Pith Number

pith:RTSTVKUJ

pith:2017:RTSTVKUJVERGA7RPLFCYBQDFHR

not attested not anchored not stored refs resolved

The 2017 DAVIS Challenge on Video Object Segmentation

Alex Sorkine-Hornung, Federico Perazzi, Jordi Pont-Tuset, Luc Van Gool, Pablo Arbel\'aez, Sergi Caelles

The 2017 DAVIS Challenge introduces a dataset, benchmark, and competition to advance video object segmentation.

arxiv:1704.00675 v3 · 2017-04-03 · 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{RTSTVKUJVERGA7RPLFCYBQDFHR}

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

We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation.

C2weakest assumption

The chosen videos and metrics sufficiently represent the diversity and difficulty of real-world video object segmentation scenarios.

C3one line summary

The 2017 DAVIS Challenge establishes a public dataset, evaluation metrics, and competition for video object segmentation.

References

17 extracted · 17 resolved · 0 Pith anchors

[1] ImageNet Large Scale Visual Recognition Challenge 2015

[2] The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results 2012

[3] A benchmark dataset and evaluation methodology for video object segmentation 2016

[4] Microsoft COCO: Common Objects in Context 2014

[5] One-shot video object segmentation 2017

Formal links

3 machine-checked theorem links

Cited by

49 papers in Pith

Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion

Geo-Align: Video Generation Alignment via Metric Geometry Reward

Understanding Deep Learning Techniques for Image Segmentation

Self-supervised Training of Proposal-based Segmentation via Background Prediction

Receipt and verification

First computed	2026-05-18T03:32:29.312678Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8ce53aaa89a922607e2f594580c0653c5f747735e02562a7c8de6acd1b6f0286

Aliases

arxiv: 1704.00675 · arxiv_version: 1704.00675v3 · doi: 10.48550/arxiv.1704.00675 · pith_short_12: RTSTVKUJVERG · pith_short_16: RTSTVKUJVERGA7RP · pith_short_8: RTSTVKUJ

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/RTSTVKUJVERGA7RPLFCYBQDFHR \
  | 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: 8ce53aaa89a922607e2f594580c0653c5f747735e02562a7c8de6acd1b6f0286

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5d12ef75ea0da2af8b1acf5ce71b23d061bbcd2f5f62f5b2ae236acfb544184f",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2017-04-03T16:44:46Z",
    "title_canon_sha256": "ca41308a33c013addfbb5d5e358611e8da14cc20d7f5f47a53f1852bbf7fdb19"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1704.00675",
    "kind": "arxiv",
    "version": 3
  }
}