多模态检索是当前向量搜索的关键突破点，做视频理解、智能体或搜索系统的团队值得关注这场演讲，看看 Twelve Labs 如何将视频从“带图片的文本”变成真正的语义搜索对象。
Twelve Labs 的 James Le 将在 Vector Space Day 上展示如何正确构建多模态检索，从体育和音频的语义搜索到处理目标跟踪和高光生成的智能体工作流。视频是信息密度最高的模态，但大多数检索管道仍将其视为带图片的文本。该演讲将展示向量搜索的前沿方向，适合对多模态检索和智能体工作流感兴趣的开发者。
Video is the most information-dense modality we have, and most retrieval pipelines treat it like tex...
Video is the most information-dense modality we have, and most retrieval pipelines treat it like text with pictures. James Le from @twelve_labs is coming to Vector Space Day to show what's actually possible when you build multimodal retrieval right, from semantic search across sports and audio to agentic workflows that handle object tracking and highlight generation at scale. If you're curious where vector search is heading, this is a session worth being in the room for. Join us at The Midway: luma.com/vsd-sf 💬 1 🔄 0 ❤️ 2 👀 63 📊 1 ⚡