AI Paper Atlas

Research map / Video / Action recognition

MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos

Arkaprava Sinha, Monish Soundar Raj, Pu Wang, Ahmed Helmy, Hieu Le, Srijan Das

CVPR 2026 · Video › Action recognition · approach: Fully supervised temporal action detection · 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 CLIP instead of I3D visual backboneMS-Temba · TSUmAP: 36.1 -> 44.0Improved
add Mamba temporal encoder (ablation)CLIP baseline · TSUmAP: 24.7 -> 40.2Improved
add dilated SSM scanning (ablation)MS-Temba · TSUmAP: 40.2 -> 42.5Improved
add dilated SSM scanning (ablation)MS-Temba · CharadesmAP: 32.4 -> 32.5No clear effect
add MS-Fuser (ablation)MS-Temba · TSUmAP: 42.5 -> 44.0Improved
add consistency loss Lcons alone (ablation)MS-Temba · TSUmAP: 42.1 -> 42.1No clear effect
add auxiliary loss Laux (ablation)MS-Temba · TSUmAP: 42.1 -> 43.0Improved
add auxiliary loss Laux (ablation)MS-Temba · CharadesmAP: 33.6 -> 33.1Hurt
add both Lcons and Laux (ablation)MS-Temba · TSUmAP: 42.1 -> 44.0Improved
consistency loss instead of correlation loss for alignment (ablation)MS-Temba · TSUmAP: 43.5 -> 44.0Improved
sum + projection + SSM fusion instead of concat + projection (ablation)MS-Fuser · TSUmAP: 42.2 -> 44.0Improved
add a fourth Temba block (ablation)MS-Temba · TSU and CharadesmAPHurt

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