AI Paper Atlas

Research map / Video / Action recognition

XOV-Action: Toward Generalizable Open-Vocabulary Action Recognition

Kun-Yu Lin, Henghui Ding, Jia-Run Du, Jiaming Zhou, Yi-Xing Peng, Yu-Ming Tang, Zhilin Zhao, Chen Change Loy, Wei-Shi Zheng

TPAMI 2026 · Video › Action recognition · approach: Disentangled action recognition · 15 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 scene-aware discrimination loss L_scene (ablation)L_vta baseline · XOVABench (trained on Kinetics150) ARID/NEC-Drclosed-set accuracy: +1.83% and +4.63%Improved
add L_scene alone (ablation)L_vta baseline · XOVABench (trained on Kinetics150) averageopen-set accuracy: 38.64 -> 37.00Hurt
add L_scene alone (ablation)L_vta baseline · XOVABench (trained on Kinetics150) averageoverall accuracy: 46.94 -> 47.42Improved
add action-aware discrimination loss L_action (ablation)L_vta + L_scene · XOVABench (trained on Kinetics150) averageopen-set accuracy: 37.00 -> 39.21Improved
add diversified elaboration representation learning (ablation)L_vta + L_scene + L_action · XOVABench (trained on Kinetics150) averageoverall accuracy: 48.00 -> 49.80Improved
add diversified elaboration representation learning (ablation)L_vta + L_scene + L_action · XOVABench (trained on Kinetics150) averageopen-set accuracy: 39.21 -> 41.79Improved
use textual descriptions at inference only (ablation)XOV-Action without elaboration learning · XOVABench (trained on Kinetics150) averageopen-set accuracy: 39.21 -> 40.56Improved
add video elaboration modules (ablation)XOV-Action · XOVABench (trained on Kinetics150) averageopen-set accuracy: 40.85 -> 41.79Improved
add adaptive elaboration matching (ablation)XOV-Action · XOVABench (trained on Kinetics150) averageopen-set accuracy: 41.13 -> 41.79Improved
add adaptive elaboration matching (ablation)XOV-Action · XOVABench (trained on Kinetics150) averageclosed-set accuracy: 54.97 -> 55.96Improved
add L_scene (ablation)XOV-Action · XOVABench (trained on Kinetics150) averageclosed-set accuracy: 53.85 -> 55.96Improved
add L_action (ablation)XOV-Action · XOVABench (trained on Kinetics150) averageopen-set accuracy: 40.99 -> 41.79Improved

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