AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation

Pia Bideau, Aruni RoyChowdhury, Rakesh R. Menon, Erik Learned-Miller

CVPR 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 49 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
combine perspective-geometry rigid-motion segmentation with CNN object proposals and object-level motion groupingmotion segmentation · FBMS-motion, complex background, camouflaged animals; multi-labelF: 64.97 vs 63.59; 65.60 vs 45.83; 72.15 vs 61.52Improved
combine perspective-geometry rigid-motion segmentation with CNN object proposals and object-level motion groupingmotion segmentation · FBMS-motion; binaryF: 81.85 vs 86.96Hurt
combine perspective-geometry rigid-motion segmentation with CNN object proposals and object-level motion groupingmotion segmentation · camouflaged animals; binaryF: 75.95 vs 76.31Hurt
combine perspective-geometry rigid-motion segmentation with CNN object proposals and object-level motion groupingmotion segmentation · complex background; binaryF: 90.11 vs 86.56Improved
model flow-error variance as a function of flow magnitude instead of using constant variance (ablation)motion segmentation · all (44 sequences), multi-labelF: 64.86 -> 66.45Improved
model flow-error variance as a function of flow magnitude instead of using constant variance (ablation)motion segmentation · all (44 sequences), binaryF: 81.15 -> 81.27Improved
add grouping of rigid motion components into composed object-motion models (ablation)motion segmentation · all (44 sequences), multi-labelF: 52.69 -> 66.45Improved
add composed motion models to refine object boundaries rather than use object proposals alone (ablation)motion segmentation · all (44 sequences), binaryF: 78.78 -> 81.27Improved
add a fully-connected CRF refinement (ablation)motion segmentation · all (44 sequences), multi-labelF: 66.45 -> 66.51No clear effect
add a fully-connected CRF refinement (ablation)motion segmentation · all (44 sequences), binaryF: 81.27 -> 81.49No clear effect

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