AI Paper Atlas

Research map / Video / Action recognition

Delving into Details: Synopsis-to-Detail Networks for Video Recognition

Shuxian Liang, Xu Shen, Jianqiang Huang, Xian-Sheng Hua

ECCV 2022 · Video › Action recognition · approach: Disentangled 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 DNet on top of SNet (ablation)S2DNet · Mini-Kineticstop-1 accuracy: 68.6 -> 74.7Improved
add SNet on top of DNet (ablation)S2DNet · Mini-Kineticstop-1 accuracy: 68.1 -> 74.7Improved
add learned location and scale parameters from SNet to DNet (ablation)DNet · Mini-Kineticstop-1 accuracy: 70.7 -> 73.3Improved
add contextual feature fusion to DNet (ablation)DNet · Mini-Kineticstop-1 accuracy: 70.7 -> 71.7Improved
combine sampling and fusion in DNet (ablation)DNet · Mini-Kineticstop-1 accuracy: 71.7 -> 74.7Improved
add spatial sampling only (ablation)detail sampler · Mini-Kineticstop-1 accuracy: 71.7 -> 72.7Improved
add temporal sampling only (ablation)detail sampler · Mini-Kineticstop-1 accuracy: 71.7 -> 74.0Improved
add learned space-time sampling over frozen center crops (ablation)detail sampler · Mini-Kineticstop-1 accuracy: 71.7 -> 74.7Improved
S2DNet over X3D-MX3D-M · Kinetics-400top-1 accuracy: 76.0 -> 78.0Improved
S2DNet over X3D-XLX3D-XL · Kinetics-400top-1 accuracy: 79.1 -> 80.6Improved
S2DNet over TSMTSM R50 · Something-Something V2top-1 accuracy: 63.4 -> 66.4Improved
S2DNet vs TDN at lower costTDN R50 · Something-Something V2top-1 accuracy: 65.3 -> 66.4Improved

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