English(EN) Video2Reaction: Training Foundation Video Models to Predict Audience Reaction

新数据集训练人工智能预测视频中的观众情绪反应

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了Video2Reaction，这是一个旨在训练视频基础模型以预测观众情绪反应的新数据集。该数据集将短视频片段映射到通过社交媒体评论表达的观众反应，将情绪建模为分布以捕捉主观性。通过对LLaVA-NeXT-Video-7B等微调的视觉语言模型（VLMs）进行基准测试，研究表明在Video2Reaction上训练的VLMs能够有效预测主导反应，并将此能力迁移到其他与情绪相关的数据集上，取得了与在完整数据集上训练的模型相当的性能。 AI

影响该数据集可以使人工智能系统更好地理解和响应视频内容中的人类情绪线索。

排序理由该集群描述了一篇介绍新数据集和基准测试模型的新学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍新数据集和基准测试模型的新学术论文。[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, 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: 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.CV TIER_1 English(EN) · Sidong Zhang, Trang Nguyen, Shiv Shankar, Gauri Jagatap, Deepak Chandran, Andrea Fanelli, Madalina Fiterau · 2026-09-03 04:00

Video2Reaction：训练基础视频模型以预测观众反应

arXiv:2609.01816v1 Announce Type: new Abstract: We introduce Video2Reaction, a multimodal dataset that maps short movie segments to the induced emotional reactions of viewers in the wild, as expressed through social media comments. Video2Reaction captures the natural diversity of…

本文如何被排名

报道来源 [1]

Video2Reaction：训练基础视频模型以预测观众反应

相关实体

相关话题