuracy: 51.7 -> 52.6Improved
add visual temporal attention to visual spatial and channel-wise attention (ablation)VAANet · VideoEmotion-8average accuracy: 52.6 -> 53.6Improved
add audio temporal attention to visual attentions (ablation)VAANet · VideoEmotion-8average accuracy: 53.6 -> 54.5Improved
add visual channel-wise attention to visual spatial attention (ablation)VAANet · Ekman-6average accuracy: 50.8 -> 53.4Improved
add visual temporal attention to visual spatial and channel-wise attention (ablation)VAANet · Ekman-6average accuracy: 53.4 -> 54.5Improved
add audio temporal attention to visual attentions (ablation)VAANet · Ekman-6average accuracy: 54.5 -> 55.3Improved
replace CE with PCCE using visual attentions only (ablation)VAANet · VideoEmotion-8average accuracy: 51.9 -> 53.6Improved
replace CE with PCCE using visual and audio attentions (ablation)VAANet · VideoEmotion-8average accuracy: 53.9 -> 54.5Improved
replace CE with PCCE using visual attentions only (ablation)VAANet · Ekman-6average accuracy: 52.0 -> 54.5Improved
replace CE with PCCE using visual and audio attentions (ablation)VAANet · Ekman-6average accuracy: 54.6 -> 55.3Improved

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