AI Paper Atlas

Research map / Video / Action recognition

RobAVA: A Large-scale Dataset and Baseline Towards Video based Robotic Arm Action Understanding

Baoli Sun, Ning Wang, Xinzhu Ma, Anqi Zou, Yihang Lu, Chuixuan Fan, Zhihui Wang, Kun Lu, Zhiyong Wang

ICCV 2025 · Video › Action recognition · approach: Disentangled action recognition · 1 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 category prompt to backbone (ablation)AGPT-Net backbone · RobAVA-Rmean accuracy: 50.2 -> 51.1Improved
add attribute prompts to backbone (ablation)AGPT-Net backbone · RobAVA-Rmean accuracy: 50.2 -> 51.9Improved
replace category prompts with atomic attributes (ablation)AGPT-Net · RobAVA-Rmean accuracy: 0.8% improvementImproved
combine category and attribute prompts (ablation)AGPT-Net · RobAVA-Rmean accuracy: 51.9 -> 52.7Improved
add joint semantic space constraint (JSC) (ablation)AGPT-Net · RobAVA-Smean accuracy: 93.9 -> 94.8Improved
add joint semantic space constraint (JSC) (ablation)AGPT-Net · RobAVA-Rmean accuracy: 52.7 -> 53.8Improved
use spatial clustering ratio 1/4 versus no merging (ablation)AGPT-Net · RobAVA-Rmean accuracy: 50.5 -> 51.0Improved
use larger clustering ratio 1/8 instead of 1/4 (ablation)AGPT-Net · RobAVA-Rmean accuracy: 51.0 -> 50.4Hurt
use temporal downsampling {1,2} instead of {1} (ablation)AGPT-Net · RobAVA-Rmean accuracy: 51.0 -> 52.7Improved
use temporal downsampling {2,3} instead of {1,2} (ablation)AGPT-Net · RobAVA-Rmean accuracy: 52.7 -> 50.8Hurt
add third temporal scale {1,2,3} versus {1,2} (ablation)AGPT-Net · RobAVA-Rmean accuracy: 52.7 -> 51.7Hurt
AGPT-Net versus UniFormerV2 on FineGym288AGPT-Net · FineGym288mean accuracy: 52.4 -> 54.7Improved

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