面向第一视角长期动作预测的意图引导认知推理方法
Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation
AI总结：
针对第一视角长期动作预测现有方法的三类局限，提出两阶段框架INSIGHT，融合手-物交互特征、动名语义依赖与意图引导的认知推理，在多个基准上取得SOTA性能。
摘要：
第一视角视频的长期动作预测对人机交互、辅助技术等应用至关重要，预测用户意图可实现主动式、情境感知的AI辅助。但现有方法存在三大核心局限：一是未充分利用手-物交互的细粒度视觉线索，二是忽略动词与名词间的语义依赖关系，三是缺乏显式认知推理，限制了泛化性与长期预测能力。为解决上述问题，我们提出面向第一视角动作预测的统一两阶段框架INSIGHT。第一阶段中，INSIGHT重点从手-物交互区域提取语义丰富的特征，并通过动词-名词共现矩阵增强动作表征；第二阶段引入基于强化学习的模块，通过“视觉感知（思考）->意图推断（推理）->动作预测（作答）”的结构化流程模拟显式认知推理。在Ego4D、EPIC-Kitchens-55、EGTEA Gaze+基准数据集上开展的大量实验表明，INSIGHT取得了当前最优性能，验证了其有效性与强泛化能力。
英文摘要：
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However, existing approaches suffer from three key limitations: 1) underutilization of fine-grained visual cues from hand-object interactions, 2) neglect of semantic dependencies between verbs and nouns, and 3) lack of explicit cognitive reasoning, limiting generalization and long-term forecasting ability. To overcome these challenges, we propose INSIGHT, a unified two-stage framework for egocentric action anticipation. In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions and enhances action representations using a verb-noun co-occurrence matrix. In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning through a structured process: visual perception (think) -> intention inference (reason) -> action anticipation (answer). Extensive experiments on Ego4D, EPIC-Kitchens-55, and EGTEA Gaze+ benchmarks show that INSIGHT achieves state-of-the-art performance, demonstrating its effectiveness and strong generalization capability.
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。
