AI Paper Atlas

Research map / Video / Action recognition

Controllable Attention for Structured Layered Video Decomposition

Jean-Baptiste Alayrac, Joao Carreira, Relja Arandjelovic, Andrew Zisserman

ICCV 2019 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 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 encoder gating masks (ablation)C2 · Kinetics-600 val blended (transparency)validation loss: 0.131 -> 0.120Improved
add encoder gating masks (ablation)C2 · Kinetics-600 val blended (occlusion)validation loss: 0.200 -> 0.190Improved
add the composition module (layers and composing coefficients) to the centrifuge (ablation)Centrifuge · Kinetics-600 val blended (occlusion)validation loss: 0.253 -> 0.200Improved
add the composition module (layers and composing coefficients) to the centrifuge (ablation)Centrifuge · Kinetics-600 val blended (transparency)validation loss: 0.149 -> 0.131Improved
use C2 instead of the twice as large predictor-corrector centrifugelayer decomposition · Kinetics-600 val blended (occlusion)validation loss: 0.264 -> 0.190Improved
use internal prediction control instead of deterministic control (ablation)C3 · Kinetics-600 val blended (transparency)validation loss: 0.191 -> 0.119Improved
use internal prediction control instead of deterministic control (ablation)C3 · Kinetics-600 val blended (transparency)control accuracy (%): 79.1% -> 77.7%No clear effect
add audio control to C2 with deterministic controlC2 · Kinetics-600 val blended (transparency)validation loss: 0.120 -> 0.191Hurt
decompose blended video with C2 before I3D classification (transparency)I3D · Kinetics-600 val action recognition (transparency blended)accuracy: 22.1 -> 40.1Improved
decompose blended video with C2 before I3D classification (occlusion)I3D · Kinetics-600 val action recognition (occlusion blended)top-1 accuracy: 21.3 -> 24.7Improved
use C2 instead of CentrifugePC to unblend before I3D (occlusion)I3D pipeline · Kinetics-600 val action recognition (occlusion blended)top-1 accuracy: 21.5 -> 24.7Improved
shift the control audio so it does not overlap the video (ablation)C3 with internal prediction · Kinetics-600 val blended (transparency)control accuracy (points): decreases by 1.4 percentage pointsHurt

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