Pith Number

pith:AZAAKXHV

pith:2026:AZAAKXHVWEADWVXBSTBVNPTHFY

not attested not anchored not stored refs resolved

GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation

Jiyong Rao, Shengjie Zhao, Yu Wang

A generative model infers soft keypoint adjacency matrices from support images to enable category-agnostic pose estimation without predefined skeletons.

arxiv:2605.13151 v1 · 2026-05-13 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{AZAAKXHVWEADWVXBSTBVNPTHFY}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our framework consists of two principal components: an iterative Structure-aware Variational Autoencoder (i-SVAE) and a Compositional Graph Transfer (CGT) module. The former infers soft, instance-specific adjacency matrices from support features through variational inference... This structure-aware design facilitates effective message propagation among keypoints and promotes semantic alignment across object categories with diverse keypoint topologies.

C2weakest assumption

That soft adjacency matrices inferred via variational inference from support features alone can reliably capture instance-specific structural cues critical for accurate pixel-level localization without additional textual descriptions or predefined skeletons.

C3one line summary

GenCape uses an iterative structure-aware variational autoencoder and compositional graph transfer to infer keypoint relationships from image support inputs, achieving gains over graph baselines on MP-100 under 1- and 5-shot settings.

References

38 extracted · 38 resolved · 0 Pith anchors

[1] European conference on computer vision , pages= 2022

[2] European Conference on Computer Vision , pages= 2024

[3] Conference on Computer Vision and Pattern Recognition , pages=

[4] Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao , booktitle=

[5] Conference on Computer Vision and Pattern Recognition , pages=

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:08:57.122151Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0640055cf5b1003b56e194c356be672e2254a9ab44199125806fe383286efe92

Aliases

arxiv: 2605.13151 · arxiv_version: 2605.13151v1 · doi: 10.48550/arxiv.2605.13151 · pith_short_12: AZAAKXHVWEAD · pith_short_16: AZAAKXHVWEADWVXB · pith_short_8: AZAAKXHV

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/AZAAKXHVWEADWVXBSTBVNPTHFY \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0640055cf5b1003b56e194c356be672e2254a9ab44199125806fe383286efe92

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "995ccf3a709ce75b2d3cd20d9dce2d9ca141c9394c25e400486df0a49320125d",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T08:17:20Z",
    "title_canon_sha256": "ec4022b7150bde6d6eb9fa4a7926e2315585ffd59dad15acb461113470368fa5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13151",
    "kind": "arxiv",
    "version": 1
  }
}