{"type":"ScholarlyArticle","title":"TPPMG: Temporal Planning-driven Progressive Motion Generation","authors":[{"name":"Ruoyu Wang","slug":"ruoyu-wang","given":"Ruoyu","family":"Wang","affiliation":""},{"name":"Can Deng","slug":"can-deng","given":"Can","family":"Deng","affiliation":""},{"name":"Xinyi Li","slug":"xinyi-li","given":"Xinyi","family":"Li","affiliation":""},{"name":"Zhuo Li","slug":"zhuo-li","given":"Zhuo","family":"Li","affiliation":""}],"abstract":"Most text-to-motion models treat motion duration as a fixed hyperparameter rather than a variable inferred from semantics, inducing two systematic failure modes: duration trailing on short prompts and stage-wise semantic collapse on long, multi-stage prompts. To address this issue, we propose TPPMG (Temporal Planning-driven Progressive Motion Generation), which factorizes generation as semantics -> temporal structure -> motion realization. TPPMG comprises two components: (1) a Temporal Planner that maps text to an explicit stage-duration script via an LLM with a lightweight duration calibrator; and (2) a Progressive Diffusion Generator that bridges fixed-length diffusion training and variable-length inference through heterogeneous noise scheduling and a sliding-window mechanism, enabling budget-driven variable-length motion synthesis. To evaluate both failure modes with verifiable ground truth, we construct three benchmarks: HumanML3D-Short, HumanML3D-Concat, and BABEL-Concat, along with a comprehensive evaluation suite. Experiments show that TPPMG suppresses duration trailing (UR: 0.52 -> 0.85), substantially improves multi-stage structure recovery (PhaseRecall: 0.56 -> 0.90, BoundaryF1: 0.28 -> 0.56), and reduces boundary discontinuity at stage transitions.","doi":"10.24963/ijcai.2026/197","url":"https://ijcai.org/proceedings/2026/197","pdf":"https://ijcai.org/proceedings/2026/0197.pdf","markdown":"https://ijcai.org/proceedings/2026/197.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/197","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":197,"pages":{"first":1767,"last":1775},"keywords":["Computer Vision: Motion and tracking","Computer Vision: Action and behavior recognition","Computer Vision: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}