no code implementations • 27 Jun 2022 • Chenxin Xu, Yuxi Wei, Bohan Tang, Sheng Yin, Ya zhang, Siheng Chen
Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction.
no code implementations • 31 May 2022 • Mingxing Xu, Chenglin Li, Wenrui Dai, Siheng Chen, Junni Zou, Pascal Frossard, Hongkai Xiong
Specifically, adaptive spherical wavelets are learned with a lifting structure that consists of trainable lifting operators (i. e., update and predict operators).
1 code implementation • CVPR 2022 • Chenxin Xu, Maosen Li, Zhenyang Ni, Ya zhang, Siheng Chen
From the aspect of interaction capturing, we propose a trainable multiscale hypergraph to capture both pair-wise and group-wise interactions at multiple group sizes.
1 code implementation • CVPR 2022 • Chenxin Xu, Weibo Mao, Wenjun Zhang, Siheng Chen
However, in this way, the model parameters come from all seen instances, which means a huge amount of irrelevant seen instances might also involve in predicting the current situation, disturbing the performance.
Ranked #2 on
Trajectory Prediction
on Stanford Drone
no code implementations • 17 Feb 2022 • Yiming Li, Ziyan An, Zixun Wang, Yiqi Zhong, Siheng Chen, Chen Feng
Vehicle-to-everything (V2X), which denotes the collaboration between a vehicle and any entity in its surrounding, can fundamentally improve the perception in self-driving systems.
no code implementations • 17 Feb 2022 • Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan
Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.
no code implementations • CVPR 2022 • Yixuan Huang, Xiaoyun Zhang, Yu Fu, Siheng Chen, Ya zhang, Yan-Feng Wang, Dazhi He
Those methods conduct the super-resolution task of the input low-resolution(LR) image and the texture transfer task from the reference image together in one module, easily introducing the interference between LR and reference features.
1 code implementation • CVPR 2022 • Qi Yang, Yipeng Liu, Siheng Chen, Yiling Xu, Jun Sun
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds.
1 code implementation • NeurIPS 2021 • Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen, Chen Feng, Wenjun Zhang
Our approach is validated on V2X-Sim 1. 0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation.
no code implementations • 30 Oct 2021 • Jian Du, Song Li, Xiangyi Chen, Siheng Chen, Mingyi Hong
The equivalent privacy costs controlled by maintaining the same gradient clipping thresholds and noise powers in each step result in unstable updates and a lower model accuracy when compared to the non-DP counterpart.
no code implementations • NeurIPS 2021 • Bohan Tang, Yiqi Zhong, Ulrich Neumann, Gang Wang, Ya zhang, Siheng Chen
2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances.
no code implementations • 23 Oct 2021 • Zida Cheng, Siheng Chen, Ya zhang
Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition.
no code implementations • 20 Oct 2021 • Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis
Backdoor attacks (BA) are an emerging threat to deep neural network classifiers.
1 code implementation • NeurIPS 2021 • Xingyue Pu, Tianyue Cao, Xiaoyun Zhang, Xiaowen Dong, Siheng Chen
The model is trained in an end-to-end fashion with pairs of node data and graph samples.
1 code implementation • 16 Oct 2021 • Xin Yu, Jeroen van Baar, Siheng Chen
We use a coarse graph, derived from a dense graph, to estimate the human's 3D pose, and the dense graph to estimate the 3D shape.
Ranked #195 on
3D Human Pose Estimation
on Human3.6M
no code implementations • 24 Sep 2021 • Jinxiang Liu, Yangheng Zhao, Siheng Chen, Ya zhang
To leverage the human body shape prior, LPNet exploits the topological information of the body mesh to learn an expressive visual representation for the target person in the 3D mesh space.
no code implementations • 25 Aug 2021 • Maosen Li, Siheng Chen, Yangheng Zhao, Ya zhang, Yanfeng Wang, Qi Tian
The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the relations in motions at various spatial and temporal scales.
no code implementations • ICCV 2021 • Tianyue Cao, Lianyu Du, Xiaoyun Zhang, Siheng Chen, Ya zhang, Yan-Feng Wang
To handle overlapping category transfer, we propose a double-supervision mean teacher to gather common category information and bridge the domain gap between two datasets.
no code implementations • 16 Jul 2021 • Zida Cheng, Siheng Chen, Ya zhang
Experiments are conducted on FPHA and HO-3D datasets.
no code implementations • 2 Jul 2021 • Maosen Li, Siheng Chen, Yanning Shen, Genjia Liu, Ivor W. Tsang, Ya zhang
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system.
no code implementations • 6 Apr 2021 • Chen Ju, Peisen Zhao, Siheng Chen, Ya zhang, Xiaoyun Zhang, Qi Tian
To solve this issue, we introduce an adaptive mutual supervision framework (AMS) with two branches, where the base branch adopts CAS to localize the most discriminative action regions, while the supplementary branch localizes the less discriminative action regions through a novel adaptive sampler.
Ranked #4 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
1 code implementation • 4 Mar 2021 • Qi Yang, Yujie Zhang, Siheng Chen, Yiling Xu, Jun Sun, Zhan Ma
In this paper, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED).
no code implementations • ICCV 2021 • Chen Ju, Peisen Zhao, Siheng Chen, Ya zhang, Yanfeng Wang, Qi Tian
Single-frame temporal action localization (STAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance.
1 code implementation • 17 Dec 2020 • Chenxin Xu, Siheng Chen, Maosen Li, Ya zhang
To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network.
no code implementations • ICLR 2021 • Chao Pan, Siheng Chen, Antonio Ortega
Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data.
no code implementations • 3 Nov 2020 • Siheng Chen, Maosen Li, Ya zhang
Compared to previous analytical sampling and recovery, the proposed methods are able to flexibly learn a variety of graph signal models from data by leveraging the learning ability of neural networks; compared to previous neural-network-based sampling and recovery, the proposed methods are designed through exploiting specific graph properties and provide interpretability.
2 code implementations • 3 Nov 2020 • Xu Chen, Siheng Chen, Jiangchao Yao, Huangjie Zheng, Ya zhang, Ivor W Tsang
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
2 code implementations • NeurIPS 2020 • Maosen Li, Siheng Chen, Ya zhang, Ivor W. Tsang
Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.
no code implementations • 16 Jul 2020 • Jingchao Su, Xu Chen, Ya zhang, Siheng Chen, Dan Lv, Chenyang Li
The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs.
no code implementations • 16 Jul 2020 • Chenyang Li, Xu Chen, Ya zhang, Siheng Chen, Dan Lv, Yan-Feng Wang
Most existing methods focus on preserving the first-order proximity between entities in the KG.
no code implementations • 17 Jun 2020 • Takuya Fujihashi, Toshiaki Koike-Akino, Siheng Chen, Takashi Watanabe
To prevent the cliff effect subject to channel quality fluctuation, we have proposed soft point cloud delivery called HoloCast.
no code implementations • 1 Jun 2020 • Siheng Chen, Yonina C. Eldar, Lingxiao Zhao
We unroll an iterative denoising algorithm by mapping each iteration into a single network layer where the feed-forward process is equivalent to iteratively denoising graph signals.
no code implementations • ICLR 2020 • Vassilis N. Ioannidis, Siheng Chen, Georgios B. Giannakis
Graph convolutional networks (GCNs) have achieved remarkable performance in a variety of network science learning tasks.
1 code implementation • 17 Mar 2020 • Maosen Li, Siheng Chen, Yangheng Zhao, Ya zhang, Yan-Feng Wang, Qi Tian
The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning.
1 code implementation • CVPR 2020 • Pengxiang Wu, Siheng Chen, Dimitris Metaxas
The backbone of MotionNet is a novel spatio-temporal pyramid network, which extracts deep spatial and temporal features in a hierarchical fashion.
1 code implementation • CVPR 2020 • Yue Hu, Siheng Chen, Ya zhang, Xiao Gu
Motion prediction is essential and challenging for autonomous vehicles and social robots.
no code implementations • 1 Mar 2020 • Siheng Chen, Baoan Liu, Chen Feng, Carlos Vallespi-Gonzalez, Carl Wellington
We present a review of 3D point cloud processing and learning for autonomous driving.
no code implementations • 6 Feb 2020 • Jingxiao Liu, Bingqing Chen, Siheng Chen, Mario Berges, Jacobo Bielak, HaeYoung Noh
We introduce a physics-guided signal processing approach to extract a damage-sensitive and domain-invariant (DS & DI) feature from acceleration response data of a vehicle traveling over a bridge to assess bridge health.
no code implementations • 27 Jan 2020 • Vassilis N. Ioannidis, Siheng Chen, Georgios B. Giannakis
The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs.
no code implementations • 5 Oct 2019 • Maosen Li, Siheng Chen, Xu Chen, Ya zhang, Yan-Feng Wang, Qi Tian
For the backbone, we propose multi-branch multi-scale graph convolution networks to extract spatial and temporal features.
Ranked #22 on
Skeleton Based Action Recognition
on NTU RGB+D
2 code implementations • 23 Jul 2019 • Xu Chen, Siheng Chen, Huangjie Zheng, Jiangchao Yao, Kenan Cui, Ya zhang, Ivor W. Tsang
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
no code implementations • 26 Jun 2019 • Siheng Chen, Sufeng. Niu, Tian Lan, Baoan Liu
We present a novel graph-neural-network-based system to effectively represent large-scale 3D point clouds with the applications to autonomous driving.
no code implementations • 11 May 2019 • Siheng Chen, Chaojing Duan, Yaoqing Yang, Duanshun Li, Chen Feng, Dong Tian
The experimental results show that (1) the proposed networks outperform the state-of-the-art methods in various tasks; (2) a graph topology can be inferred as auxiliary information without specific supervision on graph topology inference; and (3) graph filtering refines the reconstruction, leading to better performances.
no code implementations • 30 Apr 2019 • Chuan Wen, Jie Chang, Ya zhang, Siheng Chen, Yan-Feng Wang, Mei Han, Qi Tian
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.
1 code implementation • CVPR 2019 • Maosen Li, Siheng Chen, Xu Chen, Ya zhang, Yan-Feng Wang, Qi Tian
We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics.
1 code implementation • 9 Apr 2019 • Chaojing Duan, Siheng Chen, Jelena Kovacevic
NPD algorithm uses a neural network to estimate reference planes for points in noisy point clouds.
1 code implementation • 8 Jun 2017 • Sufeng. Niu, Siheng Chen, Hanyu Guo, Colin Targonski, Melissa C. Smith, Jelena Kovačević
GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs.
no code implementations • 11 Feb 2017 • Siheng Chen, Dong Tian, Chen Feng, Anthony Vetro, Jelena Kovačević
We use a general feature-extraction operator to represent application-dependent features and propose a general reconstruction error to evaluate the quality of resampling.
no code implementations • 16 Dec 2015 • Siheng Chen, Rohan Varma, Aarti Singh, Jelena Kovačević
For each class, we provide an explicit definition of the graph signals and construct a corresponding graph dictionary with desirable properties.
no code implementations • 21 Jul 2015 • Siheng Chen, Rohan Varma, Aarti Singh, Jelena Kovačević
In this paper, we consider a statistical problem of learning a linear model from noisy samples.
no code implementations • 21 Apr 2015 • Siheng Chen, Rohan Varma, Aarti Singh, Jelena Kovačević
We study signal recovery on graphs based on two sampling strategies: random sampling and experimentally designed sampling.
no code implementations • 26 Nov 2014 • Siheng Chen, Aliaksei Sandryhaila, José M. F. Moura, Jelena Kovačević
We consider the problem of signal recovery on graphs as graphs model data with complex structure as signals on a graph.