AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Meta Agent Teaming Active Learning for Pose Estimation

Jia Gong, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu

CVPR 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 57 citations (OpenAlex)

Check 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 MATAL to select images for annotationpose estimation active learning · ICVLaverage joint errorImproved
use MATAL to select images for annotationpose estimation active learning · MPIIlabeling effort at similar PCKh@0.5: 4K images; 6K images; around 2K imagesImproved
use MATAL to select images for annotationpose estimation active learning · NYUaverage joint error: 5K images; 23.5 mm; around 10K labeled imagesImproved
add global topological feature KFP0 to the state (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 23.01 -> 22.53Improved
add local topological features to the state (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 23.23 -> 22.53Improved
add appearance feature KFA to the state (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 23.55 -> 22.53Improved
add budget consumption ratio b to the state (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 23.85 -> 22.53Improved
add topological novelty scores to the action (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 25.13 -> 22.53Improved
add topological representativeness histograms to the action (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 24.12 -> 22.53Improved
add appearance feature fA to the action (ablation)MATAL · NYUMSE (mm), 8000 labeled samples: 23.69 -> 22.53Improved
add meta-optimization for agent-team retraining (ablation)MATAL · NYUtime cost: 4.5 -> 2Improved
add meta-optimization for agent-team retraining (ablation)MATAL · NYUMSE (mm): 23.68 -> 23.74Hurt

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