用概率跳跃扩散模型高效识别未知动作，提升视觉语言模型的探索效率。
A Probabilistic Jump-Diffusion Framework for Open-World Egocentric Activity Recognition
- 基于跳扩散机制的残差搜索框架，融合常识先验与视觉语言模型反馈。
- 在多个开放度级别（L0-L3）上实现领先性能，尤其在复杂搜索空间中表现优异。
- 适合研究开放世界动作识别、视觉语言模型应用的科研人员参考。
由于其无约束特性，开放世界第一人称动作识别面临根本性挑战，要求模型从广阔且部分可观测的搜索空间中推断未见动作。我们提出ProbRes，一种基于跳扩散的概率残差搜索框架，通过平衡先验引导的探索与似然驱动的利用，高效导航该空间。方法整合结构化常识先验构建语义连贯的搜索空间，利用视觉语言模型（VLMs）自适应精炼预测，并采用随机搜索机制定位高似然动作标签，同时避免穷举式搜索。我们在多个开放度级别（L0--L3）上系统评估了ProbRes，证明其对搜索空间复杂性增长具有强适应性。不仅在基准数据集（GTEA Gaze、GTEA Gaze+、EPIC-Kitchens、Charades-Ego）上达到最先进性能，还建立了开放世界识别的清晰分类体系，阐明了第一人称动作理解所需的关键挑战与方法进展。
原文摘要 · Abstract (English)
Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially observed search space. We introduce ProbRes, a Probabilistic Residual search framework based on jump-diffusion that efficiently navigates this space by balancing prior-guided exploration with likelihood-driven exploitation. Our approach integrates structured commonsense priors to construct a semantically coherent search space, adaptively refines predictions using Vision-Language Models (VLMs) and employs a stochastic search mechanism to locate high-likelihood activity labels while minimizing exhaustive enumeration efficiently. We systematically evaluate ProbRes across multiple openness levels (L0--L3), demonstrating its adaptability to increasing search space complexity. In addition to achieving state-of-the-art performance on benchmark datasets (GTEA Gaze, GTEA Gaze+, EPIC-Kitchens, and Charades-Ego), we establish a clear taxonomy for open-world recognition, delineating the challenges and methodological advancements necessary for egocentric activity understanding.
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。