(CA) MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?

MARS框架利用多模态大语言模型改进文本-视频检索

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

研究人员开发了MARS，一个旨在通过利用多模态大语言模型的多个层和自适应表示槽来增强文本-视频检索的新型框架。与通常将各种线索压缩到单个向量中的现有方法不同，MARS通过组合来自不同解码器层的隐藏状态来构建多个槽。这种方法允许更细致地比较文本和视频元素，实验证明在多个基准测试中取得了最先进的结果。该框架进一步纳入了一个硬负例感知的槽专业化目标，以改进判别性匹配线索的捕获，从而在直接基于相似度的检索和重排方面都取得了显著的收益。 AI

影响通过实现对多模态数据更细粒度的分析，提高了文本-视频检索系统的精度。

排序理由该集群包含一篇关于文本-视频检索新方法的学术论文。[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: 19 / 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文本-视频检索新方法的学术论文。[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.CV TIER_1 (CA) · Uicheol Jung, Juyoung Hong, Geuntaek Lim, Yukyung Choi · 2026-09-03 04:00

MARS：多模态大语言模型中隐藏着用于文本-视频检索的检索信号是什么？

arXiv:2609.02565v1 Announce Type: new Abstract: Text-video retrieval requires representations that can distinguish videos with similar scenes, actions, and temporal patterns. Recent multimodal large language models have been adapted as embedding models, but they often represent e…

本文如何被排名

报道来源 [1]

MARS：多模态大语言模型中隐藏着用于文本-视频检索的检索信号是什么？

相关实体

相关话题