AI Paper Atlas

Research map / Video / Action recognition

RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos

Tianshu Yu, Yikang Li, Baoxin Li

ECCV 2020 · Video › Action recognition · approach: Fully supervised temporal action detection · 8 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 BR to RhyRNN+DivPool (ablation)RhyRNN · Breakfast event recognitionaccuracy (%): 43.7 -> 44.3Improved
add BR to RhyRNN+DivPool (ablation)RhyRNN · Breakfast event recognitionmAP (%): 40.5 -> 41.9Improved
add DivPool to RhyRNN+BR (ablation)RhyRNN · Breakfast event recognitionaccuracy (%): 40.7 -> 44.3Improved
add DivPool to RhyRNN+BR (ablation)RhyRNN · Breakfast event recognitionmAP (%): 35.2 -> 41.9Improved
add DivPool and BR on top of RhyRNN alone (ablation)RhyRNN · Breakfast event recognitionaccuracy (%): 35.8 -> 44.3Improved
add BR to RhyRNN (ablation)RhyRNN on I3D features · Charades multi-label recognitionmAP (%): 24.6 -> 25.4Improved
replace 6-layer IndRNN with 2-layer RhyRNNsequence model without DivPool/BR · Breakfast event recognitionaccuracy (%): 19.4 -> 35.8Improved
replace SkipRNN with RhyRNNsequence model without DivPool/BR · Breakfast event recognitionaccuracy (%): 31.9 -> 35.8Improved
replace IndRNN with RhyRNN in DivPool+BR pipelineDivPool+BR pipeline · Breakfast event recognitionaccuracy (%): 42.7 -> 44.3Improved
replace SkipRNN with RhyRNN in DivPool+BR pipelineDivPool+BR pipeline · Breakfast event recognitionaccuracy (%): 40.2 -> 44.3Improved
stack 4 RhyRNN layers instead of 2 before one DivPool (ablation)RhyRNN+DivPool · Breakfast event recognitionaccuracy (%): 43.7 -> 43.1Hurt
use two DivPool stages with 4 RhyRNN layers instead of one with 2 (ablation)RhyRNN+DivPool · Breakfast event recognitionaccuracy (%): 43.7 -> 41.4Hurt

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