Pith Number

pith:Q56OF553

pith:2026:Q56OF553UU77N3YCFSDP7KWWFD

not attested not anchored not stored refs resolved

TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval

Ben Chen, Chenyi Lei, Huangyu Dai, Lingtao Mao, Wenwu Ou, Xinyu Sun, Zexin Zheng, Zihan Liang

Item text can guide the creation of target-focused representations from full images to match cropped visual queries without object detection.

arxiv:2605.18434 v1 · 2026-05-18 · cs.IR · 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{Q56OF553UU77N3YCFSDP7KWWFD}

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

TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings.

C2weakest assumption

That item text descriptions provide reliable semantic guidance sufficient to produce target-focused representations implicitly, without explicit localization or detection, and that the dual distillation objectives will preserve both spatial consistency and similarity structure across varied item layouts.

C3one line summary

TIGER-FG proposes text-guided implicit fine-grained grounding with dual distillation to address modality and granularity asymmetries in image-to-multimodal e-commerce retrieval, reporting Recall@1 gains of 6.1 and 34.4 points on two new benchmarks.

References

19 extracted · 19 resolved · 7 Pith anchors

[1] End-to-end object detection with transformers 2020

[2] Ben Chen, Linbo Jin, Xinxin Wang, Dehong Gao, Wen Jiang, and Wei Ning 2023

[3] Category-oriented representation learning for image to multi-modal retrieval.arXiv preprint arXiv:2305.03972,

[4] Vision Transformers Need Registers · arXiv:2309.16588

[6] The Faiss library · arXiv:2401.08281

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:06:00.782578Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

877ce2f7bba53ff6ef022c86ffaad628c125d243a197d64e833c17f6b93486b6

Aliases

arxiv: 2605.18434 · arxiv_version: 2605.18434v1 · doi: 10.48550/arxiv.2605.18434 · pith_short_12: Q56OF553UU77 · pith_short_16: Q56OF553UU77N3YC · pith_short_8: Q56OF553

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/Q56OF553UU77N3YCFSDP7KWWFD \
  | 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: 877ce2f7bba53ff6ef022c86ffaad628c125d243a197d64e833c17f6b93486b6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b270e89a8c91c34614a44460061563da9fe0983b184e0323ab070784f01508f8",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-18T14:07:20Z",
    "title_canon_sha256": "34cf35ad5b5106e6537cd79bb700be08f9a01ee018e2daa7d09ff27c569f2527"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.18434",
    "kind": "arxiv",
    "version": 1
  }
}