arXiv 2310.172902023-10-26cs.CV

RIO：面向开放环境中意图导向物体推理的基准

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network Technology（北京先进信息科学与网络技术重点实验室）；Wuhan University（武汉大学）；JD Explore Academy（京东探索研究院）；Sun Yat-sen University（中山大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；University of Electronic Science and Technology of China（电子科技大学）；Peng Cheng Laboratory（鹏城实验室）

Mengxue Qu, Yu Wu, Wu Liu, Xiaodan Liang, Jingkuan Song, Yao Zhao, Yunchao Wei

备注：: NeurIPS 2023 D&B accepted. See our project page for more details: https://reasonio.github.io/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出RIO基准数据集，包含40,214张图像和130,585个意图-物体对，以自然句子描述意图并与场景上下文关联，用于评估模型在开放环境中推理意图导向物体的能力。

摘要：

意图导向物体检测旨在根据特定意图或需求检测所需物体。例如，当我们想要“躺下休息”时，我们会本能地寻找一个能满足需求的选择，如“床”或“沙发”。该领域以往的工作要么受限于意图描述的数量，要么受限于可用于意图物体的可供性词汇。这些限制使得在开放环境中有效处理意图变得困难。为促进该研究，我们构建了一个名为Reasoning Intention-Oriented Objects（RIO）的综合数据集。具体而言，RIO专门设计用于纳入多样化的真实世界场景和广泛的物体类别。它具备以下关键特征：1）RIO中的意图描述以自然句子的形式表示，而非单纯的单词或动词短语，使其更具实用性和意义；2）意图描述与场景上下文相关，从而能够涵盖与物体相关的更广泛的潜在功能；3）该数据集共包含40,214张图像和130,585个意图-物体对。借助所提出的RIO，我们评估了部分现有模型在开放环境中推理意图导向物体的能力。

英文摘要：

Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO). In particular, RIO is specifically designed to incorporate diverse real-world scenarios and a wide range of object categories. It offers the following key features: 1) intention descriptions in RIO are represented as natural sentences rather than a mere word or verb phrase, making them more practical and meaningful; 2) the intention descriptions are contextually relevant to the scene, enabling a broader range of potential functionalities associated with the objects; 3) the dataset comprises a total of 40,214 images and 130,585 intention-object pairs. With the proposed RIO, we evaluate the ability of some existing models to reason intention-oriented objects in open environments.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。