
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Chaos and Order</title>
      <link>https://www.youngju.dev/blog</link>
      <description>천천히 올바르게. AI Researcher &amp; DevOps Engineer Youngju&#39;s tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering.</description>
      <language>ko</language>
      <managingEditor>fjvbn2003@gmail.com (Youngju Kim)</managingEditor>
      <webMaster>fjvbn2003@gmail.com (Youngju Kim)</webMaster>
      <lastBuildDate>Tue, 30 Jun 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.youngju.dev/tags/action-recognition/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis.en</guid>
    <title>SOTA Real-Time Video Analysis — Tracking, Understanding, Efficient Inference</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis.en</link>
    <description>A survey of SOTA trends in real-time video analysis. We cover video understanding tasks like action recognition, object tracking, and temporal segmentation, the SAM 2 family concept of video segmentation and tracking, transformer-based video models, and real-time inference optimization through lightening and streaming, centered on architectural principles.</description>
    <pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>video-understanding</category><category>object-tracking</category><category>sam2</category><category>action-recognition</category><category>real-time</category><category>computer-vision</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis.ja</guid>
    <title>SOTA リアルタイム動画分析 — 追跡、理解、効率的推論</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis.ja</link>
    <description>リアルタイム動画分析の SOTA の流れを整理します。行動認識・物体追跡・時間的セグメンテーションといった動画理解の課題、SAM 2 系の動画セグメンテーション・追跡の概念、トランスフォーマーベースの動画モデル、そして軽量化・ストリーミングによるリアルタイム推論最適化を、アーキテクチャの原理を中心に見ていきます。</description>
    <pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>video-understanding</category><category>object-tracking</category><category>sam2</category><category>action-recognition</category><category>real-time</category><category>computer-vision</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis</guid>
    <title>SOTA 실시간 비디오 분석 — 추적, 이해, 효율 추론</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-30-sota-realtime-video-analysis</link>
    <description>실시간 비디오 분석의 SOTA 흐름을 정리합니다. 행동 인식·객체 추적·시간적 분할 같은 비디오 이해 과제, SAM 2 계열의 비디오 분할·추적 개념, 트랜스포머 기반 비디오 모델, 그리고 경량화·스트리밍을 통한 실시간 추론 최적화를 아키텍처 원리 중심으로 살펴봅니다.</description>
    <pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>video-understanding</category><category>object-tracking</category><category>sam2</category><category>action-recognition</category><category>real-time</category><category>computer-vision</category>
  </item>

    </channel>
  </rss>
