Pith Number

pith:Z4RTWN4S

pith:2026:Z4RTWN4SKCJN26ECS6MKXSNRXV

not attested not anchored not stored refs resolved

Audio-Image Cross-Modal Retrieval with Onomatopoeic Images

Keisuke Imoto, Takao Tsuchiya, Yamato Kojima

Training modality-specific projection heads on paired onomatopoeic data enables bidirectional audio-image retrieval.

arxiv:2605.17509 v1 · 2026-05-17 · eess.AS

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Z4RTWN4SKCJN26ECS6MKXSNRXV}

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

Experimental results show that the proposed method substantially outperforms a zero-shot baseline using pretrained CLIP and CLAP embeddings.

C2weakest assumption

That training modality-specific projection heads on the MIAO dataset will produce embeddings that generalize to unseen onomatopoeic images and sounds outside the 50 classes.

C3one line summary

Introduces a cross-modal retrieval framework using modality-specific projection heads on CLIP and CLAP embeddings together with the new MIAO dataset of 50 sound event classes for onomatopoeic image-sound pairs.

References

12 extracted · 12 resolved · 0 Pith anchors

[1] Learning transferable visual models from natural languag e supervision, 2021

[2] Large-scale contrastive language-audio pretraining wit h feature fusion and keyword-to-caption augmentation, 2023

[3] AudioCLIP: Ex tending clip to image, text and audio, 2022

[4] Wav2 CLIP: Learning robust audio representations from clip, 2022

[5] ImageBind: One embedding space to bind them all, 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:42.944995Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cf233b37925092dd78829798abc9b1bd74ca0dd34d06953424ba0c24ced91fb9

Aliases

arxiv: 2605.17509 · arxiv_version: 2605.17509v1 · doi: 10.48550/arxiv.2605.17509 · pith_short_12: Z4RTWN4SKCJN · pith_short_16: Z4RTWN4SKCJN26EC · pith_short_8: Z4RTWN4S

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/Z4RTWN4SKCJN26ECS6MKXSNRXV \
  | 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: cf233b37925092dd78829798abc9b1bd74ca0dd34d06953424ba0c24ced91fb9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3ef481c270b01cd2455d38198e64fd27c6c64267088b7ad7bf12dc5f0eb6ce05",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-05-17T15:42:41Z",
    "title_canon_sha256": "37c063f8b2fde2756fcdf832e1d3b217059e05c3df71d153640f37b91a34bc3b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17509",
    "kind": "arxiv",
    "version": 1
  }
}