AI Paper Atlas

Research map / Video / Action recognition

Recognizing Car Fluents From Video

Bo Li, Tianfu Wu, Caiming Xiong, Song-Chun Zhu

CVPR 2016 · Video › Action recognition · approach: Disentangled action recognition · 11 citations (OpenAlex)

Check 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
Combine TPS with iDTCar fluent recognition · Car-FluentMP: 34.4 -> 45.0Improved
Add C3D features to TPS+iDTCar fluent recognition · Car-FluentMP: 45.0 -> 50.8Improved
Use ST-AOG with HOG instead of CNN featuresST-AOG part localization · Car-Fluentmean part detection rate: 29.0 -> 48.3Improved
Use cascade car detectionST-AOG part localization · Car-Fluentmean part detection rate: 48.3 -> 44.6Hurt
Add view penalty (ablation)ST-AOG part status estimation · Car-Fluentpart status detection rateImproved
Add part status penalty (ablation)ST-AOG part status estimation · Car-Fluentpart status detection rateImproved
Add motion flow (ablation)ST-AOG part status estimation · Car-Fluentpart status detection rateMixed
Add view and part status penalties (ablation)ST-AOG part status estimation · Car-Fluentpart status detection rateMixed

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