AI Paper Atlas

Research map / 3D vision / Human pose estimation

JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery

Jiahao Li, Zongxin Yang, Xiaohan Wang, Jianxin Ma, Chang Zhou, Yi Yang

ICCV 2023 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 32 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

add joint-to-joint contrastive loss · 3DPW-OC · MPJPE (mm): 77.0 -> 76.6 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 feature sampling to flattened 2D features (ablation)JOTR · 3DPW-OCMPJPE (mm): 77.8 -> 77.0Improved
use flattened 2D features instead of joint-sampled 2D features (no 3D) (ablation)JOTR · 3DPW-OCMPJPE (mm): 78.3 -> 77.8Improved
use flattened 2D features with 3D sampling instead of sampled 2D with 3D sampling (ablation)JOTR · 3DPW-OCMPJPE (mm): 77.4 -> 77.0Improved
add 3D features on top of flattened 2D features (ablation)JOTR · 3DPW-OCPA-MPJPE (mm): 53.2 -> 53.6Hurt
add successive refining layers (coarse-to-fine) instead of initial 2D regression (ablation)JOTR · 3DPW-OCMPJPE (mm): 276.5 -> 77.0Improved
decouple SMPL query tokens from joint query tokens (ablation)JOTR · 3DPW-OCMPJPE (mm): 79.8 -> 77.0Improved
add joint-to-non-joint contrastive loss (ablation)JOTR · 3DPW-OCMPJPE (mm): 77.0 -> 75.9Improved
add joint-to-joint contrastive loss (ablation)JOTR · 3DPW-OCMPJPE (mm): 77.0 -> 76.6Improved
combine both contrastive losses (ablation)JOTR · 3DPW-OCMPJPE (mm): 77.0 -> 75.7Improved
use JOTR instead of 3DCrowdNetJOTR · 3DPW testPA-MPJPE (mm): 51.2 -> 48.7Improved

Later papers that compared with this method

1 later accepted paper reports JOTR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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