AI Paper Atlas

Research map / Video / Action recognition

EAC-Net: Efficient and Accurate Convolutional Network for Video Recognition

Bowei Jin, Zhuo Xu

AAAI 2020 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 2 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 one MGTE block at stage 3 (Res3_1) (ablation)C2D ResNet-50 · Kinetics-400 valtop-1: 71.0 -> 72.6Improved
add one MGTE block at stage 4 instead of 3 (ablation)C2D ResNet-50 · Kinetics-400 valtop-1: 72.6 -> 73.6Improved
add one MGTE block at stage 5 (ablation)C2D ResNet-50 · Kinetics-400 valtop-1: 73.6 -> 73.7Improved
MGTE at both stage 4 and 5 (ablation)C2D ResNet-50 · Kinetics-400 valtop-1: 73.7 -> 74.3Improved
also add MGTE to stage 3 (ablation)EAC-Net w/o ATE · Kinetics-400 valtop-1: 74.3 -> 73.2Hurt
add temporal pooling branch only (ablation)C2D · Kinetics-400 valtop-1 and FLOPs: 71.0 -> 72.0; 172.7G -> 128.2GImproved
add temporal relation branch to pooling branch (ablation)MGTE block · Kinetics-400 valtop-1: 72.0 -> 74.3Improved
add gate driven by temporal gradient (ablation)MGTE temporal relation branch · Kinetics-400 valtop-1: 73.0 -> 73.6Improved
add global context to gate control (ablation)MGTE gate · Kinetics-400 valtop-1: 73.6 -> 74.3Improved
replace global average pooling with ATE block (ablation)C2D · Kinetics-400 valtop-1: 71.0 -> 72.5Improved
add ATE block (ablation)EAC-Net MGTE stage 4+5 · Kinetics-400 valtop-1: 74.3 -> 74.8Improved
increase input from 32 to 48 framesEAC-Net BNInception · Kinetics-400 valtop-1: 73.5 -> 74.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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