Search Results for author:
Found 633 papers, 204 papers with code
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.
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.
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
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.
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
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.
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.
Every Smile is Unique: Landmark-Guided Diverse Smile Generation
Finally, these landmark sequences are translated into face videos.
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).
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.
Face Aging with Contextual Generative Adversarial Nets
The age discriminative network guides the synthesized face to fit the real conditional distribution.
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].
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.
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.
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.
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.
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.
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.
Irregular Convolutional Neural Networks
Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN).
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.
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.
Reinforcement Learning Based Argument Component Detection
Argument component detection (ACD) is an important sub-task in argumentation mining.
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
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.
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.
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.
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.
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.
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.
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.
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)
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
An Unsupervised Feature Learning Approach to Improve Automatic Incident Detection
Sophisticated automatic incident detection (AID) technology plays a key role in contemporary transportation 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.
Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels
Recently, deep learning has shown its power in steganalysis.
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.
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).
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
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.
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
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.
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.
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
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.
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
Multi-View Active Learning in the Non-Realizable Case
The sample complexity of active learning under the realizability assumption has been well-studied.
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.
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.
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.
Recurrent Face Aging
Modeling the aging process of human face is important for cross-age face verification and recognition.
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.
Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning
Relation learning is a fundamental operation in many computer vision tasks.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
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.
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.
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.
Coarse-To-Fine Visual Localization Using Semantic Compact Map
Robust visual localization for urban vehicles remains challenging and unsolved.
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.
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.
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.
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.
Study of Constrained Network Structures for WGANs on Numeric Data Generation
Especially, Isomorphic WGAN is the best in 15/20 experiments.
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.
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.
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.
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.
ISBNet: Instance-aware Selective Branching Networks
Recent years have witnessed growing interests in designing efficient neural networks and neural architecture search (NAS).
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.
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.
Importance Filtered Cross-Domain Adaptation
Firstly, an importance filtered mechanism is devised to generate filtered soft labels to mitigate negative transfer desirably.
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.
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.
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.
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.
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.
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.
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.
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).
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.
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.
Adversarial Attack on Hierarchical Graph Pooling Neural Networks
However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task.
Self-Training for Domain Adaptive Scene Text Detection
To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.
Learning Effective Representations for Person-Job Fit by Feature Fusion
In this paper, we propose to learn comprehensive and effective representations of the candidates and job posts via feature fusion.
Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
The model provides automated recognition of given scans and generation of reports.
``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.
Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
We introduce Bi-GNN for modeling biological link prediction tasks such as drug-drug interaction (DDI) and protein-protein interaction (PPI).
Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
Rethink Maximum Mean Discrepancy for Domain Adaptation
On the other hand, we design two different strategies to boost the feature discriminability: 1) we directly impose a trade-off parameter on the implicit intra-class distance in MMD to regulate its change; 2) we impose the similar weights revealed in MMD on inter-class distance and maximize it, then a balanced factor could be introduced to quantitatively leverage the relative importance between the feature transferability and its discriminability.
Consensus Multi-Agent Reinforcement Learning for Volt-VAR Control in Power Distribution Networks
Volt-VAR control (VVC) is a critical application in active distribution network management system to reduce network losses and improve voltage profile.
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain.
More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
Artificial Intelligence (AI) has attracted a great deal of attention in recent years.
Using UNet and PSPNet to explore the reusability principle of CNN parameters
Some previous work like Deep transfer learning reuse the model parameters trained for the first task as the starting point for the second task, and semi-supervised learning is trained upon a combination of labeled and unlabeled data.
Exploring the parameter reusability of CNN
In recent times, using small data to train networks has become a hot topic in the field of deep learning.
Socially-Aware Conference Participant Recommendation with Personality Traits
As a result of the importance of academic collaboration at smart conferences, various researchers have utilized recommender systems to generate effective recommendations for participants.
Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement
Since major ad platforms typically run A/B tests for multiple advertisers in parallel, we explore the possibility of collaboratively learning ad creative refinement via A/B tests of multiple advertisers.
Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Recent works have shown that attention mechanism is beneficial to the fusion process.
Improving Smart Conference Participation through Socially-Aware Recommendation
This research addresses recommending presentation sessions at smart conferences to participants.
Improving adversarial robustness of deep neural networks by using semantic information
The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original inputs, raises concerns about the robustness of DNNs to such attacks.
Robust Graph Representation Learning via Neural Sparsification
Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection.
GraphCrop: Subgraph Cropping for Graph Classification
We present a new method to regularize graph neural networks (GNNs) for better generalization in graph classification.
Is Each Layer Non-trivial in CNN?
Convolutional neural network (CNN) models have achieved great success in many fields.
Distributed ADMM with Synergetic Communication and Computation
In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system.
A self-explanatory method for the black problem on discrimination part of CNN
However, it is hard for the interpretable models to approximate the discrimination part because of the tradeoff problem between interpretability performance and generalization performance of the discrimination part.
Learning to Search for Fast Maximum Common Subgraph Detection
Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in biomedical analysis, malware detection, cloud computing, etc.
Certified Distributional Robustness via Smoothed Classifiers
We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.
Multivariate Time Series Classification with Hierarchical Variational Graph Pooling
Then we combine GNNs and our proposed variational graph pooling layers for joint graph representation learning and graph coarsening, after which the graph is progressively coarsened to one node.
A Skew-Sensitive Evaluation Framework for Imbalanced Data Classification
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task.
Consistency and Coherency Enhanced Story Generation
In terms of consistency, on one hand, GPT2 cannot guarantee the consistency of the plots explicitly.
Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders.
Certified Distributional Robustness on Smoothed Classifiers
For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.
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
Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation
In recent studies, Generative Adversarial Network (GAN) is one of the popular schemes to augment the image dataset.
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
Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization
After that, maximum margin formulation is introduced to jointly enable the induction of predictive model and the estimation of labeling confidence over unlabeled data.
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.
Abstractive Text Summarization
Conversational Response Generation
+8
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.
From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.
Distributed, Parallel, and Cluster Computing
Robot-assisted Backscatter Localization for IoT Applications
Recent years have witnessed the rapid proliferation of backscatter technologies that realize the ubiquitous and long-term connectivity to empower smart cities and smart homes.
Artificial Lateral Line Based Relative State Estimation for Two Adjacent Robotic Fish
Then four typical regression methods, including random forest algorithm, support vector regression, back propagation neural network, and multiple linear regression method are used for establishing regression models between the ALLS-measured HPVs and the relative states.
Quantitative Statistical Robustness for Tail-Dependent Law Invariant Risk Measures
When estimating the risk of a financial position with empirical data or Monte Carlo simulations via a tail-dependent law invariant risk measure such as the Conditional Value-at-Risk (CVaR), it is important to ensure the robustness of the statistical estimator particularly when the data contain noise.
A Novel Mobility Model to Support the Routing of Mobile Energy Resources
Mobile energy resources (MERs) have received increasing attention due to their effectiveness in boosting the power system resilience in a flexible way.
Sequential Resource Access: Theory and Algorithm
We formulate and analyze a generic sequential resource access problem arising in a variety of engineering fields, where a user disposes a number of heterogeneous computing, communication, or storage resources, each characterized by the probability of successfully executing the user's task and the related access delay and cost, and seeks an optimal access strategy to maximize her utility within a given time horizon, defined as the expected reward minus the access cost.
Networking and Internet Architecture
Long Term Motion Prediction Using Keyposes
Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving.
Cloud Cover and Aurora Contamination at Dome A in 2017 from KLCAM
Dome A in Antarctica has many characteristics that make it an excellent site for astronomical observations, from the optical to the terahertz.
Instrumentation and Methods for Astrophysics
Peer-to-Peer Localization for Single-Antenna Devices
In this paper, we present P2PLocate, a peer-to-peer localization system that enables a single-antenna device co-located with a batteryless backscatter tag to localize another single-antenna device with decimeter-level accuracy.
Tetraquark Interpretation and Production Mechanism of the Belle $Y_b (10750)$-Resonance
Recently, the Belle Collaboration has updated the analysis of the cross sections for the processes $e^+ e^- \to \Upsilon(nS)\, \pi^+ \pi^-$ ($n = 1,\, 2,\, 3$) in the $e^+ e^-$ center-of-mass energy range from 10. 52 to 11. 02~GeV.
High Energy Physics - Phenomenology High Energy Physics - Experiment
InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction
We see information sources as multiple views and fusing them to construct an intact space with sufficient information.
A Note on Graph-Based Nearest Neighbor Search
And which data property affects the efficiency and how?
A liquid scintillator for a neutrino Detector working at -50 degree
A liquid scintillator (LS) is developed for the Taishan Antineutrino Observatory (TAO), a ton-level neutrino detector to measure the reactor antineutrino spectrum with sub-percent energy resolution by adopting Silicon Photomultipliers (SiPMs) as photosensor.
Instrumentation and Detectors High Energy Physics - Experiment
MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning
The following work presents a new algorithm for character recognition from obfuscated images.
Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
In this paper, we emphasize the significance of reducing feature redundancy for improving UDA in a bi-level way.
Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos
Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.
Time Series Analysis
Video Forensics
Cryptography and Security
A New Weighting Scheme for Fan-beam and Circle Cone-beam CT Reconstructions
In this paper, we first present an arc based algorithm for fan-beam computed tomography (CT) reconstruction via applying Katsevich's helical CT formula to 2D fan-beam CT reconstruction.
Exploring Adversarial Fake Images on Face Manifold
Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models.
Abnormal topological refraction into free medium at sub-wavelength scale in valley phononic crystal plates
In this work we propose a topological valley phononic crystal plate and we extensively investigate the refraction of valley modes into the surrounding homogeneous medium.
Applied Physics
A Spike Learning System for Event-driven Object Recognition
The proposed temporal coding scheme maps each event's arrival time and data into SNN spike time so that asynchronously-arrived events are processed immediately without delay.
A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.
FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space
Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context.
Generating Diversified Comments via Reader-Aware Topic Modeling and Saliency Detection
Automatic comment generation is a special and challenging task to verify the model ability on news content comprehension and language generation.
Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors
Particle tracks and differential energy loss measured in high pressure gaseous detectors can be exploited for event identification in neutrinoless double beta decay~($0\nu \beta \beta$) searches.
Instrumentation and Detectors High Energy Physics - Experiment
CREATe: Clinical Report Extraction and Annotation Technology
Clinical case reports are written descriptions of the unique aspects of a particular clinical case, playing an essential role in sharing clinical experiences about atypical disease phenotypes and new therapies.
Self-Renormalization of Quasi-Light-Front Correlators on the Lattice
In applying large-momentum effective theory, renormalization of the Euclidean correlators in lattice regularization is a challenge due to linear divergences in the self-energy of Wilson lines.
High Energy Physics - Lattice High Energy Physics - Phenomenology
Fusing Medical Image Features and Clinical Features with Deep Learning for Computer-Aided Diagnosis
Current Computer-Aided Diagnosis (CAD) methods mainly depend on medical images.
SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations.
RadarLoc: Learning to Relocalize in FMCW Radar
There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images.
Clinical Trial Drug Safety Assessment for Studies and Submissions Impacted by COVID-19
In this paper, we provide guidance on how standard safety analyses and reporting of clinical trial safety data may need to be modified, given the potential impact of the COVID-19 pandemic.
AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment
In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes.
Locate then Segment: A Strong Pipeline for Referring Image Segmentation
Referring image segmentation aims to segment the objects referred by a natural language expression.
Generalized Referring Expression Segmentation
Image Segmentation
+2
