AI Paper Atlas

Research map / Video / Video segmentation and tracking

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess

NeurIPS 2021 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 9 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 SIMONe's joint video decomposition rather than the strongest listed video baseline, MONetObjects Room 9 video segmentation · Objects Room 9ARI-F: 0.865 -> 0.936Improved
Use SIMONe's joint video decomposition rather than the strongest listed video baseline, S-IODINECATER video segmentation · CATERARI-F: 0.668 -> 0.918Improved
Use SIMONe's joint video decomposition rather than the strongest listed video baseline, MONetPlayroom video segmentation · PlayroomARI-F: 0.442 -> 0.800Improved
Predict allocentric position using object latent plus timestep instead of object latent alone (ablation)CATER trajectory probe, all objects · CATERR²: 0.710 -> 0.871Improved
Add frame latent to object latent and timestep for trajectory prediction (ablation)CATER trajectory probe, all objects · CATERR²: 0.871 -> 0.876No clear effect
Use the correct object's latent rather than the other object latents to predict its position (ablation)CATER trajectory probe, all objects · CATERR²: -0.062 -> 0.871Improved
Predict allocentric position using object latent plus timestep instead of object latent alone (ablation)CATER trajectory probe, moving objects · CATERR²: 0.724 -> 0.894Improved
Add frame latent to object latent and timestep for trajectory prediction (ablation)CATER trajectory probe, moving objects · CATERR²: 0.894 -> 0.898No clear effect
Use the correct object's latent rather than the other object latents to predict its position (ablation)CATER trajectory probe, moving objects · CATERR²: -0.022 -> 0.894Improved
Use frame latent rather than object latents to predict camera locationCATER camera-pose probe · CATERR²: 0.044 -> 0.949Improved
Use frame latent rather than object latents to predict camera orientationCATER camera-pose probe · CATERR²: 0.292 -> 0.946Improved

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