AI Paper Atlas

Research map / Video / Video segmentation and tracking

MOSO: Decomposing MOtion, Scene and Object for Video Prediction

Mingzhen Sun, Weining Wang, Xinxin Zhu, Jing Liu

CVPR 2023 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 14 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
decompose video into motion, scene, and object tokens and predict at token levelMOSO · BAIR video predictionFVD: 86.9 -> 83.6Improved
decompose video into motion, scene, and object tokens and predict at token levelMOSO · RoboNet 64² video predictionFVD: 62.5 -> 53.3Improved
decompose video into motion, scene, and object tokens and predict at token levelMOSO · KITTI 256² video predictionFVD: 446.1 -> 516.6Hurt
decompose video into motion, scene, and object tokens and predict at token levelMOSO · KTH 64² video predictionPSNR: 27.1 -> 29.8Improved
use motion, scene, and object decomposition instead of no decomposition (ablation)MOSO-VQVAE · KTH video reconstructionPSNR: 24.8 -> 36.0Improved
separate objects from scenes rather than treating them as combined content (ablation)MOSO-VQVAE · KTH video reconstructionPSNR: 32.6 -> 36.0Improved
add the preprocessing algorithm (ablation)MOSO-VQVAE · UCF101 video reconstructionFVD: 310.1 -> 267.9Improved
remove the preprocessing algorithm (ablation)MOSO · KTH 64² video predictionPSNR: 29.8 -> 29.2Hurt
remove the merge module (ablation)MOSO · KTH 64² video predictionLPIPS: 0.083 -> 0.125Hurt
use a single Transformer instead of the MOSO Transformer arrangement (ablation)MOSO · KTH 64² video predictionLPIPS: 0.083 -> 0.116Hurt
add a video discriminator with loss weight 0.1 (ablation)MOSO-VQVAE · UCF101 video reconstructionFID: 24.8 -> 17.9Improved
add an image discriminator alongside the video discriminator (ablation)MOSO-VQVAE · UCF101 video reconstructionFID: 17.9 -> 19.5Hurt

Later papers that compared with this method

2 later accepted papers report MOSO as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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