no code implementations • 17 Apr 2024 • Weiyu Guo, Ziyue Qiao, Ying Sun, Hui Xiong
We propose a Short Term Enhancement Module(STEM) which can be easily integrated with various models.
no code implementations • 1 Apr 2024 • Zelin He, Ying Sun, Jingyuan Liu, Runze Li
Nonasymptotic bound is provided for the estimation error of the target model, showing the robustness of the proposed method to covariate shifts.
no code implementations • 23 Mar 2024 • Tongle Wu, Ying Sun
Specifically, for $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT achieves communication complexity $\tilde{\mathcal{O}} \Big(\frac{L}{\mu K} + \frac{\delta}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$, where $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local loss.
no code implementations • 20 Mar 2024 • Zelin He, Ying Sun, Jingyuan Liu, Runze Li
We consider the transfer learning problem in the high dimensional setting, where the feature dimension is larger than the sample size.
1 code implementation • 5 Mar 2024 • Ying Sun, Hongwei Yong, Lei Zhang
Compared with first-order optimizers, it adopts a certain amount of information from the Hessian matrix to assist optimization, while compared with the existing second-order optimizers, it keeps the good generalization performance of first-order optimizers.
no code implementations • 26 Jan 2024 • Ángel López-Oriona, Ying Sun, Rosa M. Crujeiras
Time series clustering is an essential machine learning task with applications in many disciplines.
no code implementations • 31 Oct 2023 • Fen Fang, Yi Cheng, Ying Sun, Qianli Xu
In this report, we present our approach to the EPIC-KITCHENS VISOR Hand Object Segmentation Challenge, which focuses on the estimation of the relation between the hands and the objects given a single frame as input.
no code implementations • 27 Sep 2023 • Ying Sun, HengShu Zhu, Hui Xiong
Self-interpreting neural networks have garnered significant interest in research.
no code implementations • 25 Jul 2023 • Yi Cheng, Hehe Fan, Dongyun Lin, Ying Sun, Mohan Kankanhalli, Joo-Hwee Lim
The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions.
no code implementations • 16 Jul 2023 • Pratik Nag, Ying Sun, Brian J Reich
Large-scale spatial interpolation or downscaling of bivariate wind fields having velocity in two dimensions is a challenging task because wind data tend to be non-Gaussian with high spatial variability and heterogeneity.
no code implementations • 13 Jul 2023 • Yi Cheng, Ziwei Xu, Fen Fang, Dongyun Lin, Hehe Fan, Yongkang Wong, Ying Sun, Mohan Kankanhalli
Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.
no code implementations • 3 Jul 2023 • Chuan Qin, Le Zhang, Rui Zha, Dazhong Shen, Qi Zhang, Ying Sun, Chen Zhu, HengShu Zhu, Hui Xiong
To this end, we present an up-to-date and comprehensive survey on AI technologies used for talent analytics in the field of human resource management.
1 code implementation • 30 Jun 2023 • Zenglin Shi, Ying Sun, Mengmi Zhang
However, the vanilla mask generation method of SAM lacks class-specific information in the masks, resulting in inferior counting accuracy.
Ranked #1 on Object Counting on PASCAL VOC
1 code implementation • 20 Jun 2023 • Pratik Nag, Yiping Hong, Sameh Abdulah, Ghulam A. Qadir, Marc G. Genton, Ying Sun
Fitting a Gaussian process with a nonstationary Mat\'ern covariance is challenging.
no code implementations • 20 Jun 2023 • Pratik Nag, Ying Sun, Brian J Reich
Gaussian processes (GP) and Kriging are widely used in traditional spatio-temporal mod-elling and prediction.
no code implementations • CVPR 2023 • Li Xu, Mark He Huang, Xindi Shang, Zehuan Yuan, Ying Sun, Jun Liu
Then, following a novel meta optimization scheme to optimize the model to obtain good testing performance on the virtual testing sets after training on the virtual training set, our framework can effectively drive the model to better capture semantics and visual representations of individual concepts, and thus obtain robust generalization performance even when handling novel compositions.
2 code implementations • 18 Mar 2023 • Firas Al-Hindawi, Md Mahfuzur Rahman Siddiquee, Teresa Wu, Han Hu, Ying Sun
Cross-domain classification frameworks were developed to handle this data domain shift problem by utilizing unsupervised image-to-image translation models to translate an input image from the unlabeled domain to the labeled domain.
no code implementations • 29 Jan 2023 • Yi Cheng, Dongyun Lin, Fen Fang, Hao Xuan Woon, Qianli Xu, Ying Sun
In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022.
1 code implementation • CVPR 2023 • Hongwei Yong, Ying Sun, Lei Zhang
Though the full-matrix preconditioned gradient methods theoretically have a lower regret bound, they are impractical for use to train DNNs because of the high complexity.
no code implementations • 18 Dec 2022 • Firas Al-Hindawi, Tejaswi Soori, Han Hu, Md Mahfuzur Rahman Siddiquee, Hyunsoo Yoon, Teresa Wu, Ying Sun
To deal with datasets from new domains a model needs to be trained from scratch.
1 code implementation • ICCV 2023 • Parantak Singh, You Li, Ankur Sikarwar, Weixian Lei, Daniel Gao, Morgan Bruce Talbot, Ying Sun, Mike Zheng Shou, Gabriel Kreiman, Mengmi Zhang
For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication.
no code implementations • 21 Nov 2022 • Zenglin Shi, Ying Sun, Joo Hwee Lim, Mengmi Zhang
To the best of our knowledge, no existing technique can accomplish all of these objectives simultaneously.
no code implementations • 15 Aug 2022 • Duan Zhang, Ying Sun
It is verified that the type that a given lower triangular form belongs to is invariant under any lower triangular coordinate transformation.
no code implementations • 16 Jul 2022 • Joshua Fan, Di Chen, Jiaming Wen, Ying Sun, Carla P. Gomes
This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e. g. 30m, a 100x increase).
no code implementations • 8 Jul 2022 • Yan Huang, Ying Sun, Zehan Zhu, Changzhi Yan, Jinming Xu
We develop a general framework unifying several gradient-based stochastic optimization methods for empirical risk minimization problems both in centralized and distributed scenarios.
no code implementations • 3 Jun 2022 • Yi Cheng, Fen Fang, Ying Sun
Based on an existing method for video domain adaptation, i. e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition.
no code implementations • 24 May 2022 • Qianli Xu, Nicolas Gauthier, Wenyu Liang, Fen Fang, Hui Li Tan, Ying Sun, Yan Wu, Liyuan Li, Joo-Hwee Lim
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive.
no code implementations • 21 May 2022 • Dong Wei, Ying Sun, Sim-Heng Ong, Ping Chai, Lynette L. Teo, Adrian F. Low
We have also tested the robustness of the framework with respect to varied a priori segmentation in both practical and simulated settings.
no code implementations • 21 May 2022 • Dong Wei, Ying Sun, Sim-Heng Ong, Ping Chai, Lynette L Teo, Adrian F Low
To achieve accurate quantification, LGE CMR images need to be processed in two steps: segmentation of the myocardium followed by classification of infarcts within the segmented myocardium.
no code implementations • 21 May 2022 • Dong Wei, Ying Sun, Ping Chai, Adrian Low, Sim Heng Ong
Automatic segmentation of myocardium in Late Gadolinium Enhanced (LGE) Cardiac MR (CMR) images is often difficult due to the intensity heterogeneity resulting from accumulation of contrast agent in infarcted areas.
no code implementations • 20 Apr 2022 • Yuening Wang, Ying Sun, Jie Yuan, Kexin Gan, Hanzi Xu, Han Gao, Xiuming Zhang
Experiments on patient dataset reveal that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in sparing BM of cervical cancer radiotherapy.
no code implementations • 21 Jan 2022 • Ying Sun, Marie Maros, Gesualdo Scutari, Guang Cheng
Our theory shows that, under standard notions of restricted strong convexity and smoothness of the loss functions, suitable conditions on the network connectivity and algorithm tuning, the distributed algorithm converges globally at a {\it linear} rate to an estimate that is within the centralized {\it statistical precision} of the model, $O(s\log d/N)$.
no code implementations • CVPR 2022 • Hehe Fan, Xiaojun Chang, Wanyue Zhang, Yi Cheng, Ying Sun, Mohan Kankanhalli
In this paper, we propose an unsupervised domain adaptation method for deep point cloud representation learning.
1 code implementation • NeurIPS 2021 • Ying Sun, HengShu Zhu, Chuan Qin, Fuzhen Zhuang, Qing He, Hui Xiong
To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).
no code implementations • 28 Nov 2021 • Kenan E. Ak, Joo Hwee Lim, Ying Sun, Jo Yew Tham, Ashraf A. Kassim
A key challenge in e-commerce is that images have multiple attributes where users would like to manipulate and it is important to estimate discriminative feature representations for each of these attributes.
no code implementations • 12 Nov 2021 • Yao Ji, Gesualdo Scutari, Ying Sun, Harsha Honnappa
First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates.
no code implementations • ICLR 2022 • Yuanxiong Guo, Ying Sun, Rui Hu, Yanmin Gong
Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data.
no code implementations • 11 May 2021 • Yongchun Zhu, Ruobing Xie, Fuzhen Zhuang, Kaikai Ge, Ying Sun, Xu Zhang, Leyu Lin, Juan Cao
The cold item ID embedding has two main problems: (1) A gap is existing between the cold ID embedding and the deep model.
no code implementations • 4 Jan 2021 • Akira Horiguchi, Thomas J. Santner, Ying Sun, Matthew T. Pratola
This article proposes Pareto Front (PF) and Pareto Set (PS) estimation methods using Bayesian Additive Regression Trees (BART), which is a non-parametric model whose assumptions are typically less restrictive than popular alternatives, such as Gaussian Processes (GPs).
1 code implementation • 23 Jul 2020 • Wanfang Chen, Yuxiao Li, Brian J. Reich, Ying Sun
Kriging provides the best linear unbiased predictor using covariance functions and is often associated with Gaussian processes.
1 code implementation • 23 Oct 2019 • Jinming Xu, Ye Tian, Ying Sun, Gesualdo Scutari
This paper proposes a novel family of primal-dual-based distributed algorithms for smooth, convex, multi-agent optimization over networks that uses only gradient information and gossip communications.
1 code implementation • 16 Oct 2019 • Tianbo Chen, Ying Sun, Ta-Hsin Li
At each quantile level, we approximate the quantile spectrum by a function in the form of an ordinary AR spectrum.
Methodology Applications
no code implementations • 24 Sep 2019 • Yi Cheng, Hongyuan Zhu, Ying Sun, Cihan Acar, Wei Jing, Yan Wu, Liyuan Li, Cheston Tan, Joo-Hwee Lim
To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation.
no code implementations • 17 Aug 2018 • Amir Daneshmand, Ying Sun, Gesualdo Scutari, Francisco Facchinei, Brian M. Sadler
This paper studies Dictionary Learning problems wherein the learning task is distributed over a multi-agent network, modeled as a time-varying directed graph.
2 code implementations • 8 Sep 2017 • Alexander Litvinenko, Ying Sun, Marc G. Genton, David Keyes
We use available measurements to estimate the unknown parameters (variance, smoothness parameter, and covariance length) of a covariance function by maximizing the joint Gaussian log-likelihood function.
Computation 62F99, 62P12, 62M30 G.3; G.4; J.2
no code implementations • 12 Feb 2016 • Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar
In addition, we propose a method to improve the covariance estimation problem when its underlying eigenvectors are known to be sparse.
no code implementations • 17 Jun 2015 • Ying Sun, Prabhu Babu, Daniel P. Palomar
This paper considers the problem of robustly estimating a structured covariance matrix with an elliptical underlying distribution with known mean.