English(EN) VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval

VEDJE编码器通过压缩特征提升视频-文本检索性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员开发了VEDJE，一种新颖的视频高效判别联合编码器（Video-Efficient Discriminative Joint Encoder），旨在提高视频-文本检索的可扩展性和效率。该方法将视频特征压缩成可重用缓存，显著降低了检索时的计算成本。通过在训练期间引入特征变化预测信号，VEDJE在不增加查询时工作量的情况下提高了检索准确性。该系统在MSR-VTT、MSVD、DiDeMo和ActivityNet等多个基准测试中表现强劲，在大幅缩小每个视频的缓存大小时，实现了具有竞争力的召回率。 AI

影响通过在压缩视频数据上进行检索，提高了视频搜索应用的效率和可扩展性。

排序理由这是一篇详细介绍视频-文本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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍视频-文本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, infra; 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: 28 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Shahaf Wagner, Gabriele Serussi, Dan Ben Ami, Tomer Galanti, Chaim Baskin · 2026-10-09 04:00

VEDJE: 视频高效判别性联合编码器，用于可扩展的视频-文本检索

arXiv:2610.11850v1 Announce Type: new Abstract: Finding the right video often requires distinguishing similar scenes in which different events occur. Joint matching improves retrieval, but processing rich video representations for each query is costly. VEDJE compresses features w…

本文如何被排名

报道来源 [1]

VEDJE: 视频高效判别性联合编码器，用于可扩展的视频-文本检索

相关实体

相关话题