Search Results for author:
Found 467 papers, 155 papers with code
Joint Grammar and Treebank Development for Mandarin Chinese with HPSG
We present the ongoing development of MCG, a linguistically deep and precise grammar for Mandarin Chinese together with its accompanying treebank, both based on the linguistic framework of HPSG, and using MRS as the semantic representation.
Constructing a Question Corpus for Textual Semantic Relations
Finding useful questions is a challenging task in Community Question Answering (CQA).
Aligning Predicate-Argument Structures for Paraphrase Fragment Extraction
Paraphrases and paraphrasing algorithms have been found of great importance in various natural language processing tasks.
Mimicing the Kane-Mele type spin orbit interaction by spin-flexual phonon coupling in graphene devices
On the efforts of enhancing the spin orbit interaction (SOI) of graphene for seeking the dissipationless quantum spin Hall devices, unique Kane-Mele type SOI and high mobility samples are desired.
Mesoscale and Nanoscale Physics
SketchNet: Sketch Classification With Web Images
In this study, we present a weakly supervised approach that discovers the discriminative structures of sketch images, given pairs of sketch images and web images.
A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique
Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information.
Connecting Phrase based Statistical Machine Translation Adaptation
Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains with the original corpus can indeed enhance SMT performance directly.
3D Shape Induction from 2D Views of Multiple Objects
In this paper we investigate the problem of inducing a distribution over three-dimensional structures given two-dimensional views of multiple objects taken from unknown viewpoints.
Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect
Monocular visual odometry (VO) and simultaneous localization and mapping (SLAM) have seen tremendous improvements in accuracy, robustness and efficiency, and have gained increasing popularity over recent years.
Monocular Visual Odometry
Simultaneous Localization and Mapping
Binarized Mode Seeking for Scalable Visual Pattern Discovery
Second, we further extend bMS to a more general form, namely contrastive binary mean shift (cbMS), which maximizes the contrastive density in binary space, for finding informative patterns that are both frequent and discriminative for the dataset.
Sentence Embedding for Neural Machine Translation Domain Adaptation
Although new corpora are becoming increasingly available for machine translation, only those that belong to the same or similar domains are typically able to improve translation performance.
Image Deblurring via Extreme Channels Prior
The proposed method takes advantage of both Bright and Dark Channel Prior.
Shape Generation using Spatially Partitioned Point Clouds
We propose to use the expressive power of neural networks to learn a distribution over the shape coefficients in a generative-adversarial framework.
3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
The decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints.
Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras
We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras.
Instance Weighting for Neural Machine Translation Domain Adaptation
Instance weighting has been widely applied to phrase-based machine translation domain adaptation.
Neural Machine Translation with Source Dependency Representation
Source dependency information has been successfully introduced into statistical machine translation.
Online Photometric Calibration for Auto Exposure Video for Realtime Visual Odometry and SLAM
We further show that our calibration can improve the performance of a state-of-the-art direct visual odometry method that works solely on pixel intensities, calibrating for photometric parameters in an online fashion in realtime.
Context-Aware Smoothing for Neural Machine Translation
In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information.
Syntax-Directed Attention for Neural Machine Translation
In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction.
Fake Colorized Image Detection
Based on our observations, i. e., potential traces in the hue, saturation, dark and bright channels, we propose two simple yet effective detection methods for fake colorized images: Histogram based Fake Colorized Image Detection (FCID-HIST) and Feature Encoding based Fake Colorized Image Detection (FCID-FE).
Multimedia
Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery
In this work, we employ a state-of-the-art convolutional neural network architecture, called SegNet (Badrinarayanan et.
Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation
Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch.
VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Recent advances in deep neuroevolution have demonstrated that evolutionary algorithms, such as evolution strategies (ES) and genetic algorithms (GA), can scale to train deep neural networks to solve difficult reinforcement learning (RL) problems.
Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video
Our method produces superior results to the state-of-the-art learning-based, single- or two-view depth estimation methods on both indoor and outdoor benchmark datasets.
A Simple Riemannian Manifold Network for Image Set Classification
The proposed RieMNet and DRieMNet are evaluated on three tasks: video-based face recognition, set-based object categorization, and set-based cell identification.
Multiple Manifolds Metric Learning with Application to Image Set Classification
In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold.
A Survey of Domain Adaptation for Neural Machine Translation
Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available.
Riemannian kernel based Nyström method for approximate infinite-dimensional covariance descriptors with application to image set classification
We propose a novel framework for representing image sets by approximating infinite-dimensional CovDs in the paradigm of the Nystr\"om method based on a Riemannian kernel.
Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification
The core of the method is a new discriminant function for metric learning and dimensionality reduction.
Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
To this end, we incorporate deep depth predictions into Direct Sparse Odometry (DSO) as direct virtual stereo measurements.
Multiresolution Tree Networks for 3D Point Cloud Processing
We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks.
LDSO: Direct Sparse Odometry with Loop Closure
In this paper we present an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization (LDSO).
Exploring Recombination for Efficient Decoding of Neural Machine Translation
In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations.
A Deeper Look at 3D Shape Classifiers
We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations.
NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filtering Task
Using the clean data of the WMT18 shared news translation task, we designed several features and trained a classifier to score each sentence pairs in the noisy data.
NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task
Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.
Band Assignment in Dual Band Systems: A Learning-based Approach
In this work, we use a machine learning framework to provide an efficient and practical solution to the band assignment problem.
ATM:Adversarial-neural Topic Model
The proposed ATM models topics with Dirichlet prior and employs a generator network to capture the semantic patterns among latent topics.
PCGAN: Partition-Controlled Human Image Generation
Human image generation is a very challenging task since it is affected by many factors.
A Deep Cascade Model for Multi-Document Reading Comprehension
To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension.
Ranked #2 on
Question Answering
on MS MARCO
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
We lessen this friction, by (1) training several algorithms at scale and releasing trained models, (2) integrating with a previous Deep RL model release, and (3) releasing code that makes it easy for anyone to load, visualize, and analyze such models.
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Our results show that POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved by direct optimization alone, or even through a direct-path curriculum-building control algorithm introduced to highlight the critical role of open-endedness in solving ambitious challenges.
Machine learning for the recognition of emotion in the speech of couples in psychotherapy using the Stanford Suppes Brain Lab Psychotherapy Dataset
Our results show that couple therapy is a rich context for the study of emotion in naturally occurring speech.
Sound Human-Computer Interaction Audio and Speech Processing
Supervised ML Solution for Band Assignment in Dual-Band Systems with Omnidirectional and Directional Antennas
This paper considers the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate with the user equipment (UE).
Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
Deep learning-based, single-view depth estimation methods have recently shown highly promising results.
DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation
Scene understanding from images is a challenging problem encountered in autonomous driving.
CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks
Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications.
Discriminative Clustering for Robust Unsupervised Domain Adaptation
Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset.
Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth
Deep learning-based, single-view depth estimation methods have recently shown highly promising results.
Ranked #3 on
Monocular Depth Estimation
on Mid-Air Dataset
Lattice-Based Transformer Encoder for Neural Machine Translation
To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training.
Deep Reinforcement Learning for Multi-objective Optimization
The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.
Inferring 3D Shapes from Image Collections using Adversarial Networks
To this end, we present new differentiable projection operators that can be used by PrGAN to learn better 3D generative models.
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization
The success of neural summarization models stems from the meticulous encodings of source articles.
Ranked #14 on
Text Summarization
on GigaWord
Neural Machine Translation with Reordering Embeddings
The reordering model plays an important role in phrase-based statistical machine translation.
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation
In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.
Semi-supervised Domain Adaptation for Dependency Parsing
During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data.
Sentence-Level Agreement for Neural Machine Translation
The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.
Distilling with Residual Network for Single Image Super Resolution
Recently, the deep convolutional neural network (CNN) has made remarkable progress in single image super resolution(SISR).
Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system.
Syntax-aware Neural Semantic Role Labeling
Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP.
NICT's Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task
This paper presents the NICT{'}s participation in the WMT19 unsupervised news translation task.
NICT's Supervised Neural Machine Translation Systems for the WMT19 News Translation Task
In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions.
Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning
Specifically, the covariance matrix, linear subspace, and Gaussian distribution are applied for set representation simultaneously.
SG-Net: Syntax-Guided Machine Reading Comprehension
In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.
Ranked #5 on
Question Answering
on SQuAD2.0 dev
Open Event Extraction from Online Text using a Generative Adversarial Network
Experimental results show that our model outperforms the baseline approaches on all the datasets, with more significant improvements observed on the news article dataset where an increase of 15\% is observed in F-measure.
Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation
However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.
Regularized Context Gates on Transformer for Machine Translation
This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer.
More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation
We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds.
Real-Time 3D Reconstruction of Colonoscopic Surfaces for Determining Missing Regions
To the best of our knowledge, we are the first to reconstruct dense colon surface from video in real time and to display missing surface.
Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
In addition, we also theoretically prove that optimizing low-level skills with this auxiliary reward will increase the task return for the joint policy.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
First-Order Preconditioning via Hypergradient Descent
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space. These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence.
Syntax-Enhanced Self-Attention-Based Semantic Role Labeling
As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence.
Attention Optimization for Abstractive Document Summarization
Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models.
Literature Review: Human Segmentation with Static Camera
Our research topic is Human segmentation with static camera.
Document-level Neural Machine Translation with Associated Memory Network
Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network.
SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT
Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.
SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing
This paper describes our SJTU-NICT{'}s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).
Recurrent Positional Embedding for Neural Machine Translation
To address this issue, this work proposes a recurrent positional embedding approach based on word vector.
English-Myanmar Supervised and Unsupervised NMT: NICT's Machine Translation Systems at WAT-2019
This paper presents the NICT{'}s participation (team ID: NICT) in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (Burmese) - English task in both translation directions.
Probing Contextualized Sentence Representations with Visual Awareness
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations.
Machine Intelligence at the Edge with Learning Centric Power Allocation
However, power allocation in this paradigm requires maximizing the learning performance instead of the communication throughput, for which the celebrated water-filling and max-min fairness algorithms become inefficient.
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models.
Explicit Sentence Compression for Neural Machine Translation
In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT.
Knowledge Graph Embedding via Graph Attenuated Attention Networks
However, these methods assign the same weights on the relation path in the knowledge graph and ignore the rich information presented in neighbor nodes, which result in incomplete mining of triple features.
Ranked #12 on
Link Prediction
on WN18RR
Deep Audio-Visual Learning: A Survey
Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully.
Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers.
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
Semi-Supervised Neural Architecture Search
On ImageNet, it achieves 23. 5% top-1 error rate (under 600M FLOPS constraint) using 4 GPU-days for search.
Ranked #81 on
Neural Architecture Search
on ImageNet
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community.
Modeling Future Cost for Neural Machine Translation
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation.
Fake Generated Painting Detection via Frequency Analysis
With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts.
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning.
Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods
Recent advances in machine learning are consistently enabled by increasing amounts of computation.
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years.
SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization
To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios.
Human-Computer Interaction Image and Video Processing
Reference Language based Unsupervised Neural Machine Translation
Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism.
Learning Generative Models of Shape Handles
We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and building compact 3D representations.
Deep Manifold Prior
We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization.
Explicit Reordering for Neural Machine Translation
Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT.
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.
Self Punishment and Reward Backfill for Deep Q-Learning
We prove that, under certain assumptions and regardless of the reinforcement learning algorithm used, these two strategies maintain the order of policies in the space of all possible policies in terms of their total reward, and, by extension, maintain the optimal policy.
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs.
Relational Graph Attention Network for Aspect-based Sentiment Analysis
Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Neural Topic Modeling with Bidirectional Adversarial Training
Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA).
Ranked #1 on
Text Clustering
on 20 Newsgroups
Multi-Domain Dialogue Acts and Response Co-Generation
Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed.
Syntax-aware Data Augmentation for Neural Machine Translation
Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data.
Decoding SARS-CoV-2 transmission, evolution and ramification on COVID-19 diagnosis, vaccine, and medicine
Tremendous effort has been given to the development of diagnostic tests, preventive vaccines, and therapeutic medicines for coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).
Data-dependent Gaussian Prior Objective for Language Generation
However, MLE focuses on once-to-all matching between the predicted sequence and gold-standard, consequently treating all incorrect predictions as being equally incorrect.
Neural Machine Translation with Universal Visual Representation
Though visual information has been introduced for enhancing neural machine translation (NMT), its effectiveness strongly relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.
Mutations on COVID-19 diagnostic targets
Effective, sensitive, and reliable diagnostic reagents are of paramount importance for combating the ongoing coronavirus disease 2019 (COVID-19) pandemic at a time there is no preventive vaccine nor specific drug available for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).
AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks.
Aortic Pressure Forecasting with Deep Sequence Learning
The aim of this study was to forecast the mean aortic pressure five minutes in advance, using the 25 Hz time series data of previous five minutes as input.
Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches.
VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines
Starting from a color image and a Manhattan line map, we use a deep neural network to regress on a dense normal map, and a dense Manhattan label map that identifies planar regions aligned with the Manhattan directions.
Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.
Hardware-irrelevant parallel processing system
We propose a hardware-irrelevant PPS of which the performance is unaffected by hardware deviations.
Beamspace Channel Estimation for Wideband Millimeter-Wave MIMO: A Model-Driven Unsupervised Learning Approach
By utilizing the Stein's unbiased risk estimator loss, the LDGEC network can be trained only with limited measurements corresponding to the pilot symbols, instead of the real channel data.
Content Word Aware Neural Machine Translation
Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-by-word.
Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks
The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.
Decoding asymptomatic COVID-19 infection and transmission
By analyzing the distribution of 11083G>T in various countries, we unveil that 11083G>T may correlate with the hypotoxicity of SARS-CoV-2.
Accuracy Prediction with Non-neural Model for Neural Architecture Search
Considering that most architectures are represented as sequences of discrete symbols which are more like tabular data and preferred by non-neural predictors, in this paper, we study an alternative approach which uses non-neural model for accuracy prediction.
Ranked #81 on
Neural Architecture Search
on ImageNet
DeepNetQoE: Self-adaptive QoE Optimization Framework of Deep Networks
A self-adaptive QoE model is set up that relates the model's accuracy with the computing resources required for training which will allow the experience value of the model to improve.
DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
We generate the global descriptor by directly aggregating the learned local descriptors with an effective attention mechanism.
Ranked #7 on
3D Place Recognition
on Oxford RobotCar Dataset
Learning Centric Power Allocation for Edge Intelligence
While machine-type communication (MTC) devices generate massive data, they often cannot process this data due to limited energy and computation power.
Characterizing SARS-CoV-2 mutations in the United States
Using genotyping, sequence-alignment, time-evolution, $k$-means clustering, protein-folding stability, algebraic topology, and network theory, we reveal that the US SARS-CoV-2 has four substrains and five top US SARS-CoV-2 mutations were first detected in China (2 cases), Singapore (2 cases), and the United Kingdom (1 case).
Safe and Effective Picking Paths in Clutter given Discrete Distributions of Object Poses
This work proposes first a perception process for 6D pose estimation, which returns a discrete distribution of object poses in a scene.
What leads to generalization of object proposals?
It is lucrative to train a good proposal model, that generalizes to unseen classes.
Host immune response driving SARS-CoV-2 evolution
Additionally, we show that children under age five and the elderly may be at high risk from COVID-19 because of their overreacting to the viral infection.
4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving
We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving.
Graph-to-Sequence Neural Machine Translation
In the light of the current NMT models more or less capture graph information among the sequence in a latent way, we present a graph-to-sequence model facilitating explicit graph information capturing.
Neural Topic Modeling with Cycle-Consistent Adversarial Training
ToMCAT employs a generator network to interpret topics and an encoder network to infer document topics.
Neural Topic Modeling by Incorporating Document Relationship Graph
Graph Neural Networks (GNNs) that capture the relationships between graph nodes via message passing have been a hot research direction in the natural language processing community.
High-order Semantic Role Labeling
Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships.
Investigating Constraint Relationship in Evolutionary Many-Constraint Optimization
This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.
SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT 's participation in the WMT 2020 machine translation shared task.
Prediction and mitigation of mutation threats to COVID-19 vaccines and antibody therapies
This discovery implies the vulnerability of current vaccines and antibody drugs to new mutations.
Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment
Edge intelligence is an emerging network architecture that integrates sensing, communication, computing components, and supports various machine learning applications, where a fundamental communication question is: how to allocate the limited wireless resources (such as time, energy) to the simultaneous model training of heterogeneous learning tasks?
Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning
Pretrained Language Models (PLMs) have improved the performance of natural language understanding in recent years.
Chunk-based Chinese Spelling Check with Global Optimization
Chinese spelling check is a challenging task due to the characteristics of the Chinese language, such as the large character set, no word boundary, and short word length.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
Deep Reinforcement Learning Based Dynamic Route Planning for Minimizing Travel Time
Route planning is important in transportation.
Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network
Simulation results reveal that compared with traditional DRL method, the HRL training algorithm can reach convergence 30 training iterations earlier and reduce the outage probability by 5% in two-hop relay network with the same outage threshold.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems
While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.
Ranked #5 on
3D Place Recognition
on Oxford RobotCar Dataset
(AR@1% metric)
Semantic Role Labeling with Heterogeneous Syntactic Knowledge
Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention.
SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis
However, due to the variety of users{'} emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain.
Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network
Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication.
Information Theory Systems and Control Systems and Control Information Theory
Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks
The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks.
SG-Net: Syntax Guided Transformer for Language Representation
In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.
Accurate Word Representations with Universal Visual Guidance
Word representation is a fundamental component in neural language understanding models.
Prior Knowledge Representation for Self-Attention Networks
Self-attention networks (SANs) have shown promising empirical results in various natural language processing tasks.
PreDet: Large-Scale Weakly Supervised Pre-Training for Detection
State-of-the-art object detection approaches typically rely on pre-trained classification models to achieve better performance and faster convergence.
Cross-lingual Transfer Learning for Pre-trained Contextualized Language Models
Though the pre-trained contextualized language model (PrLM) has made a significant impact on NLP, training PrLMs in languages other than English can be impractical for two reasons: other languages often lack corpora sufficient for training powerful PrLMs, and because of the commonalities among human languages, computationally expensive PrLM training for different languages is somewhat redundant.
On Secure Degrees of Freedom of the MIMO Interference Channel with Local Output Feedback
This paper studies the problem of sum-secure degrees of freedom (SDoF) of the (M, M, N, N) multiple-input multiple-output (MIMO) interference channel with local output feedback, so as to build an information-theoretic foundation and provide practical transmission schemes for 6G-enabled vehicles-to-vehicles (V2V).
Information Theory Information Theory
Turbulence suppression by streamwise-varying wall rotation in pipe flow
Two control parameters, which are velocity amplitude and wavelength, are considered.
Fluid Dynamics
Theory of competing Chern-Simons orders and emergent phase transitions
Namely, the Chern-Simons superconductor describes the planar N\'{e}el state, while the Chern-Simons exciton insulator corresponds to the non-uniform chiral spin-liquid.
Strongly Correlated Electrons
Uniform Object Rearrangement: From Complete Monotone Primitives to Efficient Non-Monotone Informed Search
DFSDP is extended to solve single-buffer, non-monotone instances, given a choice of an object and a buffer.
Edge Federated Learning Via Unit-Modulus Over-The-Air Computation
Simulation results show that the proposed UMAirComp framework with PAM algorithm achieves a smaller mean square error of model parameters' estimation, training loss, and test error compared with other benchmark schemes.
Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry
To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely on feature matching to associate online visual odometry (VO) with a previously built map.
Methodology-centered review of molecular modeling, simulation, and prediction of SARS-CoV-2
To provide the reader a quick update about the status of molecular modeling, simulation, and prediction of SARS-CoV-2, we present a comprehensive and systematic methodology-centered narrative in the nick of time.
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios.
Text Compression-aided Transformer Encoding
In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily.
High-α-Metal-Rich stars in the LAMOST-MRS survey and its connection with the galactic bulge
A tentative interpretation of this special group is that its stars were formed in the X-shaped bar/bulge region, close to its corotation radius, where radial migration is the most intense, and brings them to present locations at 9 kpc and beyond.
Astrophysics of Galaxies Solar and Stellar Astrophysics
Meta-Learning Dynamics Forecasting Using Task Inference
DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain.
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Key to such capability is hand-eye coordination, a cognitive ability that enables humans to adaptively direct their movements at task-relevant objects and be invariant to the objects' absolute spatial location.
Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles
The rapid increase of the data scale in Internet of Vehicles (IoV) system paradigm, hews out new possibilities in boosting the service quality for the emerging applications through data sharing.
Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization
Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method.
Autonomous Driving
Data Augmentation
+1
Robotics
Real-time Relevant Recommendation Suggestion
When finishing reading an item, users may want to access more relevant items related to the last read one as extended reading.
Vaccine-escape and fast-growing mutations in the United Kingdom, the United States, Singapore, Spain, South Africa, and other COVID-19-devastated countries
We further unveil that mutation N501Y involved in United Kingdom (UK), South Africa, and Brazil variants may moderately weaken the binding between the RBD and many known antibodies, while mutations E484K and K417N found in South Africa and Brazilian variants can potentially disrupt the binding between the RDB and many known antibodies.
Prototypical Representation Learning for Relation Extraction
This approach allows us to learn meaningful, interpretable prototypes for the final classification.
EfficientTDNN: Efficient Architecture Search for Speaker Recognition
Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition.
Advances and Challenges in Unsupervised Neural Machine Translation
Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results.
Shapley Explanation Networks
This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time.
Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis
The novelty of this design lies in exploiting channel noise to accelerate the descent in the region around each saddle point encountered by gradient descent, thereby increasing the convergence speed of over-the-air PCA.
Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model
Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing.
Long Short-Term Temporal Meta-learning in Online Recommendation
An effective online recommendation system should jointly capture users' long-term and short-term preferences in both users' internal behaviors (from the target recommendation task) and external behaviors (from other tasks).
Model Pruning Based on Quantified Similarity of Feature Maps
In this paper, we propose a novel theory to find redundant information in three-dimensional tensors, namely Quantified Similarity between Feature Maps (QSFM), and utilize this theory to guide the filter pruning procedure.
Variational Gaussian Topic Model with Invertible Neural Projections
Based on the variational auto-encoder, the proposed VaGTM models each topic with a multivariate Gaussian in decoder to incorporate word relatedness.
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents
Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
Inspired by the success of pre-training models in natural language processing, in this paper, we develop MusicBERT, a large-scale pre-trained model for music understanding.
Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain.
A New Channel Estimation Strategy in Intelligent Reflecting Surface Assisted Networks
Specifically, in Phase I, the correlation coefficients between the channels of a typical BS antenna and those of the other antennas are estimated; while in Phase II, the cascaded channel of the typical antenna is estimated.
Patient-independent Schizophrenia Relapse Prediction Using Mobile Sensor based Daily Behavioral Rhythm Changes
In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features.
Physics-Guided Deep Learning for Dynamical Systems: A Survey
Modeling complex physical dynamics is a fundamental task in science and engineering.
BAGUA: Scaling up Distributed Learning with System Relaxations
Recent years have witnessed a growing list of systems for distributed data-parallel training.
A Survey on Low-Resource Neural Machine Translation
Neural approaches have achieved state-of-the-art accuracy on machine translation but suffer from the high cost of collecting large scale parallel data.
Synthesizing Multi-Tracer PET Images for Alzheimer's Disease Patients using a 3D Unified Anatomy-aware Cyclic Adversarial Network
Thus, it is desirable to develop an efficient multi-tracer PET synthesis model that can generate multi-tracer PET from single-tracer PET.
