pith:M2PM7S4S
SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels
Structured semantic role label captions let CLIP adapt to video tasks with only 23k pairs.
arxiv:2401.07669 v3 · 2024-01-15 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{M2PM7S4SZ75Z3XDBH4JQTVQTT6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
simple contrastive finetuning on a mere 23k video-caption pairs is adequate to learn powerful, transferable representations applicable across a diverse range of video understanding tasks that require varying levels of perceptual granularity
The assumption that rule-based captions generated from SRL annotations supply a sufficiently rich and holistic learning signal compared with the sparse narrations found in large-scale video datasets.
SRL-CLIP uses rule-based captions derived from semantic role labels to adapt CLIP via contrastive fine-tuning on 23k pairs, matching or exceeding larger models trained on far more data across video tasks.
Cited by
Receipt and verification
| First computed | 2026-05-27T01:04:46.725046Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/M2PM7S4SZ75Z3XDBH4JQTVQTT6 \
| 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: 669ecfcb92cffb9ddc613f1309d6139fafb6b2dda89137fe5bc30b948fe25d20
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "fcf55014ddd655a0fdba291419de19c02fc86c757bbc8ee9eb96c0c5f3f697a1",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2024-01-15T13:27:34Z",
"title_canon_sha256": "cc1a6fb1c5ac00d0faf988973ce6182c2bea4053866cde41ec058787425ec585"
},
"schema_version": "1.0",
"source": {
"id": "2401.07669",
"kind": "arxiv",
"version": 3
}
}