AI Paper Atlas

Research map / Video / Action recognition

Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles

Manuel Martin, Alina Roitberg, Monica Haurilet, Matthias Horne, Simon Reiss, Michael Voit, Rainer Stiefelhagen

ICCV 2019 · Video › Action recognition · approach: Action anticipation and latent actions · 215 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 interior stream to pose model (Two-Stream) (ablation)pose-based model · Drive&Act fine-grained activities, testaccuracy: 44.36 -> 45.39Improved
add car-interior network as third stream (ablation)Two-Stream · Drive&Act fine-grained activities, testaccuracy: 45.39 -> 46.95Improved
end-to-end I3D instead of Three-Stream pose modelfine-grained activity recognition · Drive&Act testaccuracy: 46.95 -> 63.64Improved
fuse all sources by softmax score averaging instead of best single view (ablation)I3D · Drive&Act fine-grained activities, testaccuracy: 64.98 -> 69.03Improved
combine NIR cameras vs best single NIR camera (ablation)I3D · Drive&Act fine-grained activities, testaccuracy: 63.64 -> 67.17Improved
use face view instead of front top viewI3D · Drive&Act fine-grained activities, testaccuracy: 63.64 -> 42.98Hurt
use I3D instead of pose models at scenario levelscenario/task recognition · Drive&Act testaccuracy: 35.45 -> 31.80Hurt
train on one view and test on another viewI3D · Drive&Act cross-viewaccuracy: 69.57 -> 27.49 (best cross-view)Hurt
I3D vs pose-based models for location classificationatomic action units · Drive&Act testlocation accuracy: 56.5 vs 51.12Hurt

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