English(EN) Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences

新的神经符号图Transformer增强了人机意图识别能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了一种神经符号图Transformer（NSGT），旨在提高人机协作中的分层意图识别能力。这种新架构将人类推理图（HR-G）集成到其自注意力机制中，并使用可微分的一阶逻辑（FOL）损失来强制执行多层次意图的本体一致性。在源自NTU RGB+D 120的合成数据集上进行的评估表明，NSGT实现了91.65%的Top-1动作准确率，在使用FOL损失后提高到96.67%。该模型还展示了准确率和结构一致性之间的可调权衡，在保持稳健的动作准确率的同时，将本体矛盾减少了33%。 AI

影响增强了对人类意图的理解，以实现更复杂的人机协作。

排序理由详细介绍新模型架构及其评估的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新模型架构及其评估的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Farnaz Soleimani (LISSI), Abdelghani Chibani (LISSI), Yacine Amirat (LISSI), Ghazaleh Khodabandelou (LISSI) · 2026-10-15 04:00

用于多模态人类活动序列分层意图识别的神经符号图Transformer

arXiv:2610.18176v1 Announce Type: new Abstract: Proactive human-robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions governing human behavior. Current deep learning approaches predominantly focus on fl…

本文如何被排名

报道来源 [1]

用于多模态人类活动序列分层意图识别的神经符号图Transformer

相关实体

相关话题