AI Paper Atlas

Research map / Video / Action recognition

Early Action Prediction by Soft Regression

Jian–Fang Hu, Wei‐Shi Zheng, Lianyang Ma, Gang Wang, Jianhuang Lai, Jianguo Zhang

TPAMI 2018 · Video › Action recognition · approach: Fully supervised temporal action detection · 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 learned soft labels instead of random soft labels (ablation)MSRNN · SYSU 3D HOIAUC: 0.66871 -> 0.71615Improved
use learned soft labels instead of all-ones labels (ablation)MSRNN · SYSU 3D HOIAUC: 0.68521 -> 0.71615Improved
use learned soft labels instead of manually increasing 0.5 to 1 (ablation)MSRNN · SYSU 3D HOIAUC: 0.70083 -> 0.71615Improved
add consistency term with weight 500 instead of 0 (ablation)MSRNN · SYSU 3D HOIAUC: 0.67031 -> 0.71615Improved
raise consistency weight to 500000 (ablation)MSRNN · SYSU 3D HOIAUC: 0.71615 -> 0.65521Hurt
use increasing weights s instead of decreasing (ablation)MSRNN · SYSU 3D HOIAUC: 0.6875 -> 0.71615Improved
learn class-specific multiple soft labels instead of a single soft label vector (ablation)SRNN · SYSU 3D HOIAUC: 70.2 -> 71.6Improved
learn class-specific multiple soft labels in linear model (ablation)SLR · SYSU 3D HOIAUC: 69.6 -> 70.1Improved
add depth and skeleton to RGB input (ablation)MSRNN · SYSU 3D HOIAUC: 61.3 -> 71.6Improved
use RGB-D input instead of RGB-only (ablation)MSRNN · SYSU 3D HOIAUC: 62.7 -> 71.6Improved
use CNN features instead of HOG-based LAFFMSRNN · SYSU 3D HOIAUC: 71.6 -> 75.4Improved
use soft regression on two-stream CNN features instead of direct two-stream predictionMSRNN · SYSU 3D HOIAUC: 64.9 -> 66.2Improved

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