arXiv:2608.23279v1 Announce Type: new
Abstract: Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For rep...
By Chengqun Yang, Liang Xu, Yanping Li, Fulong Liu, Jingnan Gao, Weili Zeng, Yichao Yan
arXiv:2608.29891v1 Announce Type: new
Abstract: Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approac...
By Xinyao Qin, Linxiang Peng, Youbao Ye, Di Yang, Jiangtao Wang
arXiv:2605. 16366v2 Announce Type: replace-cross Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling.
By Yigui Feng (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China), Qinglin Wang (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China), Yang Liu (The Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, Guangdong, China), Jie Liu (The College of Computer Science, National University of Defense Technology, Changsha, Hunan, China)
The paper introduces Frequency-Factorized Multi-Rate Tokenization (FFMT) for music-to-dance generation, separating root-relative motion into a low-frequency choreographic scaffold and a high-frequency residual. FFMT assigns a lower token rate and smaller codebook to the low-frequency component, while using a higher token rate and larger codebook for the high-frequency part, enabling a plan-then-articulate autoregressive factorization. Experiments on AIST++ and FineDance demonstrate strong distributional fidelity, realistic diversity, and music–motion synchronization, with ablations confirming the benefits of frequency factorization, asymmetric temporal allocation, and low-to-high conditioning.
By Qirong Guo, Ruijie Li, Zeyan Li, Sicheng Shu, Guanzhi Ding, Weihang Ding
arXiv:2608.24334v1 Announce Type: new
Abstract: Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for...
By Tianlv Huang, Hetian Guo, Ziyi Cai, Song Wang, Yanping Zhang, Zipei Fan, Xuan Song, Guangming Wu, Xin Zheng
MotionSpec introduces a motion supervision framework for text-to-video generation that focuses on Spectral Trajectory Consistency (STC). STC builds dense anchor-relative motion trajectories, transforms them into spectral volumes, and aligns their amplitude and phase with target trajectories to constrain motion strength and temporal organization. The framework also adds Local Flow Consistency (LFC) to stabilize local motion transitions, resulting in improved motion consistency, temporal coherence, and plausibility while maintaining visual fidelity.
By Ziqi Ni, Rui Li, Shiqi Jiang, Wei Zhou