AI Paper Atlas

Research map / Video / Action recognition

Symbiotic Attention with Privileged Information for Egocentric Action Recognition

Xiaohan Wang, Yu Wu, Linchao Zhu, Yi Yang

AAAI 2020 · Video › Action recognition · approach: Disentangled action recognition · 72 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 SAP interactions among verb, noun, and privileged detection features3D ResNet-50 action recognition · EPIC-Kitchens validationnoun top-1 accuracy: 23.8 -> 35.0Improved
add SAP interactions among verb, noun, and privileged detection features3D ResNet-50 action recognition · EPIC-Kitchens validationverb top-1 accuracy: 54.6 -> 55.9Improved
add SAP interactions among verb, noun, and privileged detection features3D ResNet-50 action recognition · EPIC-Kitchens validationaction top-1 accuracy: 25.0; 2.2% higher than LFB MaxImproved
use SAP rather than LFB MaxEPIC-Kitchens test seen (S1) · EPIC-Kitchens test seen (S1)action top-1 accuracy: 34.8 vs 32.7; 2.1%Improved
use SAP rather than LFB MaxEPIC-Kitchens test unseen (S2) · EPIC-Kitchens test unseen (S2)action top-1 accuracy: 23.9 vs 21.2; 2.7%Improved
use SAP rather than LSTAEGTEA · EGTEA averagetop-1 accuracy: 62.7 vs 61.9Improved
add verb features to noun-only CNN (ablation)EPIC-Kitchens noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 23.8 -> 24.2Improved
use privileged detection features alone with average pooling (ablation)EPIC-Kitchens noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 23.8 -> 24.5Improved
use privileged detection features alone with max pooling (ablation)EPIC-Kitchens noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 23.8 -> 25.6Improved
add cross-stream gating (ablation)SAP noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 30.4 -> 32.7Improved
add gating (ablation)SAP noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 33.6 -> 35.0Improved
add cross-stream interaction instead of gating and attending with the same stream (ablation)SAP noun prediction · EPIC-Kitchens validationnoun top-1 accuracy: 33.2 -> 35.0Improved

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