此语言仍有 24 条内容或界面任务待翻译;未完成部分显示中文原文。
Visual GroundingCategory Diagram
Content Correction

Visual Grounding

Model doubao-seed-2-1-pro-260915Large Models & Software Services
关键规格 1Provided by Supplierbbox 归一化坐标 1000×1000
关键规格 2Provided by Supplier 3D bbox 输出 9 参数
关键规格 3Provided by Supplier point 计数
关键规格 4Provided by Supplier polygon 文字定位
Reference unit priceRequest a Quote

Download DocumentsReference subtotal Request a Quote

价格与库存供选型参考,正式报价和交期请供方确认。

Specification Parameters

Basic Information

Model
doubao-seed-2-1-pro-260915
Key Parameters
bbox 归一化坐标 1000×1000, 3D bbox 输出 9 参数, point 计数, polygon 文字定位

资料下载

Comparison with Similar Products

Specifications本品 · doubao-seed-2-1-pro-260915kimi-k3.1-pro火山方舟模型 APIqwen-audio-3.1-asr-flashdoubao-seed-2.1-turbo
Main controller—————
NPU—————
Memory / VRAM—————
Reference unit priceRequest a QuoteRequest a QuoteRequest a QuoteRequest a QuoteRequest a Quote
Inventory—————

Product introduction

Visual Grounding is a visual understanding capability introduced in the Volcano Ark documentation: based on natural language task requirements, it locates the corresponding target in an image and returns coordinates. The model must possess both visual understanding and natural language understanding capabilities; compared with object detection, it adds natural language input, making the interaction more flexible. Coordinates are returned as ratio coordinates normalized to 1000×1000 and must be converted according to the actual image dimensions. It is suitable for scenarios such as object localization, multi-target detection, text position extraction, counting, and 3D box output; before use, you need to activate the Ark platform and obtain an API Key.

Sources 火山方舟

Compilation Notes 内容由 AI 根据公开资料整理;事实与推断分开呈现。

Content Correction

Product parameter comparison

Product Selection Assistant

让需求变成可修改的筛选条件

依据已录入参数生成条件,结果可查看和修改。帧率与性能需核对实测,不能仅凭算力数值保证。