AI Paper Atlas

Research map / Video / Action recognition

Soft Video Parsing by Label Distribution Learning

Xin Geng, Miaogen Ling

AAAI 2017 · Video › Action recognition · approach: Temporal action segmentation · 42 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
replace hard single-label parsing (SSRG) with soft label distribution (SP)SSRG · THUMOS'14 averageAP: 10.8 -> 18.3Improved
replace SSRG with SPSSRG · THUMOS'14 averageframe labeling accuracy: 52.8 -> 66.0Improved
replace SSRG with SPSSRG · MSR-II averageAP: 9.0 -> 23.9Improved
replace SSRG with SPSSRG · MSR-II averageframe labeling accuracy: 66.7 -> 77.9Improved
add sub-action decomposition (SSRG/SP) versus sliding-window RNMSRNMS · THUMOS'14 averageAP: 7.8 -> 10.8Improved
replace SSRG with SP on billiardsSSRG · THUMOS'14 billiardsAP: 3.7 -> 3.1Hurt
replace SSRG with SP on tennis-swingSSRG · THUMOS'14 tennis-swingframe labeling accuracy: 66.9 -> 58.4Hurt
replace RNMS with SP on long-jumpRNMS · THUMOS'14 long-jumpAP: 35.3 -> 26.7Hurt
tune ambiguity level lambda per action (OAL) instead of fixed 1.0 (ablation)SP · THUMOS'14 averageAP: 18.3 -> 22.1Improved
tune ambiguity level lambda per action (OAL) (ablation)SP · THUMOS'14 averageframe labeling accuracy: 66.0 -> 68.1Improved

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