提出新模型与评测体系，显著提升手物交互检测精度。
Improving and Evaluating Hand-Object Interaction Detection
- 基于Co-DETR改进框架，融合手物及物物交互建模。
- 在多个数据集上实现超过20个百分点的准确率提升。
- 提供完整评测套件和预训练模型，适合研究者直接使用。
理解手与物体之间的交互（包括直接接触和通过工具交互）是动作感知、三维重建和机器人任务的关键步骤。本文贡献包括：(1) HOI-DETR，一种新框架，在Co-DETR基础上引入手物交互与物物交互建模，达到当前最优性能；(2) 一套涵盖4个不同数据集的全面评测体系，包含基于HD-EPIC数据集构建的视频基准，以及对Hands23数据集的新标注；(3) 一个训练好的模型，在Hands23、HOIST、FineBio和HD-EPIC上均显著超越现有方法，尤其在Hands23和FineBio上实现超过20个百分点的mAP提升。消融实验验证了各组件的有效性。
原文摘要 · Abstract (English)
Understanding hands and the objects they interact with, both directly and through tools, is a key step for tasks ranging from action perception to 3D reconstruction and robotics. Our paper provides several contributions to the Hand-Object Interaction (HOI) understanding literature: (1) HOI-DETR, a new framework that introduces hand-object and object-object interactions to the Co-DETR architecture to produce a state-of-the-art method; (2) a comprehensive HOI evaluation suite of 4 diverse datasets, including a video benchmark derived from the HD-EPIC dataset and fresh annotations that improve the Hands23 benchmark and (3) a trained checkpoint that significantly improves the state of the art across Hands23, HOIST, FineBio, and HD-EPIC, including mAP gains of over 20 percentage points on Hands23 and FineBio. Our ablations confirm the contributions of each model component.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。