AI Paper Atlas

Research map / Video / Action recognition

Learning to Generalize without Bias for Open-Vocabulary Action Recognition

Yating Yu, Congqi Cao, Yifan Zhang, Yanning Zhang

ICCV 2025 · Video › Action recognition · approach: Disentangled action recognition · 10 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 cross-batch meta-optimization (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.3 -> 32.1Improved
add Gaussian Weight Average self-ensemble (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.3 -> 30.7Improved
combine meta-optimization and GWA (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.3 -> 33.5Improved
use cross-batch meta-optimization instead of gradient accumulation (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.9 -> 33.5Improved
add residual feature distillation CLIP regularization (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.3 -> 25.2Hurt
add interpolated weight regularization (ablation)VCLIP · UCF-SCUBA top-1accuracy: 28.3 -> 28.9No clear effect
use cross-batch meta-optimization instead of MAML meta unseen (ablation)VCLIP · UCF-SCUBA top-1accuracy: 31.8 -> 33.5Improved
shuffle batch sampler instead of initial order (ablation)Open-MeDe · UCF-SCUBA top-1accuracy: 28.9 -> 33.5Improved
use shuffled sampler instead of semantically similar classes across batches (ablation)Open-MeDe · UCF-SCUBA top-1accuracy: 30.9 -> 33.5Improved
add CLIP prediction-space ensembleOpen-MeDe · UCF-SCUBA top-1accuracy: 33.5 -> 32.0Hurt
add CLIP weight-space ensembleOpen-MeDe · UCF-SCUBA top-1accuracy: 33.5 -> 29.9Hurt
integrate Open-MeDe into X-CLIP partially tuned learnerX-CLIP · UCF cross-datasettop-1 accuracy: 72.0 -> 79.3Improved

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