arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.04771cs.CV
收藏

利用 Motion Patches 探索用于 3D 人体动作-语言模型的 Vision Transformers

Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches

LY Corporation

Qing Yu, Mikihiro Tanaka, Kent Fujiwara

AI总结:

本文提出 motion patches 动作表示并结合预训练 ViT 迁移学习,以缓解 3D 动作数据稀缺问题,在文本到动作检索及多项挑战性任务上达到 SOTA。

摘要:

为了在 3D 人体动作与语言之间构建跨模态潜空间,获取大规模、高质量的人体动作数据至关重要。然而,与丰富的图像数据不同,动作数据的稀缺限制了现有动作-语言模型的性能。为解决这一问题,我们提出“motion patches”这一新型动作序列表示,并通过迁移学习使用 Vision Transformers(ViT)作为动作编码器,旨在从图像域提取有用知识并将其应用于动作域。这些 motion patches 通过在动作序列中按身体部位划分并排序骨骼关节而生成,对不同骨骼结构具有鲁棒性,并可被视为 ViT 中的彩色图像 patch。我们发现,使用通过 2D 图像数据训练得到的 ViT 预训练权重进行迁移学习,可以提升动作分析性能,为解决动作数据有限的问题提供了有前景的方向。大量实验表明,所提出的 motion patches 与 ViT 结合使用,在文本到动作检索基准以及其他新颖且具有挑战性的任务上达到了最先进性能,这些任务包括跨骨骼识别、零样本动作分类和人体交互识别,目前均受到数据缺乏的阻碍。

英文摘要:

To build a cross-modal latent space between 3D human motion and language, acquiring large-scale and high-quality human motion data is crucial. However, unlike the abundance of image data, the scarcity of motion data has limited the performance of existing motion-language models. To counter this, we introduce "motion patches", a new representation of motion sequences, and propose using Vision Transformers (ViT) as motion encoders via transfer learning, aiming to extract useful knowledge from the image domain and apply it to the motion domain. These motion patches, created by dividing and sorting skeleton joints based on body parts in motion sequences, are robust to varying skeleton structures, and can be regarded as color image patches in ViT. We find that transfer learning with pre-trained weights of ViT obtained through training with 2D image data can boost the performance of motion analysis, presenting a promising direction for addressing the issue of limited motion data. Our extensive experiments show that the proposed motion patches, used jointly with ViT, achieve state-of-the-art performance in the benchmarks of text-to-motion retrieval, and other novel challenging tasks, such as cross-skeleton recognition, zero-shot motion classification, and human interaction recognition, which are currently impeded by the lack of data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑