no code implementations • 13 Mar 2024 • Wensheng Liang, Ruiyan Zhuang, Xianwei Shi, Shuai Li, Zhicheng Wang, Xiaoguang Ma
Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high costs and poor real-time performance.
1 code implementation • ACM International Conference on Multimedia 2022 • Zihua Liu, Songyan Zhang, Zhicheng Wang, Masatoshi Okutomi
To enhance geometric consistency, especially in low-texture regions, the estimated normal map is then leveraged to calculate a local affinity matrix, providing the residual learning with information about where the correction should refer and thus improving the residual learning efficiency.
no code implementations • 11 Dec 2023 • Haotian Zhang, Semujju Stuart Dereck, Zhicheng Wang, Xianwei Lv, Kang Xu, Liang Wu, Ye Jia, Jing Wu, Zhuo Long, Wensheng Liang, X. G. Ma, Ruiyan Zhuang
Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods.
no code implementations • 30 Oct 2023 • Bin Lin, Zhiping Mao, Zhicheng Wang, George Em Karniadakis
Initially, we utilize DeepONet to learn the solution operator for a set of smooth problems relevant to the PDEs characterized by sharp solutions.
1 code implementation • 8 May 2023 • Zhicheng Wang, Liwen Xiao, Zhiguo Cao, Hao Lu
This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature similarity, leading to an extract-then-match paradigm.
Ranked #2 on Object Counting on FSC147
1 code implementation • CVPR 2023 • Lixin Yang, Jian Xu, Licheng Zhong, Xinyu Zhan, Zhicheng Wang, Kejian Wu, Cewu Lu
Enable neural networks to capture 3D geometrical-aware features is essential in multi-view based vision tasks.
no code implementations • 16 Dec 2022 • Tianyu Shi, Zhicheng Wang, Liyin Xiao, Cong Liu
Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders.
1 code implementation • 30 Nov 2022 • Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model.
no code implementations • 3 Nov 2022 • Zhicheng Wang, Tianyu Shi, Cong Liu
In constituency parsing, span-based decoding is an important direction.
no code implementations • 1 Nov 2022 • Zhicheng Wang, Tianyu Shi, Liyin Xiao, Cong Liu
We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing.
1 code implementation • 19 Aug 2022 • Han Sun, Zhaoxin Fan, Zhenbo Song, Zhicheng Wang, Kejian Wu, Jianfeng Lu
The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of a point cloud based detector for monocular detector during the training period.
no code implementations • 20 Apr 2022 • Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important.
no code implementations • 4 Apr 2022 • Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications.
1 code implementation • 25 Nov 2021 • Sen yang, Zhicheng Wang, Ze Chen, YanJie Li, Shoukui Zhang, Zhibin Quan, Shu-Tao Xia, Yiping Bao, Erjin Zhou, Wankou Yang
This paper presents a new method to solve keypoint detection and instance association by using Transformer.
Ranked #10 on Multi-Person Pose Estimation on MS COCO
no code implementations • 20 Nov 2021 • Zhaoxin Fan, Zhengbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
ACR-Pose consists of a Reconstructor and a Discriminator.
no code implementations • 22 Aug 2021 • Xiaohu Jiang, Ze Chen, Zhicheng Wang, Erjin Zhou, ChunYuan
After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads.
no code implementations • 22 Jul 2021 • Zhengxiong Luo, Zhicheng Wang, Yan Huang, Liang Wang, Tieniu Tan, Erjin Zhou
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
3 code implementations • 7 Jul 2021 • YanJie Li, Sen yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, Shu-Tao Xia
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
1 code implementation • 8 Jun 2021 • Yang Hu, Haoxuan You, Zhecan Wang, Zhicheng Wang, Erjin Zhou, Yue Gao
Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data.
no code implementations • 21 May 2021 • Jinshuo Zhang, Zhicheng Wang, Songyan Zhang, Gang Wei
Domain shift has always been one of the primary issues in video object segmentation (VOS), for which models suffer from degeneration when tested on unfamiliar datasets.
no code implementations • 20 May 2021 • Shengze Cai, Zhiping Mao, Zhicheng Wang, Minglang Yin, George Em Karniadakis
Despite the significant progress over the last 50 years in simulating flow problems using numerical discretization of the Navier-Stokes equations (NSE), we still cannot incorporate seamlessly noisy data into existing algorithms, mesh-generation is complex, and we cannot tackle high-dimensional problems governed by parametrized NSE.
1 code implementation • ICCV 2021 • YanJie Li, Shoukui Zhang, Zhicheng Wang, Sen yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou
Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.
no code implementations • 7 Apr 2021 • Mingyang Shang, Dawei Xiang, Zhicheng Wang, Erjin Zhou
V2F-Net consists of two sub-networks: Visible region Detection Network (VDN) and Full body Estimation Network (FEN).
Ranked #1 on Object Detection on CityPersons
no code implementations • 30 Mar 2021 • Lianru Gao, Zhicheng Wang, Lina Zhuang, Haoyang Yu, Bing Zhang, Jocelyn Chanussot
Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image.
1 code implementation • CVPR 2021 • Xing Dai, Zeren Jiang, Zhao Wu, Yiping Bao, Zhicheng Wang, Si Liu, Erjin Zhou
In recent years, knowledge distillation has been proved to be an effective solution for model compression.
1 code implementation • CVPR 2021 • Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, Thomas Funkhouser
Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes.
4 code implementations • 9 Feb 2021 • Lu Lu, Raphael Pestourie, Wenjie Yao, Zhicheng Wang, Francesc Verdugo, Steven G. Johnson
We achieve the same objective as conventional PDE-constrained optimization methods based on adjoint methods and numerical PDE solvers, but find that the design obtained from hPINN is often simpler and smoother for problems whose solution is not unique.
1 code implementation • CVPR 2021 • Zhengxiong Luo, Zhicheng Wang, Yan Huang, Tieniu Tan, Erjin Zhou
However, for bottom-up methods, which need to handle a large variance of human scales and labeling ambiguities, the current practice seems unreasonable.
no code implementations • 13 Dec 2020 • Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, GuanAn Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
no code implementations • 1 Nov 2020 • Zhicheng Wang, Anqiao Li, Yixiao Zheng, Anhuan Xie, Zhibin Li, Jun Wu, Qiuguo Zhu
The NN based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.
no code implementations • CVPR 2021 • Songyan Zhang, Zhicheng Wang, Qiang Wang, Jinshuo Zhang, Gang Wei, Xiaowen Chu
Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption and slow inference speed.
no code implementations • 7 Sep 2020 • Xi Gu, Lingbin Kong, Zhicheng Wang, Jie Li, Zhaohui Yu, Gang Wei
On the DOTA dataset, CenterFPANet mAP is 64. 00%, and FPS is 22. 2, which is close to the accuracy of the anchor-based methods currently used and much faster than them.
2 code implementations • CVPR 2020 • Guan'an Wang, Shuo Yang, Huanyu Liu, Zhicheng Wang, Yang Yang, Shuliang Wang, Gang Yu, Erjin Zhou, Jian Sun
When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.
4 code implementations • ECCV 2020 • Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, Jian Sun
To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.
Ranked #1 on Keypoint Detection on COCO test-challenge
no code implementations • 19 Nov 2019 • Zhiqiang Xiong, Zhicheng Wang, Zhaohui Yu, Xi Gu
In this paper, we differentiate features for scene segmentation based on dedicated attention mechanisms (DF-DAM), and two attention modules are proposed to optimize the high-level and low-level features in the encoder, respectively.
7 code implementations • 1 Jan 2019 • Wenbo Li, Zhicheng Wang, Binyi Yin, Qixiang Peng, Yuming Du, Tianzi Xiao, Gang Yu, Hongtao Lu, Yichen Wei, Jian Sun
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods.
Ranked #1 on Pose Estimation on COCO minival
1 code implementation • 26 Aug 2018 • Maziar Raissi, Zhicheng Wang, Michael S. Triantafyllou, George Em. Karniadakis
Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field.
5 code implementations • CVPR 2018 • Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, Jian Sun
In this paper, we present a novel network structure called Cascaded Pyramid Network (CPN) which targets to relieve the problem from these "hard" keypoints.
Ranked #4 on Keypoint Detection on COCO test-challenge
no code implementations • CVPR 2016 • Gang Wang, Zhicheng Wang, Yufei Chen, Qiangqiang Zhou, Weidong Zhao
Point set registration (PSR) is a fundamental problem in computer vision and pattern recognition, and it has been successfully applied to many applications.