arXiv:2608.11367v1 Announce Type: new Abstract: Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage pipelines that require
ソーシャルアカウントでログイン
视线目标估计（Gaze Target Estimation）旨在从图像中判断画面内人物正在注视的目标位置或物体。这一任务在人际交互分析、注意力建模、辅助驾驶与智能监控等场景中具有实用价值。然而，论文摘要指出，现有方法普遍采用“脆弱的多阶段流水线”，通常需要先检测头部、估计头部姿态、再结合场景上下文推断注视点。这类方案对前置检测模块的误差敏感，且在目标类别多样、场景构成复杂的自然图像中泛化能力有限。
摘要中“in-the-wild”（自然场景）的表述强调了问题设定的开放性：不同于受控实验室环境或固定场景数据集，自然图像中的人物姿态、遮挡、光照与目标类别均高度可变。论文标题中的“Anywhere”也指向这一泛化诉求——视线估计不应局限于特定场景或预设目标类别。
从标题与摘要可推断，该工作的核心思路是将视线目标估计与“概念”（Concepts）关联起来。摘要原文在关键处截断，未完整披露方法细节，但“with Concepts”的表述暗示模型可能借助语义概念（如物体类别、场景元素或属性描述）来表征潜在的注视目标，而非依赖固定的检测框或坐标回归。
这一思路与近年视觉语言模型的发展方向相呼应。将视线目标视为可被语义概念描述的对象，有望让模型利用更丰富的先验知识进行推理，从而减少对特定检测器输出的依赖。不过，摘要未提供具体模型架构、训练数据规模或实验设置，相关技术细节需待全文公开后才能确认。
同日提交至 arXiv 的多篇计算机视觉论文反映了该领域对模型鲁棒性与泛化能力的共同关注。例如，CLEAR 针对长尾分布下的分类可靠性问题提出类别级专家聚合方法，SegPAR 研究语义分割中的稀疏黑盒攻击，GeoUniPR 则致力于跨模态地点识别中的几何一致性。这些工作虽然任务不同，但都涉及模型在复杂、非理想条件下的表现。视线目标估计同样面临此类挑战：自然场景中的类别不平衡、遮挡与跨场景差异，都可能削弱传统流水线的可靠性。
目前该论文仅以摘要形式公开，实验数据、对比基线及局限性讨论均未提供。读者可关注 arXiv 页面后续更新，以获取完整版本。
arXiv:2608.11367v1 Announce Type: new Abstract: Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage pipelines that require explicit inputs, like head bounding boxes and human pose, in order to identify the subject of gaze analysis. As a result, detection errors can cascade and lead to failure. Moreover, these prior works lack the flexibility of specifying the gaze analysis task via natural language prompting, an approach which has been shown to have significant benefits in convenience and scalability for other image analysis tasks. To overcome these limitations, we introduce the Promptable Gaze Target Estimation (PGE) task, a new end-to-end, concept-driven paradigm for gaze analysis. PGE conditions gaze prediction on flexible user text or visual prompts (e.g., "the boy in the red shirt" or "person in point [0.52, 0.48]") to identify a specific subject for gaze analysis. This approach integrates subject localization with gaze estimation, and eliminates the rigid dependency on intermediate analysis stages. We develop a scalable data engine to generate Gaze-Co (Gaze Estimation with Concepts), a dataset and benchmark of 120K high-quality, prompt-annotated image pairs. We also propose GazeAnywhere, the first model designed for PGE. GazeAnywhere uses a transformer-based detector to fuse features from frozen encoders and simultaneously solves subject localization, in/out-of-frame presence, and gaze target heatmap estimation. GazeAnywhere achieves state-of-the-art performance on multiple PGE benchmarks, setting a strong baseline for this new problem even on a difficult out-of-domain, real-world clinical dataset. GazeAnywhere is open-sourced in github.com/IrohXu/GazeAnywhere.