Pith Number

pith:K3IB4553

pith:2026:K3IB4553GAUV4KCCJNRQRZXZZP

not attested not anchored not stored refs resolved

Neural Video Compression with Domain Transfer

Haofeng Wang, Qi Zhang, Rongqun Lin, Siwei Ma, Tiange Zhang, Xiandong Meng, Xing Tian

Neural video codecs can close most of their training-test performance gap by adapting only the latent code at inference time.

arxiv:2605.13476 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{K3IB4553GAUV4KCCJNRQRZXZZP}

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

DCVC-DT achieves up to 6.21% bitrate savings over the baseline DCVC-DC, while significantly enhancing generalization to unseen testing data and alleviating error propagation.

C2weakest assumption

The lightweight online domain transfer mechanism can reliably bridge the domain gap between training and test distributions by adapting only the latent representation without any change to encoder or decoder parameters.

C3one line summary

DCVC-DT reports up to 6.21% bitrate savings over DCVC-DC by dynamically adapting encoded latents and adjusting per-frame RD trade-offs during inference.

References

44 extracted · 44 resolved · 0 Pith anchors

[1] Neural video compression with diverse contexts, 2023

[2] Vqnerv: Vector quantization neural representation for video compression, 2024

[3] Efvc: Error-propagation-free neural video coding with reversible transform, 2025

[4] Bi-directional deep contextual video compression, 2025

[5] L-lbvc: Long- term motion estimation and prediction for learned bi-directional video compression, 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:41.452135Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

56d01e77bb30295e28424b6308e6f9cbdbf58c4ba5b973993071bc1342ca40fa

Aliases

arxiv: 2605.13476 · arxiv_version: 2605.13476v1 · doi: 10.48550/arxiv.2605.13476 · pith_short_12: K3IB4553GAUV · pith_short_16: K3IB4553GAUV4KCC · pith_short_8: K3IB4553

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/K3IB4553GAUV4KCCJNRQRZXZZP \
  | 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: 56d01e77bb30295e28424b6308e6f9cbdbf58c4ba5b973993071bc1342ca40fa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "851307165de857578c471343fd61950d60f545d2e6055f7cf53430683e4bb240",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T13:02:40Z",
    "title_canon_sha256": "be4397ba06beb7600a2cf884aac7afde4e378e904d622268dbfd1f8accb9e724"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13476",
    "kind": "arxiv",
    "version": 1
  }
}