AI Paper Atlas

Research map / Video / Action recognition

MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

Syed Talal Wasim, Hamid Suleman, Olga Zatsarynna, Muzammal Naseer, Juergen Gall

ICCV 2025 · Video › Action recognition · approach: Action anticipation and latent actions · 2 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 observation-dependent mixture of A matrices (MixANT) versus MANTAMANTA · Breakfast (alpha=0.2, beta=0.1)Mean MoC: 27.7 -> 29.6Improved
add mixture of A matrices (MixANT) versus MANTAMANTA · Assembly101 (alpha=0.2, beta=0.1)Top-1 MoC: 16.9 -> 20.3Improved
scale experts from 1 to about 5 per block (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoCImproved
increase experts beyond 5 (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoCHurt
add initial static Mamba blocks up to K0=3 (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoC: 52.4 -> 53.5Improved
use unified router for forward and backward SSM instead of independent routers (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoCImproved
add load balancing loss (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoCImproved
raise load balancing coefficient beyond 0.15 (ablation)MixANT · Breakfast (alpha=0.2, beta=0.1)Top-1 MoCHurt
condition gating vector only on observed frames rather than observed plus zero-padded future (ablation)MixANT · BreakfastTop-1 MoCImproved
use mixture of experts instead of query-key for input-dependent A (ablation)MixANT · Breakfast Top-1 MoC averaged over all alpha/betaTop-1 MoC: 52.3 -> 54.1Improved
use mixture of experts instead of large MLP for input-dependent A (ablation)MixANT · Breakfast Top-1 MoC averaged over all alpha/betaTop-1 MoC: 47.4 -> 54.1Improved
replace Mamba block with MixMamba in TestraTestra short Mamba · EK-100 overallaction recall@5: 15.2 -> 17.1Improved

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