Pith Number

pith:LNV5F5DA

pith:2026:LNV5F5DANXWAYSN25XW4MAGDVZ

not attested not anchored not stored refs resolved

Rethinking Graph Convolution for 2D-to-3D Hand Pose Lifting

Chanyoung Kim, Donghyun Kim, Dong-Hyun Sim, Seong Jae Hwang, Youngjoong Kwon

Adaptive attention outperforms fixed graph convolution for lifting 2D hand poses to 3D.

arxiv:2605.13604 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{LNV5F5DANXWAYSN25XW4MAGDVZ}

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

These results suggest that, for hand pose lifting, adaptive spatial attention is a more effective inductive bias than fixed graph convolution.

C2weakest assumption

The assumption that parameter-matched ablations on the FPHA benchmark alone establish the general superiority of attention over GCNs across hand pose lifting tasks and datasets.

C3one line summary

Self-attention with input-dependent aggregation and soft graph-distance priors outperforms fixed graph convolutions for 2D-to-3D hand pose estimation on FPHA.

References

14 extracted · 14 resolved · 0 Pith anchors

[1] First-person hand action bench- mark with rgb-d videos and 3d hand pose annotations 2018

[2] Kipf and Max Welling 2017

[3] Gtignet: Global topology interaction graphormer network for 3d hand pose estimation.Neural Networks, 185:107221, 2025 2025

[4] Decoupled weight de- cay regularization 2019

[5] Assemblyhands: Towards egocen- tric activity understanding via 3d hand pose estimation

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:22.887004Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5b6bd2f4606dec0c49baededc600c3ae5bdc24a7cc1b522340ea1c10710851e3

Aliases

arxiv: 2605.13604 · arxiv_version: 2605.13604v1 · doi: 10.48550/arxiv.2605.13604 · pith_short_12: LNV5F5DANXWA · pith_short_16: LNV5F5DANXWAYSN2 · pith_short_8: LNV5F5DA

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/LNV5F5DANXWAYSN25XW4MAGDVZ \
  | 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: 5b6bd2f4606dec0c49baededc600c3ae5bdc24a7cc1b522340ea1c10710851e3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9a54a6abbe50aa07d7731aa3d34baf44e714d139388e186bec5500732c3ac533",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T14:39:24Z",
    "title_canon_sha256": "13a4a3dbc6627a86e2f0cfe61121c1938268ef673b5c7b6320f01d0695c7708c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13604",
    "kind": "arxiv",
    "version": 1
  }
}