{
  "schema_version": 1,
  "slug": "intersyn",
  "canonical_url": "https://akira-l.github.io/publications/intersyn/",
  "language_urls": {
    "en": "https://akira-l.github.io/publications/intersyn/",
    "zh-CN": "https://akira-l.github.io/zh/publications/intersyn/"
  },
  "title": "InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild",
  "short_title": "InterSyn",
  "authors": [
    "Yiyi Ma",
    "Yuanzhi Liang",
    "Xiu Li",
    "Chi Zhang",
    "Xuelong Li"
  ],
  "publication": {
    "kind": "conference",
    "venue": "IEEE/CVF International Conference on Computer Vision (ICCV 2025)",
    "citation_container_title": "2025 IEEE/CVF International Conference on Computer Vision (ICCV)",
    "status": "published",
    "year": 2025,
    "publication_date": "2025",
    "publisher": "IEEE",
    "pages": "12832-12841"
  },
  "identifiers": {
    "doi": "10.1109/ICCV51701.2025.01192",
    "arxiv": "2508.10297",
    "arxiv_primary_class": "cs.CV"
  },
  "arxiv_dates": {
    "first_posted": "2025-08-14",
    "last_revised": "2025-08-14"
  },
  "keywords": [
    "3D human motion",
    "multi-person interaction",
    "interleaved learning",
    "motion synthesis",
    "coordination refinement"
  ],
  "official_abstract": "We present Interleaved Learning for Motion Synthesis (InterSyn), a novel framework that targets the generation of realistic interaction motions by learning from integrated motions that consider both solo and multi-person dynamics. Unlike previous methods that treat these components separately, InterSyn employs an interleaved learning strategy to capture the natural, dynamic interactions and nuanced coordination inherent in real-world scenarios. Our framework comprises two key modules: the Interleaved Interaction Synthesis (INS) module, which jointly models solo and interactive behaviors in a unified paradigm from a first-person perspective to support multiple character interactions, and the Relative Coordination Refinement (REC) module, which refines mutual dynamics and ensures synchronized motions among characters. Experimental results show that the motion sequences generated by InterSyn exhibit higher text-to-motion alignment and improved diversity compared with recent methods, setting a new benchmark for robust and natural motion synthesis. Additionally, our code will be open-sourced in the future to promote further research and development in this area.",
  "official_abstract_rights": "Excluded from the site's CC BY 4.0 license; original paper rights apply.",
  "primary_source": {
    "label": "IEEE version of record",
    "url": "https://doi.org/10.1109/ICCV51701.2025.01192",
    "version": "ICCV 2025 version of record; CVF open-access copy and arXiv:2508.10297v1 cross-checked",
    "method_locator": "Abstract; INS and REC method sections",
    "evidence_locator": "Abstract; text-to-motion alignment and diversity experiments"
  },
  "source_checked": "2026-07-31",
  "verification_status": "author-verified",
  "author_verified_on": "2026-07-31",
  "commentary": {
    "license": "https://creativecommons.org/licenses/by/4.0/",
    "en": {
      "summary": "InterSyn learns solo and multi-person dynamics together rather than treating them as separate tasks: INS synthesizes both from a first-person interaction perspective, and REC refines relative coordination so characters move synchronously.",
      "problem": "Separating solo motion from multi-person interaction makes it difficult to learn how individual behavior and mutual coordination combine in realistic, dynamic interactions.",
      "contributions": [
        "Uses interleaved learning over integrated solo and multi-person motions.",
        "Introduces Interleaved Interaction Synthesis (INS) to jointly model solo and interactive behavior from a first-person perspective.",
        "Introduces Relative Coordination Refinement (REC) to refine mutual dynamics and synchronization."
      ],
      "evidence": "The paper reports higher text-to-motion alignment and greater diversity than recent comparison methods. The claim concerns the evaluated motion-synthesis setup; exact datasets, baselines, and scores should be cited from the ICCV paper.",
      "limitations": "The demonstrated scope is motion synthesis from integrated solo and multi-person data. The abstract does not establish generality to arbitrary numbers of people, environments, or interaction semantics outside the evaluated distributions.",
      "positioning": "InterSyn is a multi-person interaction-motion method centered on integrated learning and relative coordination. It should not be described as a method for learning motion jointly with a dynamic environment; its 'dynamic' aspect refers to solo and interacting character dynamics.",
      "citation_ready": "Ma et al. propose InterSyn, which interleaves solo and multi-person motion learning through an interaction-synthesis module and refines relative coordination to improve synchronized, text-aligned interaction motion."
    },
    "zh-CN": {
      "summary": "InterSyn 不把单人动作与多人交互视为彼此独立的任务：INS 从第一人称交互视角联合合成两类行为，REC 再细化角色之间的相对协调与同步。",
      "problem": "若将 solo motion 和 multi-person interaction 分开建模，模型难以学习个体行为与相互协调在真实动态交互中如何共同形成。",
      "contributions": [
        "对整合后的单人和多人动作执行 interleaved learning。",
        "提出 Interleaved Interaction Synthesis（INS），从第一人称视角统一建模 solo 与 interactive behavior。",
        "提出 Relative Coordination Refinement（REC），细化角色间的 mutual dynamics 与同步。"
      ],
      "evidence": "论文报告相比近期方法具有更高的 text-to-motion alignment 和更好的 diversity；该结论限定于已评测动作合成设置，准确数据集、baseline 和数值应引用 ICCV 论文。",
      "limitations": "已展示范围是利用整合后的单人和多人数据进行动作合成。摘要并未证明方法可泛化到任意人数、环境或评测分布外的交互语义。",
      "positioning": "InterSyn 是强调 integrated learning 与 relative coordination 的多人交互动作方法，不应误写成“联合学习人物动作和动态环境”；这里的 dynamic 指单人及交互角色的运动动态。",
      "citation_ready": "Ma 等提出 InterSyn，通过 interaction-synthesis 模块交错学习单人和多人动作，并细化相对协调，以改善同步且与文本对齐的交互动作生成。"
    }
  },
  "citation": {
    "id": "ma2025intersyn",
    "type": "paper-conference",
    "title": "InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild",
    "author": [
      {
        "given": "Yiyi",
        "family": "Ma"
      },
      {
        "given": "Yuanzhi",
        "family": "Liang"
      },
      {
        "given": "Xiu",
        "family": "Li"
      },
      {
        "given": "Chi",
        "family": "Zhang"
      },
      {
        "given": "Xuelong",
        "family": "Li"
      }
    ],
    "container-title": "2025 IEEE/CVF International Conference on Computer Vision (ICCV)",
    "issued": {
      "date-parts": [
        [
          2025
        ]
      ]
    },
    "URL": "https://doi.org/10.1109/ICCV51701.2025.01192",
    "abstract": "We present Interleaved Learning for Motion Synthesis (InterSyn), a novel framework that targets the generation of realistic interaction motions by learning from integrated motions that consider both solo and multi-person dynamics. Unlike previous methods that treat these components separately, InterSyn employs an interleaved learning strategy to capture the natural, dynamic interactions and nuanced coordination inherent in real-world scenarios. Our framework comprises two key modules: the Interleaved Interaction Synthesis (INS) module, which jointly models solo and interactive behaviors in a unified paradigm from a first-person perspective to support multiple character interactions, and the Relative Coordination Refinement (REC) module, which refines mutual dynamics and ensures synchronized motions among characters. Experimental results show that the motion sequences generated by InterSyn exhibit higher text-to-motion alignment and improved diversity compared with recent methods, setting a new benchmark for robust and natural motion synthesis. Additionally, our code will be open-sourced in the future to promote further research and development in this area.",
    "keyword": "3D human motion, multi-person interaction, interleaved learning, motion synthesis, coordination refinement",
    "publisher": "IEEE",
    "DOI": "10.1109/ICCV51701.2025.01192",
    "page": "12832-12841"
  },
  "resources": [
    {
      "label": "Version of record",
      "url": "https://doi.org/10.1109/ICCV51701.2025.01192"
    },
    {
      "label": "Open access",
      "url": "https://openaccess.thecvf.com/content/ICCV2025/html/Ma_InterSyn_Interleaved_Learning_for_Dynamic_Motion_Synthesis_in_the_Wild_ICCV_2025_paper.html"
    },
    {
      "label": "Project",
      "url": "https://myy888.github.io/InterSyn/"
    },
    {
      "label": "arXiv",
      "url": "https://arxiv.org/abs/2508.10297"
    }
  ]
}