Search Results for author:
Found 630 papers, 203 papers with code
Multi-View Active Learning in the Non-Realizable Case
The sample complexity of active learning under the realizability assumption has been well-studied.
Evaluation of Unsupervised Information Extraction
Unsupervised methods gain more and more attention nowadays in information extraction area, which allows to design more open extraction systems.
Exploring The Contribution of Unlabeled Data in Financial Sentiment Analysis
We argue that if the bias-variance trade-off is to be better balanced by a more effective feature selection method unlabeled data is very likely to boost the classification performance.
Flexible and Robust Co-Regularized Multi-Domain Graph Clustering.
Moreover, relationships between instances in different domains may be associated with weights based on prior (partial) knowledge.
An Unsupervised Feature Learning Approach to Improve Automatic Incident Detection
Sophisticated automatic incident detection (AID) technology plays a key role in contemporary transportation systems.
Big Data and Cross-Document Coreference Resolution: Current State and Future Opportunities
Information Extraction (IE) is the task of automatically extracting structured information from unstructured/semi-structured machine-readable documents.
coreference-resolution
Cross Document Coreference Resolution
Group sparsity and geometry constrained dictionary learning for action recognition from depth maps.
Human action recognition based on the depth information provided by commodity depth sensors is an important yet challenging task.
Electrocardiography Separation of Mother and Baby
Extraction of Electrocardiography (ECG or EKG) signals of mother and baby is a challenging task, because one single device is used and it receives a mixture of multiple heart beats.
Optical Character Recognition, Using K-Nearest Neighbors
The problem of optical character recognition, OCR, has been widely discussed in the literature.
Optical Character Recognition
Optical Character Recognition (OCR)
Automatic Objects Removal for Scene Completion
With the explosive growth of web-based cameras and mobile devices, billions of photographs are uploaded to the internet.
Hierarchical recurrent neural network for skeleton based action recognition
Traditional methods generally model the spatial structure and temporal dynamics of human skeleton with hand-crafted features and recognize human actions by well-designed classifiers.
Ranked #118 on
Skeleton Based Action Recognition
on NTU RGB+D
Entity Suggestion by Example using a Conceptual Taxonomy
This paper provides a query processing method based on the relevance models between entity sets and concepts.
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Super resolving a low-resolution video is usually handled by either single-image super-resolution (SR) or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video super-resolution.
Ranked #18 on
Video Super-Resolution
on Vid4 - 4x upscaling
Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning
Relation learning is a fundamental operation in many computer vision tasks.
Depth and Reflection Total Variation for Single Image Dehazing
Haze removal has been a very challenging problem due to its ill-posedness, which is more ill-posed if the input data is only a single hazy image.
Deep Learning At Scale and At Ease
The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets.
Makeup like a superstar: Deep Localized Makeup Transfer Network
In this paper, we propose a novel Deep Localized Makeup Transfer Network to automatically recommend the most suitable makeup for a female and synthesis the makeup on her face.
Recurrent Face Aging
Modeling the aging process of human face is important for cross-age face verification and recognition.
Source-LDA: Enhancing probabilistic topic models using prior knowledge sources
The approach taken is to complement the existing topic distributions over words with a known distribution based on a predefined set of topics.
Ranking Causal Anomalies via Temporal and Dynamical Analysis on Vanishing Correlations
Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis.
A Comprehensive Survey on Cross-modal Retrieval
To speed up the cross-modal retrieval, a number of binary representation learning methods are proposed to map different modalities of data into a common Hamming space.
Derivative Delay Embedding: Online Modeling of Streaming Time Series
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval
Incompatibility of image descriptor and ranking is always neglected in image retrieval.
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder.
Ranked #35 on
Machine Translation
on WMT2014 English-French
Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)
Approximate Nearest neighbor search (ANNS) is fundamental and essential operation in applications from many domains, such as databases, machine learning, multimedia, and computer vision.
Databases
Deep Models for Engagement Assessment With Scarce Label Information
We compared performances of the new data representations with the original EEG features for engagement assessment.
What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
Based on the evaluation results, we also identify the best choices for different factors and propose a new multi-scale image feature representation method to encode the image effectively.
Multimodal Memory Modelling for Video Captioning
In this paper, we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide global visual attention on described targets.
Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we propose a selective multimodal Long Short-Term Memory network (sm-LSTM) for instance-aware image and sentence matching.
Ranked #14 on
Image Retrieval
on Flickr30K 1K test
Reinforcement Learning Based Argument Component Detection
Argument component detection (ACD) is an important sub-task in argumentation mining.
Feature Fusion using Extended Jaccard Graph and Stochastic Gradient Descent for Robot
In this paper, we use Kinect and propose a feature graph fusion (FGF) for robot recognition.
Kernel Truncated Regression Representation for Robust Subspace Clustering
Our method has the advantages of a closed-form solution and the capacity of clustering data points that lie on nonlinear subspaces.
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer.
Irregular Convolutional Neural Networks
Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN).
See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification
Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification.
SSGAN: Secure Steganography Based on Generative Adversarial Networks
Furthermore, a sophisticated steganalysis network is reconstructed for the discriminative network, and the network can better evaluate the performance of the generated images.
FoveaNet: Perspective-aware Urban Scene Parsing
Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors.
Theoretical Foundation of Co-Training and Disagreement-Based Algorithms
Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance.
A wavelet frame coefficient total variational model for image restoration
In this paper, we propose a vector total variation (VTV) of feature image model for image restoration.
Cross-Domain Image Retrieval with Attention Modeling
For query images, we use each candidate image in the database as the context to locate the query attention.
Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection
To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement to reliably reason about self-occluded landmarks, precisely capture the subtle landmark displacement and accurately detect landmarks even in presence of extremely large poses.
Verb Pattern: A Probabilistic Semantic Representation on Verbs
In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb.
Contextual Regression: An Accurate and Conveniently Interpretable Nonlinear Model for Mining Discovery from Scientific Data
We demonstrate its high prediction accuracy and sensitivity through the task of predictive feature selection on a simulated dataset and the application of predicting open chromatin sites in the human genome.
Latent Constrained Correlation Filter
In this paper, we introduce an intermediate step -- solution sampling -- after the data sampling step to form a subspace, in which an optimal solution can be estimated.
Analyzing Language Learned by an Active Question Answering Agent
We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017].
Face Aging with Contextual Generative Adversarial Nets
The age discriminative network guides the synthesized face to fit the real conditional distribution.
Every Smile is Unique: Landmark-Guided Diverse Smile Generation
Finally, these landmark sequences are translated into face videos.
Empirical Bayes Matrix Factorization
This yields a sparse EBMF approach - essentially a version of sparse FA/PCA - that automatically adapts the amount of sparsity to the data.
Methodology
Fast and robust misalignment correction of Fourier ptychographic microscopy
Fourier ptychographi cmicroscopy(FPM) is a newly developed computational imaging technique that can provide gigapixel images with both high resolution (HR) and wide field of view (FOV).
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks.
Fixed-Parameter Tractable Sampling for RNA Design with Multiple Target Structures
The design of multi-stable RNA molecules has important applications in biology, medicine, and biotechnology.
Quantitative Methods
Rafiki: Machine Learning as an Analytics Service System
Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users.
Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching
We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue.
PANDA: Facilitating Usable AI Development
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved.
Ranked #81 on
Skeleton Based Action Recognition
on NTU RGB+D
Network Reconstruction and Controlling Based on Structural Regularity Analysis
In addition, the model is capable of measuring the importance of microscopic network elements, i. e., nodes and links, in terms of network regularity thereby allowing us to regulate the reconstructability of networks based on them.
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
Second, few pose-based methods model the action-related objects in recognizing human-object interaction actions in which objects play an important role.
Action Recognition In Videos
Human-Object Interaction Detection
+2
Object-Level Representation Learning for Few-Shot Image Classification
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task.
Learning to Disentangle Interleaved Conversational Threads with a Siamese Hierarchical Network and Similarity Ranking
An enormous amount of conversation occurs online every day, such as on chat platforms where multiple conversations may take place concurrently.
Multistage Adversarial Losses for Pose-Based Human Image Synthesis
Human image synthesis has extensive practical applications e. g. person re-identification and data augmentation for human pose estimation.
M3: Multimodal Memory Modelling for Video Captioning
Inspired by the facts that memory modelling poses potential advantages to long-term sequential problems [35] and working memory is the key factor of visual attention [33], we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide visual attention on described visual targets to solve visual-textual alignments.
Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible.
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
There are great demands for automatically regulating inappropriate appearance of shocking firearm images in social media or identifying firearm types in forensics.
The normalized Laplacian spectra of subdivision vertex-edge neighbourhood vertex(edge)-corona for graphs
Whereafter, the normalized Laplacian spectra of $G_1^S\bowtie (G_2^V\cup G_3^E)$ and $G_1^S\diamondsuit(G_2^V\cup G_3^E)$ are respectively determined in terms of the corresponding normalized Laplacian spectra of the connected regular graphs $G_{1}$, $G_{2}$ and $G_{3}$, which extend the corresponding results of [A. Das, P. Panigrahi, Linear Multil.
Combinatorics
Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels
Recently, deep learning has shown its power in steganalysis.
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data
However, this representation is not in a natural language form, which is difficult for humans to understand.
Ranked #12 on
Data-to-Text Generation
on WebNLG
CreditCoin: A Privacy-Preserving Blockchain-Based Incentive Announcement Network for Communications of Smart Vehicles
The vehicular announcement network is one of the most promising utilities in the communications of smart vehicles and in the smart transportation systems.
Learning Deep Network Representations with Adversarially Regularized Autoencoders
The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the "semantics" of the original network structure.
Deep Learning for Single Image Super-Resolution: A Brief Review
Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions.
GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Therefore, this task requires a high-level understanding of the mapping between the input source gesture and the output target gesture.
Ranked #1 on
Gesture-to-Gesture Translation
on NTU Hand Digit
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs.
Ranked #1 on
Graph Similarity
on IMDb
Learning Gender-Neutral Word Embeddings
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications.
Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection
Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet.
Travel Speed Prediction with a Hierarchical Convolutional Neural Network and Long Short-Term Memory Model Framework
In this paper, we propose a data-driven modelling approach with a novel hierarchical D-CLSTM-t deep learning model for short-term traffic speed prediction, a framework combined with convolutional neural network (CNN) and long short-term memory (LSTM) models.
Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed.
Deep Micro-Dictionary Learning and Coding Network
In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN).
OxIOD: The Dataset for Deep Inertial Odometry
Advances in micro-electro-mechanical (MEMS) techniques enable inertial measurements units (IMUs) to be small, cheap, energy efficient, and widely used in smartphones, robots, and drones.
Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
To exploit the multilevel corresponding visual contents, we propose a pose-guided multi-granularity attention network (PMA).
Zero-Resource Multilingual Model Transfer: Learning What to Share
In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on
Cross-Lingual NER
on CoNLL Dutch
Data-Driven Tight Frame for Cryo-EM Image Denoising and Conformational Classification
We introduce the use of data-driven tight frame (DDTF) algorithm for cryo-EM image denoising.
Computation Image and Video Processing
Convolutional Set Matching for Graph Similarity
We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs.
Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks
Neural networks has been successfully used in the processing of Lidar data, especially in the scenario of autonomous driving.
Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation
As evidenced by our results on standard hand segmentation benchmarks and on our own dataset, our approach outperforms these other, simpler recurrent segmentation techniques, as well as the state-of-the-art hand segmentation one.
Cross-Technology Communications for Heterogeneous IoT Devices Through Artificial Doppler Shifts
To this end, we propose DopplerFi, a communication framework that enables a two-way communication channel between BLE and Wi-Fi by injecting artificial Doppler shifts, which can be decoded by sensing the patterns in the Gaussian frequency shift keying (GFSK) demodulator and Channel State Information (CSI).
Networking and Internet Architecture
Particle Probability Hypothesis Density Filter based on Pairwise Markov Chains
Most multi-target tracking filters assume that one target and its observation follow a Hidden Markov Chain (HMC) model, but the implicit independence assumption of HMC model is invalid in many practical applications, and a Pairwise Markov Chain (PMC) model is more universally suitable than traditional HMC model.
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
Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
Extensive experiments on the large-scale SQuAD and TriviaQA datasets validate the effectiveness of the proposed method.
Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression
To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps.
Improving MMD-GAN Training with Repulsive Loss Function
To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD.
Ranked #19 on
Image Generation
on STL-10
Ensembles of feedforward-designed convolutional neural networks
An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work.
ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis systems recently achieve promising progress to take over tedious examinations by cardiologists.
Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data.
Generative Adversarial Network
Image-to-Image Translation
+1
Evolving the pulmonary nodules diagnosis from classical approaches to deep learning aided decision support: three decades development course and future prospect
Lung cancer is the commonest cause of cancer deaths worldwide, and its mortality can be reduced significantly by performing early diagnosis and screening.
Attribute-Guided Sketch Generation
To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation.
Multi-Depth Fusion Network for Whole-Heart CT Image Segmentation
Obtaining precise whole-heart segmentation from computed tomography (CT) or other imaging techniques is prerequisite to clinically analyze the cardiac status, which plays an important role in the treatment of cardiovascular diseases.
Lightweight Feature Fusion Network for Single Image Super-Resolution
Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit.
Ranked #11 on
Image Super-Resolution
on Manga109 - 3x upscaling
Efficient Memory Management for GPU-based Deep Learning Systems
They are achieved by exploiting the iterative nature of the training algorithm of deep learning to derive the lifetime and read/write order of all variables.
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Nevertheless, how to effectively extract discriminative spatial and temporal features is still a challenging problem.
Ranked #51 on
Skeleton Based Action Recognition
on NTU RGB+D
CN-Probase: A Data-driven Approach for Large-scale Chinese Taxonomy Construction
Taxonomies play an important role in machine intelligence.
On the generalization of GAN image forensics
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect.
KBQA: Learning Question Answering over QA Corpora and Knowledge Bases
Based on these templates, our QA system KBQA effectively supports binary factoid questions, as well as complex questions which are composed of a series of binary factoid questions.
Monte Carlo Neural Fictitious Self-Play: Approach to Approximate Nash equilibrium of Imperfect-Information Games
Experimentally, we demonstrate that the proposed Monte Carlo Neural Fictitious Self Play can converge to approximate Nash equilibrium in games with large-scale search depth while the Neural Fictitious Self Play can't.
CFSNet: Toward a Controllable Feature Space for Image Restoration
Deep learning methods have witnessed the great progress in image restoration with specific metrics (e. g., PSNR, SSIM).
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.
Ranked #1 on
Graph Classification
on Web
OpBerg: Discovering causal sentences using optimal alignments
Current methods for extracting causal sentences are based on either machine learning or a predefined database of causal terms.
Effective and Efficient Dropout for Deep Convolutional Neural Networks
However, many recent works show that the standard dropout is ineffective or even detrimental to the training of CNNs.
Dynamic Routing Networks
The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs.
Expression Conditional GAN for Facial Expression-to-Expression Translation
In this paper, we focus on the facial expression translation task and propose a novel Expression Conditional GAN (ECGAN) which can learn the mapping from one image domain to another one based on an additional expression attribute.
Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal
To address MH-QA specifically, we propose a Deep Reinforcement Learning based method capable of learning sequential reasoning across large collections of documents so as to pass a query-aware, fixed-size context subset to existing models for answer extraction.
Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images
Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist.
mID: Tracking and Identifying People with Millimeter Wave Radar
The key to offering personalised services in smart spaces is knowing where a particular person is with a high degree of accuracy.
How to best use Syntax in Semantic Role Labelling
There are many different ways in which external information might be used in an NLP task.
Joint Multi-Label Attention Networks for Social Text Annotation
To better utilise this information, we design a framework that separates the title from the content of a document and apply a title-guided attention mechanism over each sentence in the content.
Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation
Noise and domain are important aspects of data quality for neural machine translation.
Progressive Cluster Purification for Transductive Few-shot Learning
Furthermore, the inter-class classification and the intra-class transduction are extremely flexible to be repeated several times to progressively purify the clusters.
Recurrent U-Net for Resource-Constrained Segmentation
State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs.
Antonym-Synonym Classification Based on New Sub-space Embeddings
We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper.
A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset
Underwater image enhancement algorithms have attracted much attention in underwater vision task.
Backpropagation-Friendly Eigendecomposition
Eigendecomposition (ED) is widely used in deep networks.
Database Meets Deep Learning: Challenges and Opportunities
Deep learning has recently become very popular on account of its incredible success in many complex data-driven applications, such as image classification and speech recognition.
Artificial Intelligence Governance and Ethics: Global Perspectives
Artificial intelligence (AI) is a technology which is increasingly being utilised in society and the economy worldwide, and its implementation is planned to become more prevalent in coming years.
Enhancing Air Quality Prediction with Social Media and Natural Language Processing
Accompanied by modern industrial developments, air pollution has already become a major concern for human health.
Dynamically Composing Domain-Data Selection with Clean-Data Selection by ``Co-Curricular Learning'' for Neural Machine Translation
Noise and domain are important aspects of data quality for neural machine translation.
Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties.
Proximal Policy Optimization with Mixed Distributed Training
Instability and slowness are two main problems in deep reinforcement learning.
Jointly Extracting Multiple Triplets with Multilayer Translation Constraints
Triplets extraction is an essential and pivotal step in automatic knowledge base construction, which captures structural information from unstructured text corpus.
Dynamic Malware Analysis with Feature Engineering and Feature Learning
In this paper, we propose a novel and low-cost feature extraction approach, and an effective deep neural network architecture for accurate and fast malware detection.
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (C$^2$GAN) for the task of keypoint-guided image generation.
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as sentiment classification, natural language inference, semantic textual similarity and question answering.
Ranked #1 on
Natural Language Inference
on QNLI
Learning a Multi-Domain Curriculum for Neural Machine Translation
Most data selection research in machine translation focuses on improving a single domain.
Incorporating External Knowledge into Machine Reading for Generative Question Answering
Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context.
Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
To identify adversarial attacks, a perturbation discriminator validates how likely a token in the text is perturbed and provides a set of potential perturbations.
The Disruptions of 5G on Data-driven Technologies and Applications
With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management.
Networking and Internet Architecture Databases Distributed, Parallel, and Cluster Computing
Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP).
LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution
In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution.
Ranked #14 on
Image Super-Resolution
on Set14 - 3x upscaling
An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image
A CNN segmentation model was trained based on the augmented training data by leave-one-out strategy.
DeepTIO: A Deep Thermal-Inertial Odometry with Visual Hallucination
The hallucination network is taught to predict fake visual features from thermal images by using Huber loss.
Understanding Architectures Learnt by Cell-based Neural Architecture Search
Neural architecture search (NAS) searches architectures automatically for given tasks, e. g., image classification and language modeling.
Sensor-Augmented Neural Adaptive Bitrate Video Streaming on UAVs
In this paper, we present SA-ABR, a new sensor-augmented system that generates ABR video streaming algorithms with the assistance of various kinds of inherent sensor data that are used to pilot UAVs.
Neural Maximum Common Subgraph Detection with Guided Subgraph Extraction
Maximum Common Subgraph (MCS) is defined as the largest subgraph that is commonly present in both graphs of a graph pair.
Robust Natural Language Representation Learning for Natural Language Inference by Projecting Superficial Words out
In natural language inference, the semantics of some words do not affect the inference.
Distribution Matching Prototypical Network for Unsupervised Domain Adaptation
State-of-the-art Unsupervised Domain Adaptation (UDA) methods learn transferable features by minimizing the feature distribution discrepancy between the source and target domains.
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks.
Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise
However, the practical noise under high sensitivity setting in real captured videos is complex and inaccurate to model with these assumptions.
Learning Robust Representations with Graph Denoising Policy Network
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.
MUTLA: A Large-Scale Dataset for Multimodal Teaching and Learning Analytics
Automatic analysis of teacher and student interactions could be very important to improve the quality of teaching and student engagement.
Coarse-To-Fine Visual Localization Using Semantic Compact Map
Robust visual localization for urban vehicles remains challenging and unsolved.
DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network
There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images.
Abnormal Client Behavior Detection in Federated Learning
In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server.
Study of Constrained Network Structures for WGANs on Numeric Data Generation
Especially, Isomorphic WGAN is the best in 15/20 experiments.
Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem.
Single-Stage 6D Object Pose Estimation
Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task.
HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition
To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming.
RTN: Reparameterized Ternary Network
We first bring up three omitted issues in extremely low-bit networks: the squashing range of quantized values; the gradient vanishing during backpropagation and the unexploited hardware acceleration of ternary networks.
Self Organizing Nebulous Growths for Robust and Incremental Data Visualization
In addition, SONG is capable of handling new data increments, no matter whether they are similar or heterogeneous to the already observed data distribution.
Automatic Analysis System of Calcaneus Radiograph: Rotation-Invariant Landmark Detection for Calcaneal Angle Measurement, Fracture Identification and Fracture Region Segmentation
This study aims to develop an analysis system that can automatically locate four anatomic landmarks, measure BA and CAG for fracture assessment, identify fractured calcaneus, and segment fractured regions.
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
The new types of generated images are emerging one after another, and the existing detection methods cannot cope well.
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market.
A New Ensemble Method for Concessively Targeted Multi-model Attack
Thus, in this paper, we propose a new attack mechanism which performs the non-targeted attack when the targeted attack fails.
Importance Filtered Cross-Domain Adaptation
Firstly, an importance filtered mechanism is devised to generate filtered soft labels to mitigate negative transfer desirably.
ISBNet: Instance-aware Selective Branching Networks
Recent years have witnessed growing interests in designing efficient neural networks and neural architecture search (NAS).
Deep Learning based Pedestrian Inertial Navigation: Methods, Dataset and On-Device Inference
Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots.
Interpretable Click-Through Rate Prediction through Hierarchical Attention
For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks.
A deep network for sinogram and CT image reconstruction
A CT image can be well reconstructed when the sampling rate of the sinogram satisfies the Nyquist criteria and the sampled signal is noise-free.
Recommending Themes for Ad Creative Design via Visual-Linguistic Representations
There is a perennial need in the online advertising industry to refresh ad creatives, i. e., images and text used for enticing online users towards a brand.
Temporal Pulses Driven Spiking Neural Network for Fast Object Recognition in Autonomous Driving
Accurate real-time object recognition from sensory data has long been a crucial and challenging task for autonomous driving.
Learning to Detect Malicious Clients for Robust Federated Learning
Federated learning systems are vulnerable to attacks from malicious clients.
GLSearch: Maximum Common Subgraph Detection via Learning to Search
However, MCS computation is NP-hard, and state-of-the-art MCS solvers rely on heuristic search algorithms which in practice cannot find good solution for large graph pairs given a limited computation budget.
Deep Multi-Task Learning via Generalized Tensor Trace Norm
The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures.
Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach
The feature extraction model transforms original data and threshold to a Hamming space, in which a deep learning-based regression model is utilized to exploit the incremental property of cardinality w. r. t.
Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition
In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks.
PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
Communication-Efficient Distributed Deep Learning: A Comprehensive Survey
In this paper, we provide a comprehensive survey of the communication-efficient distributed training algorithms, focusing on both system-level and algorithmic-level optimizations.
DymSLAM:4D Dynamic Scene Reconstruction Based on Geometrical Motion Segmentation
The only input of DymSLAM is stereo video, and its output includes a dense map of the static environment, 3D model of the moving objects and the trajectories of the camera and the moving objects.
Emotion Recognition From Gait Analyses: Current Research and Future Directions
This article reviews current research on gait-based emotion detection, particularly on how gait parameters can be affected by different emotion states and how the emotion states can be recognized through distinct gait patterns.
Revisit Systematic Generalization via Meaningful Learning
Humans can systematically generalize to novel compositions of existing concepts.
Efficient Bitwidth Search for Practical Mixed Precision Neural Network
Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks.
TRACER: A Framework for Facilitating Accurate and Interpretable Analytics for High Stakes Applications
In high stakes applications such as healthcare and finance analytics, the interpretability of predictive models is required and necessary for domain practitioners to trust the predictions.
Software Language Comprehension using a Program-Derived Semantics Graph
To continue to advance this research, we present the program-derived semantics graph, a new graphical structure to capture semantics of code.
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
A Recurrent Model for Collective Entity Linking with Adaptive Features
Traditional machine learning based methods for NED were outperformed and made obsolete by the state-of-the-art deep learning based models.
Open Domain Dialogue Generation with Latent Images
Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques.
Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations
Fine-Grained Named Entity Typing (FG-NET) is a key component in Natural Language Processing (NLP).
Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments
As objects are often observed locally, the proposed algorithm uses the symmetrical properties of indoor artificial objects to estimate the occluded parts to obtain more accurate quadric parameters.
Kinship Identification through Joint Learning Using Kinship Verification Ensembles
The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Ranked #1 on
Text Generation
on CNN/Daily Mail
Abstractive Text Summarization
Conversational Response Generation
+8
"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition
In this paper, we propose Pronunciation-attentive Contextualized Pun Recognition (PCPR) to perceive human humor, detect if a sentence contains puns and locate them in the sentence.
One-Shot Image Classification by Learning to Restore Prototypes
In this paper, we adopt metric learning for this problem, which has been applied for few- and many-shot image classification by comparing the distance between the test image and the center of each class in the feature space.
TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator
The D-r optimizes the target bounding box estimated by SiamRPN++, based on the spatial depth distribution difference between the target and the surrounding background.
Sparsely-Labeled Source Assisted Domain Adaptation
However, there are usually a large number of unlabeled data but only a few labeled data in the source domain, and how to transfer knowledge from this sparsely-labeled source domain to the target domain is still a challenge, which greatly limits their application in the wild.
DEFM: Delay E mbedding based Forecast Machine for Time Series Forecasting by Spatiotemporal Information Transformation
Making accurate forecasts for a complex system is a challenge in various practical applications.
Consistent and Flexible Selectivity Estimation for High-Dimensional Data
Selectivity estimation aims at estimating the number of database objects that satisfy a selection criterion.
