no code implementations • 28 Aug 2014 • Chao Zhang, DaCheng Tao, Tao Hu, Xiang Li
We are mainly concerned with two theoretical questions: 1) under what conditions does RMTL perform better with a smaller task sample size than STL?
no code implementations • 24 Nov 2015 • Dekang Zhu, Dan P. Guralnik, Xuezhi Wang, Xiang Li, Bill Moran
Distance-based hierarchical clustering (HC) methods are widely used in unsupervised data analysis but few authors take account of uncertainty in the distance data.
no code implementations • 25 Nov 2015 • Dekang Zhu, Dan P. Guralnik, Xuezhi Wang, Xiang Li, Bill Moran
We derive a statistical model for estimation of a dendrogram from single linkage hierarchical clustering (SLHC) that takes account of uncertainty through noise or corruption in the measurements of separation of data.
no code implementations • ICCV 2015 • Wei-Shi Zheng, Xiang Li, Tao Xiang, Shengcai Liao, Jian-Huang Lai, Shaogang Gong
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views.
no code implementations • ICCV 2015 • Xiang Li, Wei-Shi Zheng, Xiaojuan Wang, Tao Xiang, Shaogang Gong
In real world person re-identification (re-id), images of people captured at very different resolutions from different locations need be matched.
no code implementations • 15 Apr 2016 • Xiang Li, Lili Mou, Rui Yan, Ming Zhang
In this paper, we propose StalemateBreaker, a conversation system that can proactively introduce new content when appropriate.
no code implementations • 26 Apr 2016 • Shangxuan Wu, Ying-Cong Chen, Xiang Li, An-Cong Wu, Jin-Jie You, Wei-Shi Zheng
In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features.
no code implementations • CVPR 2016 • Jin-Jie You, An-Cong Wu, Xiang Li, Wei-Shi Zheng
Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the occlusion, pose and camera-view change, and lighting variation problems.
2 code implementations • 23 Oct 2016 • Yiping Song, Rui Yan, Xiang Li, Dongyan Zhao, Ming Zhang
In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain.
no code implementations • NeurIPS 2016 • Xiang Li, Tao Qin, Jian Yang, Tie-Yan Liu
Based on the 2-Component shared embedding, we design a new RNN algorithm and evaluate it using the language modeling task on several benchmark datasets.
4 code implementations • ICLR 2019 • Zhengdao Chen, Xiang Li, Joan Bruna
We show that, in a data-driven manner and without access to the underlying generative models, they can match or even surpass the performance of the belief propagation algorithm on binary and multi-class stochastic block models, which is believed to reach the computational threshold.
Ranked #1 on Community Detection on Amazon (Accuracy-NE metric, using extra training data)
no code implementations • 29 May 2017 • Songting Shi, Xiang Li, Arkadiusz Sitek, Quanzheng Li
In this article, we derive a Bayesian model to learning the sparse and low rank PARAFAC decomposition for the observed tensor with missing values via the elastic net, with property to find the true rank and sparse factor matrix which is robust to the noise.
no code implementations • CVPR 2017 • Yasushi Makihara, Atsuyuki Suzuki, Daigo Muramatsu, Xiang Li, Yasushi Yagi
This paper describes a joint intensity metric learning method to improve the robustness of gait recognition with silhouette-based descriptors such as gait energy images.
no code implementations • 19 Jul 2017 • Xiang Li, Aoxiao Zhong, Ming Lin, Ning Guo, Mu Sun, Arkadiusz Sitek, Jieping Ye, James Thrall, Quanzheng Li
However, the development of a robust and reliable deep learning model for computer-aided diagnosis is still highly challenging due to the combination of the high heterogeneity in the medical images and the relative lack of training samples.
no code implementations • 21 Jul 2017 • Seongah Jeong, Xiang Li, Jiarui Yang, Quanzheng Li, Vahid Tarokh
In order to address the limitations of the unsupervised DLSC-based fMRI studies, we utilize the prior knowledge of task paradigm in the learning step to train a data-driven dictionary and to model the sparse representation.
no code implementations • 31 Jul 2017 • Jing Mei, Eryu Xia, Xiang Li, Guotong Xie
Precision medicine requires the precision disease risk prediction models.
no code implementations • 1 Aug 2017 • Xiang Li, Luke Vilnis, Andrew McCallum
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints.
1 code implementation • 11 Sep 2017 • Xuan Peng, Xunzhang Gao, Xiang Li
To break this dependency between neighboring hidden units and speed up the convergence of training, a novel training strategy is proposed.
no code implementations • 23 Oct 2017 • Mo Zhang, Xiang Li, Mengjia Xu, Quanzheng Li
Reliable cell segmentation and classification from biomedical images is a crucial step for both scientific research and clinical practice.
no code implementations • 31 Oct 2017 • Zhe Guo, Xiang Li, Heng Huang, Ning Guo, Quanzheng Li
Image analysis using more than one modality (i. e. multi-modal) has been increasingly applied in the field of biomedical imaging.
no code implementations • 6 Dec 2017 • Le Hui, Xiang Li, Jiaxin Chen, Hongliang He, Chen Gong, Jian Yang
Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays.
4 code implementations • CVPR 2018 • Jifeng Wang, Xiang Li, Le Hui, Jian Yang
Specifically, a shadow image is fed into the first generator which produces a shadow detection mask.
Ranked #3 on RGB Salient Object Detection on ISTD
4 code implementations • 8 Jan 2018 • Han Zhu, Xiang Li, Pengye Zhang, Guozheng Li, Jie He, Han Li, Kun Gai
In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult.
4 code implementations • CVPR 2019 • Xiang Li, Shuo Chen, Xiaolin Hu, Jian Yang
Theoretically, we find that Dropout would shift the variance of a specific neural unit when we transfer the state of that network from train to test.
1 code implementation • 31 Jan 2018 • Xi Cheng, Xiang Li, Ying Tai, Jian Yang
Single image super resolution is a very important computer vision task, with a wide range of applications.
Ranked #34 on Image Super-Resolution on BSD100 - 4x upscaling
2 code implementations • 3 Feb 2018 • Zixiang Ding, Rui Xia, Jianfei Yu, Xiang Li, Jian Yang
Deep neural networks have recently been shown to achieve highly competitive performance in many computer vision tasks due to their abilities of exploring in a much larger hypothesis space.
1 code implementation • 6 Feb 2018 • Wenhai Wang, Xiang Li, Jian Yang, Tong Lu
Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link").
no code implementations • 9 Feb 2018 • Shuo Chen, Chen Gong, Jian Yang, Xiang Li, Yang Wei, Jun Li
In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.
9 code implementations • NeurIPS 2018 • Robert J. Wang, Xiang Li, Charles X. Ling
In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead.
no code implementations • ACL 2018 • Luke Vilnis, Xiang Li, Shikhar Murty, Andrew McCallum
Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE) (Vendrov et al., 2016), are a natural way to model transitive relational data (e. g. entailment graphs).
no code implementations • 28 May 2018 • Yabo Ni, Dan Ou, Shichen Liu, Xiang Li, Wenwu Ou, An-Xiang Zeng, Luo Si
In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization.
no code implementations • 31 May 2018 • Yu Zhao, Xiang Li, Wei zhang, Shijie Zhao, Milad Makkie, Mo Zhang, Quanzheng Li, Tianming Liu
Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cognitive neuroscience and medical image analysis.
9 code implementations • 7 Jun 2018 • Xiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang
To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance.
Ranked #12 on Scene Text Detection on ICDAR 2017 MLT
1 code implementation • IEEE International Conference on Mobile Data Management (MDM) 2018 • Yijun Su, Xiang Li, Wei Tang, Ji Xiang, Yuanye He
In this paper, we propose a unified location prediction framework to integrate the effect of history check-in and the influence of social circles.
no code implementations • ECCV 2018 • Xiang Li, An-Cong Wu, Wei-Shi Zheng
The main idea is learning to attack feature extractor on the target people by using GAN to generate very target-like images (imposters), and in the meantime the model will make the feature extractor learn to tolerate the attack by discriminative learning so as to realize group-based verification.
1 code implementation • COLING 2018 • Zikun Hu, Xiang Li, Cunchao Tu, Zhiyuan Liu, Maosong Sun
Specifically, our model outperforms other baselines by more than 50{\%} in the few-shot scenario.
no code implementations • 6 Aug 2018 • Jiasha Liu, Xiang Li, Hui Ren, Quanzheng Li
The framework combines two 1st-level modules: direct estimation module and a segmentation module.
no code implementations • ECCV 2018 • Zhen-Yu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang
In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks.
Ranked #76 on Semantic Segmentation on NYU Depth v2
no code implementations • 1 Oct 2018 • Xiang Li, Qitian Chen, Xing Wang, Ning Guo, Nan Wu, Quanzheng Li
In this work, we developed a network inference method from incomplete data ("PathInf") , as massive and non-uniformly distributed missing values is a common challenge in practical problems.
no code implementations • 8 Oct 2018 • Xi Cheng, Xiang Li, Jian Yang
Single image super resolution is of great importance as a low-level computer vision task.
no code implementations • 17 Oct 2018 • Jing Mei, Shiwan Zhao, Feng Jin, Eryu Xia, Haifeng Liu, Xiang Li
In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention.
2 code implementations • ICLR 2018 • Zhengdao Chen, Xiang Li, Joan Bruna
This graph inference task can be recast as a node-wise graph classification problem, and, as such, computational detection thresholds can be translated in terms of learning within appropriate models.
no code implementations • 2 Nov 2018 • Xiang Li, Haiyang Xue, Wei Chen, Yang Liu, Yang Feng, Qun Liu
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
1 code implementation • 3 Dec 2018 • Jie Zhao, Quanzheng Li, Xiang Li, Hongfeng Li, Li Zhang
Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image.
1 code implementation • 17 Dec 2018 • Xiang Li, Shihao Ji
The proposed method is generic and can defend white-box and black-box attacks without the need of retraining the original CNN classifiers, and can further strengthen the defense by retraining CNN or end-to-end finetuning the whole pipeline.
no code implementations • 18 Dec 2018 • Jiechao Ma, Xiang Li, Hongwei Li, Bjoern H. Menze, Sen Liang, Rongguo Zhang, Wei-Shi Zheng
In this paper, we propose a novel and effective abnormality detector implementing the attention mechanism and group convolution on 3D single-shot detector (SSD) called group-attention SSD (GA-SSD).
Computed Tomography (CT) Finding Pulmonary Nodules In Large-Scale Ct Images
no code implementations • 13 Feb 2019 • Xiang Li, Shusen Wang, Zhihua Zhang
Subsampled Newton methods approximate Hessian matrices through subsampling techniques, alleviating the cost of forming Hessian matrices but using sufficient curvature information.
1 code implementation • NeurIPS 2019 • Han Zhu, Daqing Chang, Ziru Xu, Pengye Zhang, Xiang Li, Jie He, Han Li, Jian Xu, Kun Gai
The previous work Tree-based Deep Model (TDM) \cite{zhu2018learning} greatly improves recommendation accuracy using tree index.
1 code implementation • 25 Feb 2019 • Yuan Hu, Yunpeng Chen, Xiang Li, Jiashi Feng
In this work, we propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations adaptively.
no code implementations • NeurIPS 2019 • Xiang Li, Wenhao Yang, Zhihua Zhang
We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term.
20 code implementations • CVPR 2019 • Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang
A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches.
Ranked #98 on Image Classification on CIFAR-100 (using extra training data)
19 code implementations • CVPR 2019 • Wenhai Wang, Enze Xie, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu, Shuai Shao
Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.
Ranked #12 on Scene Text Detection on SCUT-CTW1500
1 code implementation • 2 Apr 2019 • Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang
In contrast, the proposed point registration neural network (PR-Net) actively learns the registration pattern as a parametric function from a training dataset, consequently predict the desired geometric transformation to align a pair of point sets.
2 code implementations • ACL 2019 • Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.
no code implementations • 18 Apr 2019 • Ying Wang, Xiao Xu, Tao Jin, Xiang Li, Guotong Xie, Jian-Min Wang
In addition, for unordered medical activity set, existing medical RL methods utilize a simple pooling strategy, which would result in indistinguishable contributions among the activities for learning.
no code implementations • ICLR 2019 • Xiang Li, Luke Vilnis, Dongxu Zhang, Michael Boratko, Andrew McCallum
However, the hard edges of the boxes present difficulties for standard gradient based optimization; that work employed a special surrogate function for the disjoint case, but we find this method to be fragile.
3 code implementations • 23 May 2019 • Xiang Li, Xiaolin Hu, Jian Yang
The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features.
Ranked #739 on Image Classification on ImageNet
no code implementations • 30 May 2019 • Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, Wei-Shi Zheng
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential.
3 code implementations • 7 Jun 2019 • Lingjing Wang, Xiang Li, Jianchun Chen, Yi Fang
In contrast to previous efforts (e. g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process.
no code implementations • 1 Jul 2019 • Jiechao Ma, Sen Liang, Xiang Li, Hongwei Li, Bjoern H. Menze, Rongguo Zhang, Wei-Shi Zheng
Mammogram is the most effective imaging modality for the mass lesion detection of breast cancer at the early stage.
2 code implementations • ICLR 2020 • Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang
In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data and establish a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.
no code implementations • 7 Jul 2019 • Mo Zhang, Jie Zhao, Xiang Li, Li Zhang, Quanzheng Li
Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale.
no code implementations • 26 Jul 2019 • Xiang Geng, Bin Gu, Xiang Li, Wanli Shi, Guansheng Zheng, Heng Huang
Specifically, to handle two types of data instances involved in S$^3$VM, TSGS$^3$VM samples a labeled instance and an unlabeled instance as well with the random features in each iteration to compute a triply stochastic gradient.
1 code implementation • CVPR 2020 • Xiang Li, Tianhan Wei, Yau Pun Chen, Yu-Wing Tai, Chi-Keung Tang
In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only.
Ranked #20 on Few-Shot Semantic Segmentation on FSS-1000 (5-shot)
no code implementations • 29 Jul 2019 • Wanli Shi, Bin Gu, Xiang Li, Xiang Geng, Heng Huang
To address this problem, in this paper, we propose a novel scalable quadruply stochastic gradient algorithm (QSG-S2AUC) for nonlinear semi-supervised AUC optimization.
1 code implementation • 9 Aug 2019 • Xiang Li, Shihao Ji
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited.
1 code implementation • 19 Aug 2019 • Congcong Wen, Lina Yang, Ling Peng, Xiang Li, Tianhe Chi
In this paper, we proposed a directionally constrained fully convolutional neural network (D-FCN) that can take the original 3D coordinates and LiDAR intensity as input; thus, it can directly apply to unstructured 3D point clouds for semantic labeling.
no code implementations • 21 Sep 2019 • Xiang Li, Jiechao Ma, Hongwei Li
In this study, we explore the fusion of the two kinds of features and claim that radiomics features can be complementary to deep-learning features.
no code implementations • 1 Oct 2019 • Jiaming Guo, Wei Qiu, Xiang Li, Xuandong Zhao, Ning Guo, Quanzheng Li
Imaging-based early diagnosis of Alzheimer Disease (AD) has become an effective approach, especially by using nuclear medicine imaging techniques such as Positron Emission Topography (PET).
no code implementations • CVPR 2020 • Xiang Li, Chen Lin, Chuming Li, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang
In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.
no code implementations • 7 Oct 2019 • Wei Qiu, Jiaming Guo, Xiang Li, Mengjia Xu, Mo Zhang, Ning Guo, Quanzheng Li
As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples.
no code implementations • 14 Oct 2019 • Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang
Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.
no code implementations • 21 Oct 2019 • Xiang Li, Wenhao Yang, Shusen Wang, Zhihua Zhang
Recently, the technique of local updates is a powerful tool in centralized settings to improve communication efficiency via periodical communication.
no code implementations • 27 Oct 2019 • Junyu Liu, Xiang Li, Jin Wang, Jiqiang Zhou, Jianxiong Shen
Recent breakthroughs made by deep learning rely heavily on large number of annotated samples.
no code implementations • 4 Nov 2019 • Caihua Shan, Leong Hou U, Nikos Mamoulis, Reynold Cheng, Xiang Li
The number of microtasks depends on the budget allocated for the problem.
no code implementations • 4 Nov 2019 • Caihua Shan, Nikos Mamoulis, Reynold Cheng, Guoliang Li, Xiang Li, Yuqiu Qian
In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms.
no code implementations • 12 Nov 2019 • Yabo Dan, Yong Zhao, Xiang Li, Shaobo Li, Ming Hu, Jianjun Hu
The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84. 5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules.
1 code implementation • NeurIPS 2019 • Jianchun Chen, Lingjing Wang, Xiang Li, Yi Fang
To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment.
no code implementations • 24 Dec 2019 • Zhou Zhai, Bin Gu, Xiang Li, Heng Huang
To address this challenge, in this paper, we propose two safe sample screening rules for RSVM based on the framework of concave-convex procedure (CCCP).
no code implementations • 6 Jan 2020 • Guangmo Tong, Ruiqi Wang, Chen Ling, Zheng Dong, Xiang Li
The well-known influence maximization problem aims at maximizing the influence of one information cascade in a social network by selecting appropriate seed users prior to the diffusion process.
Social and Information Networks
1 code implementation • ACL 2020 • Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
1 code implementation • AKBC 2020 • Dhruvesh Patel, Shib Sankar Dasgupta, Michael Boratko, Xiang Li, Luke Vilnis, Andrew McCallum
Box Embeddings [Vilnis et al., 2018, Li et al., 2019] represent concepts with hyperrectangles in $n$-dimensional space and are shown to be capable of modeling tree-like structures efficiently by training on a large subset of the transitive closure of the WordNet hypernym graph.
1 code implementation • 19 Feb 2020 • Xiang Li, Shusen Wang, Kun Chen, Zhihua Zhang
As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments.
no code implementations • 7 Mar 2020 • Xiang Li, Chao Wang, Jiwei Tan, Xiaoyi Zeng, Dan Ou, Bo Zheng
Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations.
1 code implementation • 9 Mar 2020 • Xiang Li, Peng Wang
Firstly, both communication parties establish a word vector table by training a deep learning model according to specified hyperparameters.
no code implementations • 20 Apr 2020 • Congcong Wen, Xiang Li, Xiaojing Yao, Ling Peng, Tianhe Chi
To achieve point cloud classification, previous studies proposed point cloud deep learning models that can directly process raw point clouds based on PointNet-like architectures.
1 code implementation • 3 May 2020 • Xiang Li, Songcan Chen
In aligning, we characterize the global and local structures of multiple labels to be high-rank and low-rank, respectively.
1 code implementation • 8 May 2020 • Xiang Li, Lin Zhang, Yau Pun Chen, Yu-Wing Tai, Chi-Keung Tang
Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited.
no code implementations • 20 May 2020 • Xin Hu, Zhijun Liu, Xiaofei Yu, Yulong Zhao, WenHua Chen, Biao Hu, Xuekun Du, Xiang Li, Mohamed Helaoui, Weidong Wang, Fadhel M. Ghannouchi
We design a pre-designed filter using the convolutional layer to extract the basis functions required for the PA forward or reverse modeling.
no code implementations • CVPR 2020 • Xiang Li, Yasushi Makihara, Chi Xu, Yasushi Yagi, Mingwu Ren
Existing gait recognition approaches typically focus on learning identity features that are invariant to covariates (e. g., the carrying status, clothing, walking speed, and viewing angle) and seldom involve learning features from the covariate aspect, which may lead to failure modes when variations due to the covariate overwhelm those due to the identity.
no code implementations • 4 Jun 2020 • Xiang Li, Mingyang Wang, Yi Fang
Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multi-view image matching.
1 code implementation • IEEE International Conference on Communications 2020 • Yijun Su, Xiang Li, Baoping Liu, Daren Zha, Ji Xiang, Wei Tang and Neng Gao.
With the popularity of location-based social networks (LBSNs), Point-of-Interest (POI) recommendation has become an essential location-based service to help people explore novel locations.
no code implementations • WS 2020 • Junxuan Chen, Xiang Li, Jiarui Zhang, Chulun Zhou, Jianwei Cui, Bin Wang, Jinsong Su
Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder.
7 code implementations • NeurIPS 2020 • Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #104 on Object Detection on COCO test-dev
1 code implementation • 8 Jun 2020 • Xiang Li, Ben Kao, Caihua Shan, Dawei Yin, Martin Ester
We study the problem of applying spectral clustering to cluster multi-scale data, which is data whose clusters are of various sizes and densities.
no code implementations • 10 Jun 2020 • Xiang Li, Lingjing Wang, Yi Fang
Recent studies have shown the benefits of using additional elevation data (e. g., DSM) for enhancing the performance of the semantic segmentation of aerial images.
no code implementations • 11 Jun 2020 • Lingjing Wang, Xiang Li, Yi Fang
Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment.
no code implementations • 14 Jun 2020 • Jingyu Deng, Xiang Li, Yi Fang
In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories.
no code implementations • 17 Jun 2020 • Lingjing Wang, Yi Shi, Xiang Li, Yi Fang
Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.
3 code implementations • 19 Jun 2020 • Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Depeng Jin, Yong Li
We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.
no code implementations • 24 Jun 2020 • Shuaihang Yuan, Xiang Li, Yi Fang
In this paper, we aim at handling the problem of 3D tracking, which provides the tracking of the consecutive frames of 3D shapes.
no code implementations • 24 Jun 2020 • Shuaihang Yuan, Xiang Li, Anthony Tzes, Yi Fang
To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time.
no code implementations • WS 2020 • Yuhui Sun, Mengxue Guo, Xiang Li, Jianwei Cui, Bin Wang
This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair.
no code implementations • 11 Jul 2020 • Dong Xu, Xiao Huang, Joseph Mango, Xiang Li, Zhenlong Li
We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping.
1 code implementation • IEEE International Joint Conference on Neural Network 2020 • Yijun Su, Jia-Dong Zhang, Xiang Li, Daren Zha, Ji Xiang, Wei Tang, and Neng Gao
Recent studies mainly utilize social information, categorical information and/or geographical information to supplement the highly sparse check-in data.
no code implementations • 25 Jul 2020 • Lingjing Wang, Xiang Li, Yi Fang
More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets.
no code implementations • 13 Aug 2020 • Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang
Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.
no code implementations • 14 Aug 2020 • Bin Gu, Zhiyuan Dang, Xiang Li, Heng Huang
In this paper, we focus on nonlinear learning with kernels, and propose a federated doubly stochastic kernel learning (FDSKL) algorithm for vertically partitioned data.
no code implementations • 15 Aug 2020 • Xiang Li, Yuan Tian, Fuyao Zhang, Shuxue Quan, Yi Xu
Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.
no code implementations • 11 Sep 2020 • Xiang Li, Lingjing Wang, Yi Fang
To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process.
no code implementations • 18 Sep 2020 • Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula
In recent years, the Natural Language Inference (NLI) task has garnered significant attention, with new datasets and models achieving near human-level performance on it.
no code implementations • 29 Sep 2020 • Lingjing Wang, Xiang Li, Yi Fang
Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.
no code implementations • 4 Oct 2020 • Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula
We transform the one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.
no code implementations • 21 Oct 2020 • Hao Huang, Lingjing Wang, Xiang Li, Yi Fang
In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.
no code implementations • 22 Oct 2020 • Lingjing Wang, Yu Hao, Xiang Li, Yi Fang
In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds.
no code implementations • 31 Oct 2020 • Wenhao Yang, Xiang Li, Guangzeng Xie, Zhihua Zhang
Regularized MDPs serve as a smooth version of original MDPs.
1 code implementation • 16 Nov 2020 • Yufeng Wang, Dan Li, Xiang Li, Min Yang
Further, this classifier is incorporated into the generative adversarial framework to help the generator to yield higher quality imputation results.
no code implementations • 16 Nov 2020 • Xiang Li, Xinyu Fu, Zheng Lu, Ruibin Bai, Uwe Aickelin, Peiming Ge, Gong Liu
Internet hospital is a rising business thanks to recent advances in mobile web technology and high demand of health care services.
5 code implementations • CVPR 2021 • Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #26 on Object Detection on COCO-O
no code implementations • 26 Nov 2020 • Aoxiao Zhong, Xiang Li, Dufan Wu, Hui Ren, Kyungsang Kim, YoungGon Kim, Varun Buch, Nir Neumark, Bernardo Bizzo, Won Young Tak, Soo Young Park, Yu Rim Lee, Min Kyu Kang, Jung Gil Park, Byung Seok Kim, Woo Jin Chung, Ning Guo, Ittai Dayan, Mannudeep K. Kalra, Quanzheng Li
These results demonstrate our deep metric learning based image retrieval model is highly efficient in the CXR retrieval, diagnosis and prognosis, and thus has great clinical value for the treatment and management of COVID-19 patients.
1 code implementation • NeurIPS 2020 • Tao Zhuang, Zhixuan Zhang, Yuheng Huang, Xiaoyi Zeng, Kai Shuang, Xiang Li
Experimentally, we show that structured pruning using polarization regularizer achieves much better results than using L1 regularizer.
no code implementations • Joint Conference on Lexical and Computational Semantics 2020 • Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula
We transform one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.
no code implementations • 2 Dec 2020 • Ankush Khandelwal, Shaoming Xu, Xiang Li, Xiaowei Jia, Michael Stienbach, Christopher Duffy, John Nieber, Vipin Kumar
The goal of this work is to incorporate our understanding of physical processes and constraints in hydrology into machine learning algorithms, and thus bridge the performance gap while reducing the need for large amounts of data compared to traditional data-driven approaches.
1 code implementation • 6 Dec 2020 • Jia-Qi Yang, Xiang Li, Shuguang Han, Tao Zhuang, De-Chuan Zhan, Xiaoyi Zeng, Bin Tong
To strike a balance in this trade-off, we propose Elapsed-Time Sampling Delayed Feedback Model (ES-DFM), which models the relationship between the observed conversion distribution and the true conversion distribution.
no code implementations • 15 Dec 2020 • Wenjie Qin, Xiang Li, Yuhui Sun, Deyi Xiong, Jianwei Cui, Bin Wang
In this paper, we propose a robust neural machine translation (NMT) framework.
no code implementations • 15 Dec 2020 • Bing Luo, Xiang Li, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
In this paper, we analyze how to design adaptive FL that optimally chooses these essential control variables to minimize the total cost while ensuring convergence.
no code implementations • 18 Dec 2020 • Xiang Li, Danhao Ding, Ben Kao, Yizhou Sun, Nikos Mamoulis
A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types.
no code implementations • 1 Jan 2021 • Shib Sankar Dasgupta, Xiang Li, Michael Boratko, Dongxu Zhang, Andrew McCallum
In Patel et al. (2020), the authors demonstrate that only the transitive reduction is required, and further extend box embeddings to capture joint hierarchies by augmenting the graph with new nodes.
1 code implementation • 1 Jan 2021 • Xiulong Yang, Hui Ye, Yang Ye, Xiang Li, Shihao Ji
We show that our Generative MMC (GMMC) can be trained discriminatively, generatively, or jointly for image classification and generation.
no code implementations • 4 Jan 2021 • Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang
Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.
Time Series Analysis Video Forensics Cryptography and Security
no code implementations • 5 Jan 2021 • Xiang Li, Zhihua Zhang
In this work, we study a novel class of projection-based algorithms for linearly constrained problems (LCPs) which have a lot of applications in statistics, optimization, and machine learning.
1 code implementation • 1 Feb 2021 • Meimei Shang, Fei Gao, Xiang Li, Jingjie Zhu, Lingna Dai
In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data.
no code implementations • 12 Feb 2021 • Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma
Collaborative filtering has been largely used to advance modern recommender systems to predict user preference.
9 code implementations • ICCV 2021 • Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao
Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.
Ranked #5 on Semantic Segmentation on SynPASS
no code implementations • 24 Feb 2021 • Xiang Li, Yuzheng Chen, Rakesh Patibanda, Florian 'Floyd' Mueller
With the popularity of online access in virtual reality (VR) devices, it will become important to investigate exclusive and interactive CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) designs for VR devices.
Human-Computer Interaction
no code implementations • 1 Mar 2021 • Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang
The low communication power and the possible privacy breaches of data make the computation of eigenspace challenging.
1 code implementation • 5 Mar 2021 • Shunyu Jiang, Fuli Feng, Weijian Chen, Xiang Li, Xiangnan He
Graph classification is a highly impactful task that plays a crucial role in a myriad of real-world applications such as molecular property prediction and protein function prediction. Aiming to handle the new classes with limited labeled graphs, few-shot graph classification has become a bridge of existing graph classification solutions and practical usage. This work explores the potential of metric-based meta-learning for solving few-shot graph classification. We highlight the importance of considering structural characteristics in the solution and propose a novel framework which explicitly considers global structure and local structure of the input graph.
no code implementations • 21 Mar 2021 • Varun Buch, Aoxiao Zhong, Xiang Li, Marcio Aloisio Bezerra Cavalcanti Rockenbach, Dufan Wu, Hui Ren, Jiahui Guan, Andrew Liteplo, Sayon Dutta, Ittai Dayan, Quanzheng Li
Predictive risk scores for COVID-19 severe outcomes ("CO-RISK" score) were derived from model output and evaluated on the testing dataset, as well as compared to human performance.
no code implementations • 8 Apr 2021 • Xiang Li, Changhe Song, Jingbei Li, Zhiyong Wu, Jia Jia, Helen Meng
This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis.
no code implementations • 12 Apr 2021 • Cong Li, Min Shi, Bo Qu, Xiang Li
In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.
1 code implementation • 2 May 2021 • Wenhai Wang, Enze Xie, Xiang Li, Xuebo Liu, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen
By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text.
1 code implementation • 19 May 2021 • Cong Xu, Xiang Li, Min Yang
Neural networks are susceptible to artificially designed adversarial perturbations.
Ranked #1 on Adversarial Attack on CIFAR-10
no code implementations • ACL 2021 • Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao
A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information.
no code implementations • 31 May 2021 • Binbin Xie, Jinsong Su, Yubin Ge, Xiang Li, Jianwei Cui, Junfeng Yao, Bin Wang
However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions.
1 code implementation • NeurIPS 2021 • Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, xiangyang xue, Yanwei Fu
To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.
no code implementations • 20 Jun 2021 • Chaolei Tan, Zihang Lin, Jian-Fang Hu, Xiang Li, Wei-Shi Zheng
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task.
16 code implementations • 25 Jun 2021 • Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao
We hope this work will facilitate state-of-the-art Transformer researches in computer vision.
Ranked #23 on Object Detection on COCO-O
no code implementations • 28 Jun 2021 • Wenchao Zhang, Chong Fu, Xiangshi Chang, Tengfei Zhao, Xiang Li, Chiu-Wing Sham
Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.
no code implementations • DCASE workshop 2021 • Weiqiang Yuan ∗, Qichen Han∗, Dong Liu, Xiang Li, Zhen Yang
Our solution focuses on solving two problems in automated audio captioning: data insufficiency and word selection indeterminacy.
Ranked #1 on Audio captioning on Clotho (using extra training data)
no code implementations • 7 Jul 2021 • Xiang Li, Lingjing Wang, Yi Fang
To achieve this, we treat the shape segmentation as a point labeling problem in the metric space.
no code implementations • 29 Jul 2021 • Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Jun Li, Jian Yang
However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.
Ranked #2 on Depth Completion on KITTI Depth Completion
no code implementations • SEMEVAL 2021 • Qinglin Zhu, Zijie Lin, Yice Zhang, Jingyi Sun, Xiang Li, Qihui Lin, Yixue Dang, Ruifeng Xu
This paper presents the winning system that participated in SemEval-2021 Task 5: Toxic Spans Detection.
2 code implementations • ICCV 2021 • Kun Wang, Zhenyu Zhang, Zhiqiang Yan, Xiang Li, Baobei Xu, Jun Li, Jian Yang
Monocular depth estimation aims at predicting depth from a single image or video.
no code implementations • 3 Sep 2021 • Xiang Li, Jiadong Liang, Xiangyu Chang, Zhihua Zhang
Both the methods are communication efficient and applicable to online data.
no code implementations • 12 Sep 2021 • Bing Luo, Xiang Li, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
Federated learning (FL) is a distributed learning paradigm that enables a large number of mobile devices to collaboratively learn a model under the coordination of a central server without sharing their raw data.
no code implementations • 13 Sep 2021 • Chaofei Wang, Shiji Song, Qisen Yang, Xiang Li, Gao Huang
As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks.
no code implementations • 14 Sep 2021 • Rahul Ghosh, Arvind Renganathan, Kshitij Tayal, Xiang Li, Ankush Khandelwal, Xiaowei Jia, Chris Duffy, John Neiber, Vipin Kumar
Furthermore, we show that KGSSL is relatively more robust to distortion than baseline methods, and outperforms the baseline model by 35\% when plugging in KGSSL inferred characteristics.
1 code implementation • 29 Sep 2021 • Liang Zongwei, Junan Yang, Keju Huang, Hui Liu, Lin Cui, Lingzhi Qu, Xiang Li
The interpretability of the current temporal KG forecasting models is manifested in providing the reasoning paths.
no code implementations • 1 Oct 2021 • Zheng Li, Xiang Li, Lingfeng Yang, Jian Yang, Zhigeng Pan
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm.
no code implementations • 5 Oct 2021 • Yusui Chen, Wenhao Hu, Xiang Li
Fully convolutional networks are robust in performing semantic segmentation, with many applications from signal processing to computer vision.
1 code implementation • 12 Oct 2021 • Jinghuan Shang, Kumara Kahatapitiya, Xiang Li, Michael S. Ryoo
Reinforcement Learning (RL) can be considered as a sequence modeling task: given a sequence of past state-action-reward experiences, an agent predicts a sequence of next actions.
1 code implementation • 20 Oct 2021 • Guanjie Huang, Hongjian He, Xiang Li, Xingchen Li, Ziang Liu
Currently, it is hard to compare and evaluate different style transfer algorithms due to chaotic definitions of style and the absence of agreed objective validation methods in the study of style transfer.
no code implementations • 20 Oct 2021 • Xiang Li, Jinglu Wang, Xiao Li, Yan Lu
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.
no code implementations • 2 Nov 2021 • Liao Qu, Shuaiqi Huang, Yunsong Jia, Xiang Li
By increasing the weight of extreme temperature samples and reducing the possibility of misjudging extreme temperature as normal, the proposed loss function can enhance the prediction results in extreme situations.
1 code implementation • 8 Nov 2021 • Xiang Li, Shihao Ji
Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods.
no code implementations • 10 Nov 2021 • Yi Lin, Jianchao Su, Xiang Wang, Xiang Li, Jingen Liu, Kwang-Ting Cheng, Xin Yang
We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.
no code implementations • NeurIPS 2021 • Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, Dongsheng Li
To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning.
no code implementations • 2 Dec 2021 • Alina Walch, Xiang Li, Jonathan Chambers, Nahid Mohajeri, Selin Yilmaz, Martin Patel, Jean-Louis Scartezzini
Shallow ground-source heat pumps (GSHPs) are a promising technology for contributing to the decarbonisation of the energy sector.
no code implementations • 3 Dec 2021 • Xiang Li, Jinglu Wang, Xiao Li, Yan Lu
Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames.
no code implementations • 9 Dec 2021 • Gang Li, Xiang Li, Yujie Wang, Shanshan Zhang, Yichao Wu, Ding Liang
Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively.
1 code implementation • 29 Dec 2021 • Xiang Li, Wenhao Yang, Jiadong Liang, Zhihua Zhang, Michael I. Jordan
We study Q-learning with Polyak-Ruppert averaging in a discounted Markov decision process in synchronous and tabular settings.
no code implementations • 31 Dec 2021 • Xiang Li, Dong Li, Ruoming Jin, Gagan Agrawal, Rajiv Ramnath
Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability.
1 code implementation • 10 Jan 2022 • Lianghao Xia, Chao Huang, Yong Xu, Huance Xu, Xiang Li, WeiGuo Zhang
As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks.
no code implementations • 24 Jan 2022 • Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang
The cybersecurity breaches expose surveillance video streams to forgery attacks, under which authentic streams are falsified to hide unauthorized activities.
no code implementations • 6 Feb 2022 • Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, Yikang Li
Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers.
1 code implementation • 14 Feb 2022 • Qiyang Zhang, Xiang Li, Xiangying Che, Xiao Ma, Ao Zhou, Mengwei Xu, Shangguang Wang, Yun Ma, Xuanzhe Liu
Deploying deep learning (DL) on mobile devices has been a notable trend in recent years.
no code implementations • 28 Feb 2022 • Jingwei Zhuo, Bin Liu, Xiang Li, Han Zhu, Xiaoqiang Zhu
Motivated by the observation that model-free methods like behavioral retargeting (BR) and item-based collaborative filtering (ItemCF) hit different parts of the user-item relevance compared to neural sequential recommendation models, we propose a novel model-agnostic training approach called WSLRec, which adopts a three-stage framework: pre-training, top-$k$ mining, and fine-tuning.
no code implementations • 2 Mar 2022 • Yunxiao Shan, Shu Li, Fuxiang Li, Yuxin Cui, Shuai Li, Ming Zhou, Xiang Li
It is proved that the algorithm can effectively reduce the computational complexity of the original DPC from $O(n^2K)$ to $O(n(n^{1-1/K}+k))$.
1 code implementation • CVPR 2022 • Lingfeng Yang, Xiang Li, RenJie Song, Borui Zhao, Juntian Tao, Shihao Zhou, Jiajun Liang, Jian Yang
Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.
1 code implementation • 14 Mar 2022 • Lingfeng Yang, Xiang Li, Borui Zhao, RenJie Song, Jian Yang
In semantic segmentation, RM also surpasses the baseline and CutMix by 1. 9 and 1. 1 mIoU points under UperNet on ADE20K, respectively.
no code implementations • 16 Mar 2022 • Xiang Li, Yazhou Zhang, Prayag Tiwari, Dawei Song, Bin Hu, Meihong Yang, Zhigang Zhao, Neeraj Kumar, Pekka Marttinen
Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.
no code implementations • 18 Mar 2022 • Zhiqiang Yan, Xiang Li, Kun Wang, Zhenyu Zhang, Jun Li, Jian Yang
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.
no code implementations • 20 Mar 2022 • Yang Lou, Ruizi Wu, Junli Li, Lin Wang, Xiang Li, Guanrong Chen
Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors; 2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability; 3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations; 4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures.
1 code implementation • 29 Mar 2022 • Zhifang Fan, Dan Ou, Yulong Gu, Bairan Fu, Xiang Li, Wentian Bao, Xin-yu Dai, Xiaoyi Zeng, Tao Zhuang, Qingwen Liu
In this paper, we propose a new perspective for context-aware users' behavior modeling by including the whole page-wisely exposed products and the corresponding feedback as contextualized page-wise feedback sequence.
1 code implementation • 30 Mar 2022 • Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang
Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance.
1 code implementation • 31 Mar 2022 • Wenlin Dai, Changhe Song, Xiang Li, Zhiyong Wu, Huashan Pan, Xiulin Li, Helen Meng
Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task.
1 code implementation • 12 Apr 2022 • Wenjing Zhu, Xiang Li
Speech Emotion Recognition (SER) is a fundamental task to predict the emotion label from speech data.
1 code implementation • ACL 2022 • Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao
We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models.
1 code implementation • ACL 2022 • Renyu Zhu, Lei Yuan, Xiang Li, Ming Gao, Wenyuan Cai
In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components.
1 code implementation • Findings (NAACL) 2022 • Ziqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, Yangqiu Song
In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals.
1 code implementation • 15 May 2022 • Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, Weining Qian
Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.
Ranked #2 on Node Classification on pokec