AI Paper Atlas

Research map / Video / Action recognition

Adversarial Cross-Domain Action Recognition with Co-Attention

Boxiao Pan, Zhangjie Cao, Ehsan Adeli, Juan Carlos Niebles

AAAI 2020 · Video › Action recognition · approach: Disentangled action recognition · 103 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 TCoN instead of CDANTSN · HMDB51 → UCF101 (1)accuracy (%): 91.86 -> 96.78Improved
use TCoN instead of DAAAC3D · UCF50 → Olympic_Sportsaccuracy (%): 91.37 -> 95.92Improved
use TCoN instead of TA3NTRN · Olympic_Sports → UCF50accuracy (%): 92.92 -> 96.79Improved
use TCoN instead of TA3NTRN · UCF50 → Olympic_Sportsaccuracy (%): 98.15 -> 96.82Hurt
use TCoN instead of TA3NTRN · Jester (S) → Jester (T)accuracy (%): 60.11 -> 62.53Improved
add a segment-level discriminator (ablation)TCoN · Jester (S) → Jester (T)accuracy (%): 71.13 -> 72.24Improved
use target-aligned source features for matching (ablation)TCoN · Jester (S) → Jester (T)accuracy (%): 65.48 -> 72.24Improved
use co-attention instead of self-attention (ablation)TCoN · Jester (S) → Jester (T)accuracy (%): 57.95 -> 72.24Improved
weight segment predictions with attention scores instead of averaging (ablation)TCoN · Jester (S) → Jester (T)accuracy (%): 63.13 -> 72.24Improved

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