PulseAugur
中
实时 07:41:40
English(EN) Gaze Target Estimation Anywhere with Concepts

新型可提示注视估计模型集成主体定位

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员推出了一种新颖的端到端方法——可提示注视目标估计（PGE），用于分析图像中的人类注视。与依赖多阶段流水线和显式输入的先前方法不同，PGE 使用自然语言或视觉提示来识别主体并预测注视目标。新推出的 GazeAnywhere 模型专为 PGE 构建，集成了主体定位和注视估计，在基准测试中取得了最先进的成果，并展示了其在临床应用中的潜力。此外，还发布了一个包含 120,000 个带提示注释的图像对的数据集 Gaze-Co，以支持这项任务。 AI

影响 这种新的注视估计方法可以改善人机交互，并在临床研究等领域实现更复杂的分析。

排序理由 该集群描述了一篇关于计算机视觉领域新任务、新模型和新数据集的最新研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新型可提示注视估计模型集成主体定位

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇关于计算机视觉领域新任务、新模型和新数据集的最新研究论文。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product
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
58 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Xu Cao, Houze Yang, Vipin Gunda, Zhongyi Zhou, Tianyu Xu, Adarsh Kowdle, Inki Kim, James M. Rehg ·

    Concepts enables gaze target estimation anywhere

    arXiv:2608.11367v1 Announce Type: cross 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, …

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Concepts enables gaze target estimation anywhere

    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.…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    Concepts Enables Gaze Target Estimation Anywhere

    A new promptable paradigm integrates subject localization and gaze estimation into an end-to-end transformer model that uses text or visual prompts to identify subjects and predict gaze targets without multi-stage pipelines.

相关实体

相关话题