Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Referring-expression pipeline from KITTI labels v1.0.0

Use this resource to generate referring-expression annotations from images and KITTI labels

New

  • 524 downloads
  • 187 likes
  • 150 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install referring-expression-annotation-pipeline

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets up the VLM server, configures the four steps (per-object descriptions, scene captions, grouped expressions tied to boxes, optional verification), then runs a pilot. You get per-image annotations in the image_referring_expression format.

Mostly picked by

Updated November 2, 2026

Card for the “Referring-expression pipeline from KITTI labels” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/configuration.md: pipeline settings
  • references/vllm_server.md: vLLM server
  • SKILL.md: steps and outputs

Good fit for

  • You have images with KITTI labels and want referring expressions
  • You annotate street scenes for a grounding dataset

Not for

    Tags

    • referring expressions
    • KITTI
    • annotation
    • VLM

    About

    You say

    “Generate referring expressions for my street scenes from the KITTI labels.”

    Card for the “Referring-expression pipeline from KITTI labels” skill

    Skill published by nvidia under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to generate referring-expression annotations from images and KITTI labels
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.4 KB
    • config/skillspector-baseline.yaml0.8 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/configuration.md12.9 KB
    • references/skill_info.yaml1.5 KB
    • references/vllm_server.md6.9 KB
    • skill-card.md4.8 KB
    • SKILL.md10.3 KB
    • skill.oms.sig5.4 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-generate-referring-expressions
    Licence
    Apache-2.0

    Notice

    « tao-generate-referring-expressions » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.