pith:MEYMV52W
Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search
A two-stage cascade filters candidates by skeletal pose then verifies semantics with a multi-agent squad to bridge the gap where different actions share similar structures.
arxiv:2604.23282 v2 · 2026-04-25 · cs.CV · cs.MM
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MEYMV52WB5ZJLJWB2PGHVWAO7G}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval... and (2) Detective Squad Interaction... Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning.
That skeletal geometry provides a sufficiently reliable coarse filter for semantically distinct actions and that the multi-agent LLM verification stage can resolve remaining ambiguities accurately without introducing new errors or prohibitive latency.
SSDC is a two-stage cascade that first filters by skeletal similarity then applies a multi-agent LLM squad for semantic verification, achieving SOTA on the PAB benchmark for text-based person anomaly search.
Receipt and verification
| First computed | 2026-05-28T01:05:12.419147Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6130caf7560f7295a6c1d3cc7ad80ef9aa3abc017d46ef2eb4340e59887bee9a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G \
| 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: 6130caf7560f7295a6c1d3cc7ad80ef9aa3abc017d46ef2eb4340e59887bee9a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "19158958884ff097ad978dc1cc87b02c6c62db770879be4303c007a6def39835",
"cross_cats_sorted": [
"cs.MM"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-25T12:53:15Z",
"title_canon_sha256": "1635911ff6033b54975f20a72325427826b0434d0bf5343535c9457f432b9507"
},
"schema_version": "1.0",
"source": {
"id": "2604.23282",
"kind": "arxiv",
"version": 2
}
}