English(EN) THG-Omni: Traceable Human-Centric Graph Supervision for Video Reasoning

新的THG-Omni框架通过图监督提升AI视频推理能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员推出THG-Omni，一个旨在增强全模态AI模型视频推理能力的新型框架。该系统采用以人为中心的图监督方法，将来自Segment Anything Model的参与者轨迹与Qwen3-VL的时间注解相结合。通过构建基于语义声明的训练问题，并与视频和音频证据进行验证，THG-Omni教会模型解释结构化视频数据，包括参与者属性、动作和交互。在IntentBench和NExT-QA等基准测试上的实验表明，推理准确性显著提高，尤其是在社会推理、情感理解和欺骗感知等领域。 AI

影响通过将推理与可识别的参与者和事件联系起来，增强了AI理解和解释复杂视频内容的能力。

排序理由该集群包含一篇关于AI视频推理新框架的学术论文。[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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇关于AI视频推理新框架的学术论文。[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) · Jisheng Dang, Kai Wei, Ronghao Lin, Bimei Wang, Hong Peng, Wei-Shi Zheng, Bin Hu, Qi Tian, Tat-Seng Chua · 2026-11-06 05:00

THG-Omni: 可追踪以人为本的图监督用于视频推理

arXiv:2611.07836v1 Announce Type: cross Abstract: Omni-modal models can answer questions about video, but their predictions rarely show which participant, event, or interval supports an answer. Moreover, answer-level supervision alone does not teach a model to interpret structure…

本文如何被排名

报道来源 [1]

THG-Omni: 可追踪以人为本的图监督用于视频推理

相关实体

相关话题