AI Paper Atlas

Research map / Video / Action recognition

Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification

Yang Du, Chunfeng Yuan, Bing Li, Lili Zhao, Yangxi Li, Weiming Hu

ECCV 2018 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 99 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 3 pyramid scales instead of 1 scale (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1 (Inception-ResNet-V2)accuracy RGB/Flow: 86.3% -> 87.3% (RGB), 84.0% -> 85.5% (Flow)Improved
add a fourth scale (Conv2d_4a_3x3) to the 3-scale pyramid (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1accuracy RGB/Flow: 87.3% -> 86.5% (RGB), 85.5% -> 85.0% (Flow)Hurt
aggregate the last conv layer of Block C instead of Block A (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1accuracy RGB/Flow: 85.8% -> 86.3% (RGB), 83.5% -> 84.0% (Flow)Improved
aggregate a conv layer instead of the last fully-connected layer (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1accuracy RGB/Flow: 85.5% -> 86.3% (RGB), 83.4% -> 84.0% (Flow)Improved
use element-wise multiplication instead of element-wise maximum for fusion (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1accuracy RGB: 85.7% -> 87.3%Improved
use element-wise multiplication instead of element-wise sum for fusion (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1accuracy RGB: 86.4% -> 87.3%Improved
add l_interactive and l_attn losses (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1 (3 scales)accuracy RGB/Flow/Late fusion: 87.3% -> 88.2% (RGB), 85.5% -> 86.5% (Flow), 94.2% -> 95.1% (late fusion)Improved
add only the l_interactive loss (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1 (3 scales)accuracy RGB: 87.3% -> 87.8%Improved
add only the l_attn loss (ablation)Interaction-aware spatio-temporal pyramid attention · UCF101 split 1 (3 scales)accuracy RGB: 87.3% -> 87.5%Improved
plug the attention layer into VGGNet-16Two-Stream VGGNet-16 · UCF101 split 1accuracy late fusion: 90.7% -> 92.8%Improved
plug the attention layer into BN-InceptionTwo-Stream BN-Inception · UCF101 split 1accuracy late fusion: 92.0% -> 94.6%Improved
plug the attention layer into Inception-ResNet-V2Two-Stream Inception-ResNet-V2 · UCF101 split 1accuracy late fusion: 92.6% -> 95.1%Improved

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