Search Results for author: Ailing Zeng

Found 15 papers, 8 papers with code

Are Transformers Effective for Time Series Forecasting?

2 code implementations26 May 2022 Ailing Zeng, Muxi Chen, Lei Zhang, Qiang Xu

Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task.

Anomaly Detection Relation Extraction +2

DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation

1 code implementation16 Mar 2022 Ailing Zeng, Xuan Ju, Lei Yang, Ruiyuan Gao, Xizhou Zhu, Bo Dai, Qiang Xu

This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch.

3D Human Pose Estimation 3D Pose Estimation +1

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

2 code implementations27 Dec 2021 Ailing Zeng, Lei Yang, Xuan Ju, Jiefeng Li, Jianyi Wang, Qiang Xu

With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect.

3D Human Pose Estimation 3D Human Reconstruction +1

T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis

no code implementations ICLR 2022 Minhao Liu, Ailing Zeng, Qiuxia Lai, Ruiyuan Gao, Min Li, Jing Qin, Qiang Xu

In this work, we propose a novel tree-structured wavelet neural network for time series signal analysis, namely T-WaveNet, by taking advantage of an inherent property of various types of signals, known as the dominant frequency range.

Activity Recognition Representation Learning +1

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

1 code implementation ICCV 2021 Ailing Zeng, Xiao Sun, Lei Yang, Nanxuan Zhao, Minhao Liu, Qiang Xu

While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory.

3D Human Pose Estimation 3D Pose Estimation +3

Information Bottleneck Approach to Spatial Attention Learning

1 code implementation7 Aug 2021 Qiuxia Lai, Yu Li, Ailing Zeng, Minhao Liu, Hanqiu Sun, Qiang Xu

Extensive experiments show that the proposed IB-inspired spatial attention mechanism can yield attention maps that neatly highlight the regions of interest while suppressing backgrounds, and bootstrap standard DNN structures for visual recognition tasks (e. g., image classification, fine-grained recognition, cross-domain classification).

Decision Making Image Classification

Human Pose Regression with Residual Log-likelihood Estimation

3 code implementations ICCV 2021 Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu

In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution.

3D Human Pose Estimation Multi-Person Pose Estimation

Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction

3 code implementations17 Jun 2021 Minhao Liu, Ailing Zeng, Zhijian Xu, Qiuxia Lai, Qiang Xu

Motivated by the above, in this paper, we propose a novel neural network architecture that conducts sample convolution and interaction for temporal modeling and apply it for the time series forecasting problem, namely \textbf{SCINet}.

Time Series Analysis Traffic Prediction +1

Relational Graph Neural Network Design via Progressive Neural Architecture Search

no code implementations30 May 2021 Ailing Zeng, Minhao Liu, Zhiwei Liu, Ruiyuan Gao, Jing Qin, Qiang Xu

We propose a novel solution to addressing a long-standing dilemma in the representation learning of graph neural networks (GNNs): how to effectively capture and represent useful information embedded in long-distance nodes to improve the performance of nodes with low homophily without leading to performance degradation in nodes with high homophily.

Neural Architecture Search Node Classification +1

Skimming and Scanning for Untrimmed Video Action Recognition

no code implementations21 Apr 2021 Yunyan Hong, Ailing Zeng, Min Li, Cewu Lu, Li Jiang, Qiang Xu

Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes.

Action Recognition Video Understanding

T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis

no code implementations10 Dec 2020 Minhao Liu, Ailing Zeng, Qiuxia Lai, Qiang Xu

Motivated by the fact that usually a small subset of the frequency components carries the primary information for sensor data, we propose a novel tree-structured wavelet neural network for sensor data analysis, namely \emph{T-WaveNet}.

Activity Recognition Gesture Recognition +4

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

1 code implementation ECCV 2020 Ailing Zeng, Xiao Sun, Fuyang Huang, Minhao Liu, Qiang Xu, Stephen Lin

With the reduced dimensionality of less relevant body areas, the training set distribution within network branches more closely reflects the statistics of local poses instead of global body poses, without sacrificing information important for joint inference.

Monocular 3D Human Pose Estimation

DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image

no code implementations9 Dec 2019 Fuyang Huang, Ailing Zeng, Minhao Liu, Qiuxia Lai, Qiang Xu

In this paper, we propose a two-stage fully 3D network, namely \textbf{DeepFuse}, to estimate human pose in 3D space by fusing body-worn Inertial Measurement Unit (IMU) data and multi-view images deeply.

3D Human Pose Estimation 3D Pose Estimation

Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image

no code implementations26 Dec 2018 Fuyang Huang, Ailing Zeng, Minhao Liu, Jing Qin, Qiang Xu

Experimental results show that the proposed structure-aware 3D hourglass network is able to achieve a mean joint error of 7. 4 mm in MSRA and 8. 9 mm in NYU datasets, respectively.

Hand Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.