论文/arXiv 2608.18317·2 个月前

可复现的多模态可供性预测

针对可供性预测难以公平比较的问题，提出 Affordance Sheet 文档，用于真实场景中的可复现基准与评估。

AI 整理

• 数据与采集
• 端侧部署
• 评测与安全

原文链接：Reproducible Multimodal Affordance Prediction（arXiv 2608.18317 · 发布日期：2026-08-18）

Reproducible Multimodal Affordance Prediction

针对可供性预测难以公平比较的问题，提出 Affordance Sheet 文档，用于真实场景中的可复现基准与评估。

核心要点

• 多模态可供性预测需识别智能体可对目标物体执行的潜在动作。
• 现有方法因问题定义、标注、实验协议和部署信息不一致而难以比较。
• Affordance Sheet 记录输入模态、模型架构、训练信息、数据集和实验协议。
• 该文档旨在支持可复现基准和可靠评估，涵盖新条件泛化与人类安全。

英文摘要 (Abstract)

Affordance prediction is the identification of potential actions an agent can perform on a target object from multimodal inputs. Affordance prediction methods are difficult to evaluate and compare due to heterogeneous problem formulations, inconsistent dataset annotations, incomplete reporting of experimental protocols, and limited information about deployment conditions. These limitations challenge fair benchmarking and performance comparison. To promote transparency, we propose the Affordance Sheet, a documentation detailing task formulation with its input modalities, model architectures and training information, datasets, and experimental protocols. Affordance Sheets enable reproducible benchmarking and reliable evaluation of affordance models for real-world scenarios, including generalisation to novel conditions and human safety.

作者：Tommaso Apicella, Alessio Xompero, Andrea Cavallaro

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2608.18317：Reproducible Multimodal Affordance Prediction访问 2026-10-21