In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
Furthermore, we show that it is possible to forecast LOS from all facility types and all networks with a single model, whereas fine-tuning for a particular facility or network only brings modest improvements.
This paper proposes a novel particle image velocimetry (PIV) technique to generate an instantaneous two-dimensional velocity field for sediment-laden fluid based on the optical flow algorithm of ultrasound imaging.
To support these requirements, the third generation partnership project (3GPP) has introduced enhanced grant-free (GF) transmission in the uplink (UL), with multiple active configured-grants (CGs) for URLLC UEs.
Specifically, we exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool.
Positron emission tomography (PET) reconstruction has become an ill-posed inverse problem due to low-count projection data, and a robust algorithm is urgently required to improve imaging quality.
Specifically, when modeling the observed data from social media with neural temporal point process, we jointly learn a Gibbs-like distribution of group assignment based on how consistent an assignment is to (1) the account embedding space and (2) the prior knowledge.
Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories.
The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change.
On the one hand, we model the rich correlations between the users' diverse behaviors (e. g., answer, follow, vote) to obtain the individual-level behavior interaction.
Long text understanding is important yet challenging in natural language processing.
To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts.
Data augmentation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting.
In this paper, we introduce MeDiaQA, a novel question answering(QA) dataset, which constructed on real online Medical Dialogues.
Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task.
Identifying and characterizing disinformation in political discourse on social media is critical to ensure the integrity of elections and democratic processes around the world.
This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV).
The misinformation communities are more vocal either specific to the vaccine discussion or political discussion, and we find other differences in the characteristic behaviours of different communities.
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues.
Magnetic resonance imaging (MRI) acquisition, reconstruction, and segmentation are usually processed independently in the conventional practice of MRI workflow.
1 code implementation • 21 Apr 2021 • Ren Yang, Radu Timofte, Jing Liu, Yi Xu, Xinjian Zhang, Minyi Zhao, Shuigeng Zhou, Kelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy, Xin Li, Fanglong Liu, He Zheng, Lielin Jiang, Qi Zhang, Dongliang He, Fu Li, Qingqing Dang, Yibin Huang, Matteo Maggioni, Zhongqian Fu, Shuai Xiao, Cheng Li, Thomas Tanay, Fenglong Song, Wentao Chao, Qiang Guo, Yan Liu, Jiang Li, Xiaochao Qu, Dewang Hou, Jiayu Yang, Lyn Jiang, Di You, Zhenyu Zhang, Chong Mou, Iaroslav Koshelev, Pavel Ostyakov, Andrey Somov, Jia Hao, Xueyi Zou, Shijie Zhao, Xiaopeng Sun, Yiting Liao, Yuanzhi Zhang, Qing Wang, Gen Zhan, Mengxi Guo, Junlin Li, Ming Lu, Zhan Ma, Pablo Navarrete Michelini, Hai Wang, Yiyun Chen, Jingyu Guo, Liliang Zhang, Wenming Yang, Sijung Kim, Syehoon Oh, Yucong Wang, Minjie Cai, Wei Hao, Kangdi Shi, Liangyan Li, Jun Chen, Wei Gao, Wang Liu, XiaoYu Zhang, Linjie Zhou, Sixin Lin, Ru Wang
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods.
no code implementations • 16 Mar 2021 • Hongjie He, Ke Yang, Yuwei Cai, Zijian Jiang, Qiutong Yu, Kun Zhao, JunBo Wang, Sarah Narges Fatholahi, Yan Liu, Hasti Andon Petrosians, Bingxu Hu, Liyuan Qing, Zhehan Zhang, Hongzhang Xu, Siyu Li, Kyle Gao, Linlin Xu, Jonathan Li
Building rooftop data are of importance in several urban applications and in natural disaster management.
Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations.
With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT.
The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications.
We propose a marginal structural model (MSM) for effect modification by different patient characteristics and co-medications in a meta-analysis of observational IPD.
Treatment recommendation is a complex multi-faceted problem with many conflicting objectives, e. g., optimizing the survival rate (or expected lifetime), mitigating negative impacts, reducing financial expenses and time costs, avoiding over-treatment, etc.
We present augmented counterfactual ordinary differential equations (ACODEs), a new approach to counterfactual inference on time series data with a focus on healthcare applications.
Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis.
As countries look towards re-opening of economic activities amidst the ongoing COVID-19 pandemic, ensuring public health has been challenging.
Compressed sensing (CS) computed tomography has been proven to be important for several clinical applications, such as sparse-view computed tomography (CT), digital tomosynthesis and interior tomography.
In this work, we analyze RACH success probability in a self-powered NB-IoT network taking into account the repeated preamble transmissions and collisions, where each IoT device with data is active when its battery energy is sufficient to support the transmission.
Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning.
Current mainstream of CT reconstruction methods based on deep learning usually needs to fix the scanning geometry and dose level, which will significantly aggravate the training cost and need more training data for clinical application.
Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs).
We prove the asymptotic properties of the maximum likelihood estimator (MLE) in time-varying transition probability (TVTP) regime-switching models.
NarrowBand-Internet of Things (NB-IoT) is a new 3GPP radio access technology designed to provide better coverage for Low Power Wide Area (LPWA) networks.
Epidemic spread in a population is traditionally modeled via compartmentalized models which represent the free evolution of disease in absence of any intervention policies.
We evaluate the effectiveness of our propose method by comparing it with the baseline models and also with state-of-the-art works.
Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain.
In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.
In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations.
Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable.
Although the knowledge of governing partial differential equations (PDE) of data can be helpful for the fast adaptation to few observations, it is mostly infeasible to exactly find the equation for observations in real-world physical systems.
The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition.
To do so, we propose a HAR method that consists of three steps: (i) data transformation involving the generation of new features based on transforming of raw data, (ii) feature extraction involving the learning of a classifier based on the AdaBoost algorithm and the use of training data consisting of the transformed features, and (iii) parameter determination and pattern recognition involving the determination of parameters based on the features generated in (ii) and the use of the parameters as training data for deep learning algorithms to be used to recognize human activities.
We propose a Capsule network-based method to Decompose the unsupervised word Embedding of an ambiguous word into context specific Sense embedding, called CapsDecE2S.
Predicting Origin-Destination (OD) flow is a crucial problem for intelligent transportation.
The analysis is presented and updated on a publically accessible dashboard (https://usc-melady. github. io/COVID-19-Tweet-Analysis) to track the nature of online discourse and misinformation about COVID-19 on Twitter from March 1 - June 5, 2020.
Label noise is increasingly prevalent in datasets acquired from noisy channels.
Ranked #10 on Image Classification on Clothing1M (using extra training data)
Most existing crowd counting methods require object location-level annotation, i. e., placing a dot at the center of an object.
Based on this framework, we define the latent access failure probability to characterize URLLC reliability and latency performances.
Ultra-Reliable and Low-Latency Communications (URLLC) services in vehicular networks on millimeter-wave bands present a significant challenge, considering the necessity of constantly adjusting the beam directions.
A generic model for CrowdMining is further proposed based on a set of existing studies.
With higher-order neighborhood information of graph network, the accuracy of graph representation learning classification can be significantly improved.
Whether it is computer vision, natural language processing or speech recognition, the essence of these applications is to obtain powerful feature representations that make downstream applications completion more efficient.
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree.
To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks.
In this paper we present GumDrop, Georgetown University's entry at the DISRPT 2019 Shared Task on automatic discourse unit segmentation and connective detection.
Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models.
Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods.
The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news, and mitigation of its widespread impact on public opinion.
After these two steps, we have two p-values for each test instance and the test instance is assigned to the class associated with the smaller p-value.
Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models.
Neural networks are known to model statistical interactions, but they entangle the interactions at intermediate hidden layers for shared representation learning.
In this paper, we first design an efficient division method to decompose a manifold into ordered continuous maximal linear patches (CMLPs) that denote meaningful action snippets of the action sequence.
Multi-Rate Multivariate Time Series (MR-MTS) are the multivariate time series observations which come with various sampling rates and encode multiple temporal dependencies.
The major advantages of DynGEM include: (1) the embedding is stable over time, (2) it can handle growing dynamic graphs, and (3) it has better running time than using static embedding methods on each snapshot of a dynamic graph.
Social and Information Networks
We propose in this paper a modified Sigma-Pi-Sigma neural network (MSPSNN) with an adaptive approach to find a better multinomial for a given problem.
The numerical results show that there is not significant reduction in the classification ability of the network if the input signals are subject to sinusoidal and Gaussian perturbations.
Spatiotemporal forecasting has become an increasingly important prediction task in machine learning and statistics due to its vast applications, such as climate modeling, traffic prediction, video caching predictions, and so on.
Recent advances in computing technology and sensor design have made it easier to collect longitudinal or time series data from patients, resulting in a gigantic amount of available medical data.
Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention.
This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data.
Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications.
We use this generative model together with a convolutional neural network (CNN) based prediction model to improve the onset prediction performance.
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
Ranked #3 on Traffic Prediction on PeMS-M
Music emotion recognition (MER) is usually regarded as a multi-label tagging task, and each segment of music can inspire specific emotion tags.
Specifically, we incorporate the behavior of both parties, users and articles, and the group behavior of users who propagate fake news.
To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts.
The Universal Dependencies (UD) Project seeks to build a cross-lingual studies of treebanks, linguistic structures and parsing.
In this paper, we show ways of sampling intermediate steps of alternating minimization algorithms for computing low rank tensor CP decompositions, leading to the sparse alternating least squares (SPALS) method.
A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a probability distribution.
Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly.
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.
Ranked #4 on Multivariate Time Series Forecasting on MuJoCo
no code implementations • 20 Jan 2016 • V. S. Subrahmanian, Amos Azaria, Skylar Durst, Vadim Kagan, Aram Galstyan, Kristina Lerman, Linhong Zhu, Emilio Ferrara, Alessandro Flammini, Filippo Menczer, Andrew Stevens, Alexander Dekhtyar, Shuyang Gao, Tad Hogg, Farshad Kooti, Yan Liu, Onur Varol, Prashant Shiralkar, Vinod Vydiswaran, Qiaozhu Mei, Tim Hwang
A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes.
Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research.
However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications.
Our work is particularly motivated by the algorithmic problems for speeding up the classic Newton's method in applications such as computing the inverse square-root of the precision matrix of a Gaussian random field, as well as computing the $q$th-root transition (for $q\geq1$) in a time-reversible Markov model.
random samples for $n$-dimensional Gaussian random fields with SDDM precision matrices.
Existing group anomaly detection approaches rely on the assumption that the groups are known, which can hardly be true in real world social media applications.