Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Petrovich, Mathis"'
We provide results of our study on text-based 3D human motion retrieval and particularly focus on cross-dataset generalization. Due to practical reasons such as dataset-specific human body representations, existing works typically benchmarkby trainin
Externí odkaz:
http://arxiv.org/abs/2405.16909
Autor:
Petrovich, Mathis, Litany, Or, Iqbal, Umar, Black, Michael J., Varol, Gül, Peng, Xue Bin, Rempe, Davis
Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as in
Externí odkaz:
http://arxiv.org/abs/2401.08559
In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the state-of-the-
Externí odkaz:
http://arxiv.org/abs/2305.00976
Our goal is to synthesize 3D human motions given textual inputs describing simultaneous actions, for example 'waving hand' while 'walking' at the same time. We refer to generating such simultaneous movements as performing 'spatial compositions'. In c
Externí odkaz:
http://arxiv.org/abs/2304.10417
Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions. In particular, our goal is to enable the synthesis of a series of a
Externí odkaz:
http://arxiv.org/abs/2209.04066
We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generatin
Externí odkaz:
http://arxiv.org/abs/2204.14109
We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action
Externí odkaz:
http://arxiv.org/abs/2104.05670
Autor:
Petrovich, Mathis, Liang, Chao, Sato, Ryoma, Liu, Yanbin, Tsai, Yao-Hung Hubert, Zhu, Linchao, Yang, Yi, Salakhutdinov, Ruslan, Yamada, Makoto
Optimal transport is a machine learning problem with applications including distribution comparison, feature selection, and generative adversarial networks. In this paper, we propose feature-robust optimal transport (FROT) for high-dimensional data,
Externí odkaz:
http://arxiv.org/abs/2005.12123
Autor:
Petrovich, Mathis, Yamada, Makoto
Regression is an important task in machine learning and data mining. It has several applications in various domains, including finance, biomedical, and computer vision. Recently, network Lasso, which estimates local models by making clusters using th
Externí odkaz:
http://arxiv.org/abs/2003.05747
Biological data including gene expression data are generally high-dimensional and require efficient, generalizable, and scalable machine-learning methods to discover their complex nonlinear patterns. The recent advances in machine learning can be att
Externí odkaz:
http://arxiv.org/abs/2001.08322