no code implementations • 6 Dec 2023 • Ekkasit Pinyoanuntapong, Pu Wang, Minwoo Lee, Chen Chen
MMM consists of two key components: (1) a motion tokenizer that transforms 3D human motion into a sequence of discrete tokens in latent space, and (2) a conditional masked motion transformer that learns to predict randomly masked motion tokens, conditioned on the pre-computed text tokens.
no code implementations • 30 Oct 2023 • Junhui Li, Pu Wang, Jialu Li, Xinzhe Wang, Youshan Zhang
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods.
1 code implementation • 31 Jan 2023 • Ekkasit Pinyoanuntapong, Ayman Ali, Kalvik Jakkala, Pu Wang, Minwoo Lee, Qucheng Peng, Chen Chen, Zhi Sun
mmWave radar-based gait recognition is a novel user identification method that captures human gait biometrics from mmWave radar return signals.
no code implementations • 31 Jan 2023 • Ayman Ali, Ekkasit Pinyoanuntapong, Pu Wang, Mohsen Dorodchi
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features, and illumination invariance.
no code implementations • 31 Jan 2023 • Ayman Ali, Ekkasit Pinyoanuntapong, Pu Wang, Mohsen Dorodchi
In this research, we address the challenge faced by existing deep learning-based human mesh reconstruction methods in balancing accuracy and computational efficiency.
1 code implementation • 27 Oct 2022 • Ekkasit Pinyoanuntapong, Ayman Ali, Pu Wang, Minwoo Lee, Chen Chen
Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities.
Ranked #5 on
Multiview Gait Recognition
on CASIA-B
no code implementations • 18 Jul 2022 • Toshiaki Koike-Akino, Pu Wang, Genki Yamashita, Wataru Tsujita, Makoto Nakajima
A learning-based THz multi-layer imaging has been recently used for contactless three-dimensional (3D) positioning and encoding.
no code implementations • 28 Jun 2022 • Pu Wang, Hugo Van hamme
End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data.
1 code implementation • 18 May 2022 • Kunqi Wang, Daolin Si, Pu Wang, Jing Ge, Peiyuan Ni, Shuguo Wang
Matching the rail cross-section profiles measured on site with the designed profile is a must to evaluate the wear of the rail, which is very important for track maintenance and rail safety.
no code implementations • 17 May 2022 • Toshiaki Koike-Akino, Pu Wang, Ye Wang
Beyond data communications, commercial-off-the-shelf Wi-Fi devices can be used to monitor human activities, track device locomotion, and sense the ambient environment.
no code implementations • 17 May 2022 • Toshiaki Koike-Akino, Pu Wang, Ye Wang
Commercial Wi-Fi devices can be used for integrated sensing and communications (ISAC) to jointly exchange data and monitor indoor environment.
no code implementations • CVPR 2022 • Peizhao Li, Pu Wang, Karl Berntorp, Hongfu Liu
We consider the object recognition problem in autonomous driving using automotive radar sensors.
Ranked #1 on
Multiple Object Tracking
on RADIATE
1 code implementation • CVPR 2022 • Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen
To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.
1 code implementation • 24 Nov 2021 • Ce Zheng, Matias Mendieta, Pu Wang, Aidong Lu, Chen Chen
We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh.
Ranked #51 on
3D Human Pose Estimation
on 3DPW
no code implementations • 18 Oct 2021 • Pinyarash Pinyoanuntapong, Tagore Pothuneedi, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang
Federated Learning (FL) over wireless multi-hop edge computing networks, i. e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm.
no code implementations • 14 Oct 2021 • Pinyarash Pinyoanuntapong, Prabhu Janakaraj, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang
To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i. e., workers) and the remote server.
no code implementations • 15 Jun 2021 • Pu Wang, Bagher BabaAli, Hugo Van hamme
The acoustic model is pre-trained in two stages: initialization with a corpus of normal speech and finetuning on a mixture of dysarthric and normal speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • 14 May 2021 • Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen
MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.
no code implementations • 30 Mar 2021 • Pu Wang, Hugo Van hamme
In this paper we combine the encoder of an end-to-end ASR system with the prior NMF/capsule network-based user-taught decoder, and investigate whether pre-training methodology can reduce training data requirements for the NMF and capsule network.
1 code implementation • 26 Nov 2020 • Jiawei Zhu, Xin Han, Hanhan Deng, Chao Tao, Ling Zhao, Pu Wang, Lin Tao, Haifeng Li
On this background, this study presents a knowledge representation-driven traffic forecasting method based on spatial-temporal graph convolutional networks.
no code implementations • 22 Nov 2020 • Jiawei Zhu, Chao Tao, Hanhan Deng, Ling Zhao, Pu Wang, Tao Lin, Haifeng Li
Traffic forecasting is a fundamental and challenging task in the field of intelligent transportation.
no code implementations • 6 Feb 2019 • Kalvik Jakkala, Arupjyoti Bhuya, Zhi Sun, Pu Wang, Zhuo Cheng
Gait is a person's natural walking style and a complex biological process that is unique to each person.
9 code implementations • 12 Nov 2018 • Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li
However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.
no code implementations • 9 Nov 2013 • Jun Fang, Yanning Shen, Hongbin Li, Pu Wang
In this paper, we develop a new sparse Bayesian learning method for recovery of block-sparse signals with unknown cluster patterns.