pith:LHFLFPOV
RELO: Reinforcement Learning to Localize for Visual Object Tracking
RELO learns a reinforcement learning policy to localize targets in visual tracking by maximizing IoU and AUC rewards instead of relying on handcrafted spatial priors.
arxiv:2605.07379 v2 · 2026-05-08 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LHFLFPOVLOCCYTTPKQLAKQT2U2}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
RELO replaces handcrafted spatial priors with a localization policy learned over spatial positions via reinforcement learning, with rewards combining frame-level IoU and sequence-level AUC, attaining 57.5% AUC on LaSOText without template updates.
That a policy trained with combined IoU and AUC rewards will generalize across diverse tracking scenarios and benchmarks without requiring template updates or extensive hyperparameter tuning.
RELO replaces handcrafted spatial priors with a reinforcement learning policy for target localization in visual tracking and reports 57.5% AUC on LaSOText without template updates.
Formal links
Receipt and verification
| First computed | 2026-05-20T01:05:15.747775Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
59cab2bdd55b842c4e6f541605427aa681fe387743014d38214f25662c9f923c
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LHFLFPOVLOCCYTTPKQLAKQT2U2 \
| 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: 59cab2bdd55b842c4e6f541605427aa681fe387743014d38214f25662c9f923c
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e242862be18eb9f789b5eb46325ddf33737f82ed5a93c88d1653deb0033fdb0d",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-08T07:34:29Z",
"title_canon_sha256": "36e429072431a8e3c3669e4e2dec412c54b56d855cbf16207eb3c8c59ed4207c"
},
"schema_version": "1.0",
"source": {
"id": "2605.07379",
"kind": "arxiv",
"version": 2
}
}