AI Paper Atlas

Research map / Video / Video segmentation and tracking

On the Usage of the Trifocal Tensor in Motion Segmentation

Federica Arrigoni, Luca Magri, Tomas Pajdla

ECCV 2020 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 6 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
use trifocal tensor (TriSeg) instead of fundamental matrix (Mode) for partial segmentationRPA-based motion segmentation with synchronization · Existing benchmark, 12 sequencesmisclassification error (%): lowest error in 9 out of 12 sequencesImproved
use trifocal tensor (TriSeg) instead of fundamental matrix (Mode)RPA-based motion segmentation · Novel benchmark stuffed animals1misclassification error (%): 8.92 -> 1.82Improved
use trifocal tensor (TriSeg) instead of fundamental matrix (Mode)RPA-based motion segmentation · Novel benchmark stuffed animals2misclassification error (%): 17.56 -> 3.05Improved
add fundamental-matrix pair segmentations to triplets (TriPairSeg vs TriSeg) (ablation)TriSeg · Existing benchmark (all correspondences)classified points (%): 60.51 -> 79.56 (Pen)Improved
add fundamental-matrix pair segmentations to triplets (TriPairSeg vs TriSeg) (ablation)TriSeg · Novel benchmark stuffed animals1misclassification error (%): 1.82 -> 4.73Hurt
add fundamental-matrix pair segmentations to triplets (TriPairSeg vs TriSeg) (ablation)TriSeg · Existing benchmark, trajectories of length two removedmisclassification error (%): Pouch 1.07 -> 0.65; Tea 0.01 -> 0.09Mixed
remove trajectories of length two from input correspondences (ablation)TriSeg · Existing benchmark, Penclassified points (%): 60.51 -> 83.98Improved
remove trajectories of length two from input correspondences (ablation)TriSeg · Existing benchmark, Penmisclassification error (%): 0.15 -> 0.15No clear effect
remove trajectories of length two from input correspondences (ablation)Mode · Existing benchmark, Teamisclassification error (%): 0.29 -> 0.15Improved
remove trajectories of length two from input correspondences (ablation)Synch · Existing benchmark, Penmisclassification error (%): 0.82 -> 0.42Improved

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