Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Li, Maosen"'
Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. However, these methods have two critical issues: first, deep graph convolutions filter fe
Externí odkaz:
http://arxiv.org/abs/2208.00368
Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works only consider pair-wise interactions with limited relational reasoning. To pro
Externí odkaz:
http://arxiv.org/abs/2204.08770
Publikováno v:
In Construction and Building Materials 4 October 2024 446
We propose a multiscale spatio-temporal graph neural network (MST-GNN) to predict the future 3D skeleton-based human poses in an action-category-agnostic manner. The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the rel
Externí odkaz:
http://arxiv.org/abs/2108.11244
Publikováno v:
In Construction and Building Materials 26 July 2024 437
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system. We propose a novel collaborative prediction unit (CoPU), which aggregates the predictions from multiple collabor
Externí odkaz:
http://arxiv.org/abs/2107.00894
Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The reason of
Externí odkaz:
http://arxiv.org/abs/2012.15497
We propose a novel method based on teacher-student learning framework for 3D human pose estimation without any 3D annotation or side information. To solve this unsupervised-learning problem, the teacher network adopts pose-dictionary-based modeling f
Externí odkaz:
http://arxiv.org/abs/2012.09398
We propose interpretable graph neural networks for sampling and recovery of graph signals, respectively. To take informative measurements, we propose a new graph neural sampling module, which aims to select those vertices that maximally express their
Externí odkaz:
http://arxiv.org/abs/2011.01412
Publikováno v:
Neurips 2020
We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to
Externí odkaz:
http://arxiv.org/abs/2010.01804