AI Paper Atlas

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

MOVES: Manipulated Objects in Video Enable Segmentation

Richard E. L. Higgins, David F. Fouhey

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 4 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 MOVES features for held-object segmentation instead of COHESIVEPICK HOS · EPICKObject mIoU (%): 19.5 →25.7Improved
Use MOVES features for Box2Seg instead of COHESIVVISOR Box2Seg · VISOR held objectsmIoU: 8.9 →44.2Improved
Use MOVES features for Box2Seg instead of COHESIVVISOR Box2Seg · VISOR non-held objectsmIoU: 7.5 →45.0Improved
Use MOVES feature distances to determine whether pixels belong to the same object instead of RGB distancesObject grouping · VISOR and FGAUROC: 99.5 vs 81.5; 95.2 vs 78.4; 95.0 vs 78.6; 97.1 vs 75.8; 94.7 vs 73.3Improved
Train instance segmentation using MOVES Box2Seg masks rather than painstakingly annotated masksVISOR HOS instance segmentation · VISORMask AP@50 Held: 49.8 vs 25.5Hurt
Replace GMA-Flow with PWC-Net optical flow (ablation)MOVES · VISOR Hand feature distanceAUROC: 99.5 -> 98.2No clear effect
Replace GMA-Flow with PWC-Net optical flow (ablation)MOVES · VISOR Held feature distanceAUROC: 95.2 -> 94.6No clear effect
Replace GMA-Flow with PWC-Net optical flow (ablation)MOVES · VISOR Non-held feature distanceAUROC: 95.0 -> 94.2No clear effect
Use connected components on above-mean optical-flow magnitude for grouping pseudolabels (ablation)MOVES · VISOR Hand feature distanceAUROC: 99.5 -> 98.9No clear effect
Use MOVES with grouping loss on EISEN playroom rather than EISENObject segmentation · EISEN playroommIoU: 73.0 vs 71.8No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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