AI Paper Atlas

Research map / Video / Video segmentation and tracking

Introducing Decomposed Causality with Spatiotemporal Object-Centric Representation for Video Classification

Yachong Zhang, Lei Meng, Shuo Xu, Zhuang Qi, Wei Wu, Lei Wu, Xiangxu Meng

AAAI 2026 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 0 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
add STEM module (ablation)Uniformerv2-B base · MSR-VTTTop-1 accuracy: 60.73 -> 62.23Improved
add STEM module (ablation)Uniformerv2-B base · ActivityNetTop-1 accuracy: 86.77 -> 88.58Improved
add compositional structure-aware attention (CSA) (ablation)SurdCRL w/ Uniformerv2-B · MSR-VTTTop-1 accuracy: 62.23 -> 62.50Improved
add adaptive sampling (AS) (ablation)SurdCRL w/ Uniformerv2-B · ActivityNetTop-1 accuracy: 88.94 -> 89.10Improved
add back-door intervention (BDI) (ablation)SurdCRL w/ Uniformerv2-B · MSR-VTTTop-1 accuracy: 62.80 -> 63.51Improved
add front-door intervention (FDI) after BDI (ablation)SurdCRL w/ Uniformerv2-B · MSR-VTTTop-1 accuracy: 63.51 -> 63.82Improved
add front-door intervention (FDI) after BDI (ablation)SurdCRL w/ Uniformerv2-B · ActivityNetTop-1 accuracy: 89.65 -> 89.95Improved
use saliency mask instead of zero mask for confounder dictionary (ablation)SurdCRL w/ Uniformerv2-B · MSR-VTTTop-1 accuracy: 63.16 -> 63.82Improved
use saliency mask instead of boxes mask (ablation)SurdCRL w/ Uniformerv2-B · ActivityNetTop-1 accuracy: 89.85 -> 89.95Improved
increase sampling count N beyond 10 in adaptive sampling (ablation)SurdCRL · MSR-VTT and ActivityNetTop-1 accuracyHurt
replace ORViT with SurdCRL on Uniformerv2-BUniformerv2-B · ActivityNetTop-1 accuracy: 88.21 -> 89.95Improved
replace ECRL with SurdCRL on Uniformerv2-BUniformerv2-B · MSR-VTTTop-5 accuracy: 86.33 -> 86.62 (Top-5), ActivityNet Top-5 97.52 -> 98.01Mixed

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