AI Paper Atlas

Research map / 3D vision / Human pose estimation

BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations

Lucas Martini, Alexander Lappe, Anna Bognár, Rufin Vogels, Martin A. Giese

ICLR 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 2 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 3D-Rot pose vectors to ResNet50 features (ablation)ResNet50 · BigMaQ500mAP: 34.3 -> 44.0Improved
add pose vectors to ViT-base-cls features (ablation)ViT-base-cls · BigMaQ500mAP: 32.9 -> 44.0Improved
add pose vectors to TimeSformer features (ablation)TimeSformer · BigMaQ500mAP: 31.9 -> 42.6Improved
add pose vectors to VideoPrism-base features (ablation)VideoPrism-base · BigMaQ500mAP: 38.3 -> 43.8Improved
add pose vectors to DINOv2-base (patch tokens) features (ablation)DINOv2-base · BigMaQ500mAP: 40.4 -> 41.4No clear effect
pose-only stream versus best visual-only model (ablation)pose-only · BigMaQ500mAP: 43.5 vs 40.4 (DINOv2-base)Improved
use 3D-Rot joint rotations instead of 2D keypoints (ablation)pose representation · BigMaQ500 pose-onlymAP: 35.6 -> 43.5Improved
use 3D-Rot instead of 3D keypoints in pose-only stream (ablation)pose representation · BigMaQ500 pose-onlymAP: 40.8 -> 43.5Improved
use 3D-Rot instead of 3D keypoints combined with VideoPrism (ablation)VideoPrism-base · BigMaQ500mAP: 34.0 -> 43.8Improved
subject-specific mesh with temporal loss versus MAMMAL templateBigMaQ tracking · single-subject actionsIoU: 0.714 -> 0.844Improved
subject-specific mesh versus MAMMAL on 3D alignmentBigMaQ tracking · single-subject actionsMPJPE (mm): 31.661 -> 26.907Improved

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