This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE).
Therefore, to make up for the vacancy of Chinese AMR parsing evaluation methods, based on AMR evaluation metric smatch, we have improved the algorithm of generating triples so that to make it compatible with concept alignment and relation alignment.
“连动句是形如“NP+VP1+VP2”的句子, 句中含有两个或两个以上的动词(或动词结构)且动词的施事为同一对象。相同结构的连动句可以表示多种不同的语义关系。本文基于前人对连动句中VP1和VP2之间的语义关系分类, 标注了连动句语义关系数据集, 基于神经网络完成了对连动句语义关系的识别。该方法将连动句语义识别任务进行分解, 基于BERT进行编码, 利用BiLSTM-CRF先识别出连动句中连动词(VP)及其主语(NP), 再基于融合连动词信息的编码, 利用BiLSTM-Attention对连动词进行关系判别, 实验结果验证了所提方法的有效性。”
Given an input video, the MedVidCL task aims to correctly classify it into one of three following categories: Medical Instructional, Medical Non-instructional, and Non-medical.
Question Answering (QA) is a Natural Language Processing (NLP) task that can measure language and semantics understanding ability, it requires a system not only to retrieve relevant documents from a large number of articles but also to answer corresponding questions according to documents.
This paper describes the contribution of the LingJing team’s method to the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Emotion Classification.
For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages.
作为信息抽取的一项核心子任务, 实体关系抽取对于知识图谱、智能问答、语义搜索等自然语言处理应用都十分重要。关系抽取在于从非结构化文本中自动地识别实体之间具有的某种语义关系。该文聚焦句子级别的关系抽取研究, 介绍用于关系抽取的主要数据集并对现有的技术作了阐述, 主要分为:有监督的关系抽取、远程监督的关系抽取和实体关系联合抽取。我们对比用于该任务的各种模型, 分析它们的贡献与缺 陷。最后介绍中文实体关系抽取的研究现状和方法。
连动句是具有连动结构的句子, 是汉语中的特殊句法结构, 在现代汉语中十分常见且使用频繁。连动句语法结构和语义关系都很复杂, 在识别中存在许多问题, 对此本文针对连动句的识别问题进行了研究, 提出了一种基于神经网络的连动句识别方法。本方法分两步:第一步, 运用简单的规则对语料进行预处理;第二步, 用文本分类的思想, 使用BERT编码, 利用多层CNN与BiLSTM模型联合提取特征进行分类, 进而完成连动句识别任务。在人工标注的语料上进行实验, 实验结果达到92. 71%的准确率, F1值为87. 41%。
疑问句的句法语义分析在搜索引擎、信息抽取和问答系统等领域有着广泛的应用。计算语言学多采取问句分类和句法分析相结合的方式来处理疑问句, 精度和效率还不理想。而疑问句的语言学研究成果丰富, 比如疑问句的结构类型、疑问焦点和疑问代词的非疑问用法等, 但缺乏系统的形式化表示。本文致力于解决这一难题, 采用基于图结构的汉语句子语义的整体表示方法—中文抽象语义表示(CAMR)来标注疑问句的语义结构, 将疑问焦点和整句语义一体化表示出来。然后选取了宾州中文树库CTB8. 0网络媒体语料、小学语文教材以及《小王子》中文译本的2万句语料中共计2071句疑问句, 统计了疑问句的主要特点。统计表明, 各种疑问代词都可以通过疑问概念amr-unknown和语义关系的组合来表示, 能够完整地表示出疑问句的关键信息、疑问焦点和语义结构。最后, 根据疑问代词所关联的语义关系, 统计了疑问焦点的概率分布, 其中原因、修饰语和受事的占比最高, 分别占26. 53%、16. 73%以及16. 44%。基于抽象语义表示的疑问句标注与分析可以为汉语疑问句研究提供基础理论与资源。
对话分析是智能客服、聊天机器人等自然语言对话应用的基础课题, 而对话语料与常规书面语料有较大差异, 存在大量的称谓、情感短语、省略、语序颠倒、冗余等复杂现象, 对句法和语义分析器的影响较大, 对话自动分析的准确率相对书面语料一直不高。其主要原因在于对多轮对话缺乏严整的形式化描写方式, 不利于后续的分析计算。因此, 本文在梳理国内外针对对话的标注体系和语料库的基础上, 提出了基于抽象语义表示的篇章级多轮对话标注体系。具体探讨了了篇章级别的语义结构标注方法, 给出了词语和概念关系的对齐方案, 针对称谓语和情感短语增加了相应的语义关系和概念, 调整了表示主观情感词语的论元结构, 并对对话中一些特殊现象进行了规定, 设计了人工标注平台, 为大规模的多轮对话语料库标注与计算研究奠定基础。
One significant change we have made to the AMR annotation methodology is the inclusion of the alignment between word tokens in the sentence and the concepts/relations in the CAMR annotation to make it easier for automatic parsers to model the correspondence between a sentence and its meaning representation.
"《古籍汉字分级字表》是基于大规模古籍文本语料库、为辅助学习者古籍文献阅读而研制的分级字表。该字表填补了古籍字表研究成果的空缺, 依据各汉字学习优先级别的不同, 实现了古籍汉字的等级划分, 目前收录一级字105个, 二级字340个, 三级字555个。本文介绍了该字表研制的主要依据和基本步骤, 并将其与传统识字教材“三百千”及《现代汉语常用字表》进行比较, 验证了其收字的合理性。该字表有助于学习者优先掌握古籍文本常用字, 提升古籍阅读能力, 从而促进中华优秀传统文化的继承与发展。”
In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks.
A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations.
“先秦汉语在汉语史研究上具有重要地位, 然而以往的研究始终没有形成结构化的先秦词汇资源, 难以满足古汉语信息处理和跨语言对比的研究需要。国际上以英文词网(WordNet)的义类架构为基础, 已经建立了数十种语言的词网, 已经成为多语言自然语言处理和跨语言对比的基础资源。本文综述了国内外各种词网的构建情况, 特别是古代语言的词网和汉语词网, 然后详细介绍了先秦词网的构建和校正过程, 构建起了涵盖43591个词语、61227个义项、17975个义类的先秦汉语词网。本文还通过与古梵语词网的跨语言对比, 尝试分析这两种古老语言在词汇上的共性和差异, 初步验证先秦词网的有效性。”
“汉语词语的离合现象是汉语中一种词语可分可合的特殊现象。本文采用字符级序列标注方法解决二字动词离合现象的自动识别问题, 以避免中文分词及词性标注的错误传递, 节省制定匹配规则与特征模板的人工开支。在训练过程中微调BERT中文预训练模型, 获取面向目标任务的字符向量表示, 并引入掩码机制对模型隐藏离用法中分离的词语, 减轻词语本身对识别结果的影响, 强化中间插入成分的学习, 并对前后语素采用不同的掩码以强调其出现顺序, 进而使模型具备了识别复杂及偶发性离用法的能力。为获得含有上下文信息的句子表达, 将原始的句子表达与采用掩码的句子表达分别输入两个不同参数的BiLSTM层进行训练, 最后采用CRF算法捕捉句子标签序列的依赖关系。本文提出的BERT MASK + 2BiLSTMs + CRF模型比现有最优的离合词识别模型提高了2. 85%的F1值。”
This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022).
Glutamate-gated kainate receptors (KARs) are ubiquitous in the central nervous system of vertebrates, mediate synaptic transmission on post-synapse, and modulate transmitter release on pre-synapse.
In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal.
The model also achieves the new ability: Gaussian processes are employed as priors of view latent variables for generation and novel-view prediction without viewpoint annotations.
In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
As the deep learning rapidly promote, the artificial texts created by generative models are commonly used in news and social media.
In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way.
Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision.
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #1 on Object Detection on COCO test-dev (using extra training data)
In this paper, we propose a federated adaptive prompt tuning algorithm, FedAPT, for cross-domain federated image classification scenarios with the vision-language pre-trained model, CLIP, which gives play to the strong representation ability in FL.
This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence.
We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question.
In this paper, we first analyze the generalization bound of the aggregation model produced from knowledge distillation for the client domains, and then describe two challenges, server-to-client discrepancy and client-to-client discrepancy, brought to the aggregation model by the domain discrepancies.
The proposed scheme generates diverse prompts from a domain bank that contains many more diverse domains than existing DG datasets.
We observe that the global characteristics of the transformer make it easier to extract contextual information to perform depth estimation of transparent areas.
The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks.
However, making full use of the abundant information available from LFIs, such as 2D array of sub-views and the disparity map of each sub-view, for effective rain removal is still a challenging problem.
We connect Fourier amplitude and phase with Gram matrices and a content reconstruction loss in style transfer, respectively.
At first, we propose a novel clear memory-augmented module, which combines the encoding and memory-encoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preservation clear backgrounds.
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
Besides estimating the probability distribution, our entropy model also generates the quantization step at spatial-channel-wise.
To fully leverage the visual information for both scene understanding and dialogue generation, we propose the scene-aware prompt for the MDUG task.
In order to learn both the global knowledge and the personalized knowledge in different domains, the proposed framework first performs the federated training to obtain a public global aggregated model through multi-teacher distillation, and sends the aggregated model back to each client for finetuning its personalized local model.
The development of reconfigurable intelligent surfaces (RIS) has recently advanced the research of physical layer security (PLS).
We propose a normalized distortion threshold to evaluate the sensitivity of each involved convolutional layer of the base model to guide STD-NET to compress target network in an efficient and unsupervised approach, and obtain two network structures of different shapes with low computation cost and similar performance compared with the original one.
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
These methods generally extract the global features as descriptor to represent the original image.
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.
Federated Learning (FL) has recently made significant progress as a new machine learning paradigm for privacy protection.
The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic.
The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries.
This paper describes our proposed method for the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Personality Prediction (PER) and Reactivity Index Prediction (IRI).
The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame.
This paper studies multi-unit auctions powered by intermediaries, where each intermediary owns a private set of unit-demand buyers and all intermediaries are networked with each other.
However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task.
Blood pressure (BP) monitoring is vital in daily healthcare, especially for cardiovascular diseases.
Visual scene representation learning is an important research problem in the field of computer vision.
A growing number of service providers are exploring methods to improve server utilization, reduce power consumption, and reduce total cost of ownership by co-scheduling high-priority latency-critical workloads with best-effort workloads.
The experimental results indicate that the performance of baselines on CTR datasets is not as good as that on English datasets due to the characteristics of Chinese texts that are quite different from the Latin alphabet.
Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators.
However, the recognition of low-resolution scene text images remains a challenge.
To address the above issue, this paper proposes an new method for acronym disambiguation, named as ADBCMM, which can significantly improve the performance of low-resource languages by building counterfactuals and multilingual mixing.
When observing a visual scene that contains multiple objects from multiple viewpoints, humans are able to perceive the scene in a compositional way from each viewpoint, while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold.
However, these approaches formulated skin cancer diagnosis as a simple classification task, dismissing the potential benefit from lesion segmentation.
The mutually-exciting Hawkes process (ME-HP) is a natural choice to model reciprocity, which is an important attribute of continuous-time edge (dyadic) data.
In this paper, we propose a Simple framework for Contrastive Learning of Acronym Disambiguation (SimCLAD) method to better understand the acronym meanings.
In this paper, we propose a Prompt-based Sequence Generation (PSG) method for the acronym extraction task.
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
The most common solution for this is to compute an approximate risk by replacing the 0-1 loss with a surrogate one.
Then, ML-MMDR, a difference reduction method that adds multi-level MMD regularization into the loss, is proposed, and its effectiveness is testified on three typical difference-based defense methods.
To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.
Follow-the-Regularized-Lead (FTRL) and Online Mirror Descent (OMD) are regret minimization algorithms for Online Convex Optimization (OCO), they are mathematically elegant but less practical in solving Extensive-Form Games (EFGs).
Then, we develop a dense visual reconstruction algorithm to represent the scene by surfels, estimate the laparoscope poses and fuse the depth maps into a unified reference coordinate for tissue reconstruction.
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.
Deep learning-based video compression is a challenging task and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error.
Ten learning-based surgical tasks are built in the platform, which are common in the real autonomous surgical execution.
Our proposed network contains two stages: the first one is a lung region segmentation step and is used to exclude irrelevant factors, and the second is a detection and recommendation stage.
Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects.
Pixel-wise classification is a popular approach to segmenting the region of interest.
In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations.
In this paper, we propose a self-adversarial training strategy and a reliable coarse-to-fine network that utilizes a self-attention mechanism to localize forged regions in forgery images.
Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters.
Image super-resolution, which is often regarded as a preprocessing procedure of scene text recognition, aims to recover the realistic features from a low-resolution text image.
To address the issue, in this paper we extend an existing automatic cost learning scheme to JPEG, where the proposed scheme called JEC-RL (JPEG Embedding Cost with Reinforcement Learning) is explicitly designed to tailor the JPEG DCT structure.
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics.
Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks.
Ranked #1 on SMAC+ on Off_Superhard_parallel
Heart beat rhythm and heart rate (HR) are important physiological parameters of the human body.
Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution.
In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables.
The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation.
More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map.
Ranked #3 on Depth Completion on KITTI Depth Completion
Accurate hand joints detection from images is a fundamental topic which is essential for many applications in computer vision and human computer interaction.
Thus, the overall computational complexity of our algorithm is similar to that of the linear UCB for unconstrained stochastic linear bandits.
In this paper, we present a novel steganography scheme denoted as ITE-SYN (based on ITEratively adversarial perturbations onto a SYNchronized-directions sub-image), by which security data is embedded with synchronizing modification directions to enhance security and then iteratively increased perturbations are added onto a sub-image to reduce loss with cover class label of the target CNN classifier.
Here, UCB estimates balance the tradeoff between exploration and exploitation in learning and are critical for yielding a small cumulative regret.
DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex.
Astrophysics of Galaxies
Auto-bidding plays an important role in online advertising and has become a crucial tool for advertisers and advertising platforms to meet their performance objectives and optimize the efficiency of ad delivery.
Computer Science and Game Theory
Experimental results show that Neural ReCFR-B is competitive with the state-of-the-art neural CFR algorithms at a much lower training cost.
The method is based on a Convolutional Neural Network (CNN) that is trained to solve the estimation as a standard regression problem.
We propose a MIL-based method for WSI classification and tumor detection that does not require localized annotations.
The sFFT algorithms decrease the runtime and sampling complexity by taking advantage of the signal inherent characteristics that a large number of signals are sparse in the frequency domain(e. g., sensors, video data, audio, medical image, etc.).
In the second part, we make two categories of experiments for computing the signals of different SNR, different N, different K by a standard testing platform and record the run time, percentage of the signal sampled and L0, L1, L2 error both in the exactly sparse case and general sparse case.
Extending a similar setup from the previous year, five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the English training and evaluation data for the task, packaged in a uniform graph abstraction and serialization; for four of these representation frameworks, additional training and evaluation data was provided for one additional language per framework.
A modified three-dimensional Markov chain model adopting the quitting probability and cluster division is developed for the performance analysis.
Information Theory Information Theory
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance.
Ranked #63 on Object Detection on COCO test-dev
Quite a number of methods have been proposed to stabilize the training of GANs, the focuses of which were respectively put on the loss functions, regularization and normalization technologies, training algorithms, and model architectures.
Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies.
Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem.
In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution.
To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation.
Leveraging this, we propose for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption.
Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood.
The basic tasks of ancient Chinese information processing include automatic sentence segmentation, word segmentation, part-of-speech tagging and named entity recognition.
The existing lexicons blur senses and frames of predicates, which needs to be refined to meet the tasks like word sense disambiguation and event extraction.
Based on the Event-Stream dataset, we develop a deep neural network for grasping detection which consider the angle learning problem as classification instead of regression.
This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.
We initially propose the Integrated Smoothing Graphon (ISG) which introduces one smoothing parameter to the SBM graphon to generate continuous relational intensity values.
In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data.
At present, electric vehicles (EVs), small-scale wind power, and solar power have been increasingly integrated into modern power system via the combined cooling heating and power based microgrid (CCHP-MG).
Existing methods usually perform feature selection and outlier scoring separately, which would select feature subsets that may not optimally serve for outlier detection, leading to unsatisfying performance.
Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different values of the AoI across the servers (due to the random updating processes) and different response times across the servers, which can be exploited to minimize the expected AoI at the user's side.
no code implementations • 4 Dec 2019 • Joyce Fang, Martin Ellis, Bin Li, Siyao Liu, Yasaman Hosseinkashi, Michael Revow, Albert Sadovnikov, Ziyuan Liu, Peng Cheng, Sachin Ashok, David Zhao, Ross Cutler, Yan Lu, Johannes Gehrke
Bandwidth estimation and congestion control for real-time communications (i. e., audio and video conferencing) remains a difficult problem, despite many years of research.
In this work, we propose a probabilistic framework for relational data modelling and latent structure exploring.
Massive multiple-input multiple-output (MIMO) radar, enabled by millimeter-wave virtual MIMO techniques, provides great promises to the high-resolution automotive sensing and target detection in unmanned ground/aerial vehicles (UGA/UAV).
We propose a probabilistic framework for modelling and exploring the latent structure of relational data.
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
Ranked #1 on Visual Question Answering on VCR (Q-A) dev
With the representation effectiveness, skeleton-based human action recognition has received considerable research attention, and has a wide range of real applications.
Automatic medical image segmentation has wide applications for disease diagnosing.
Particularly, The QGMRN is composed of visual, textual and routing network.
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.
The Binary Space Partitioning~(BSP)-Tree process is proposed to produce flexible 2-D partition structures which are originally used as a Bayesian nonparametric prior for relational modelling.
Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components.
Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work.
If the channel is unknown, we cannot easily achieve traditional coherent channel estimation and cancellation, and the impact of ISI will be more severe.
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance.
In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).
Data Structures and Algorithms
The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer.
In this paper, we address the problem of detecting deep network generated (DNG) images by analyzing the disparities in color components between real scene images and DNG images.
An automatic classification method has been studied to effectively detect and recognize Electrocardiogram (ECG).
To tackle this problem, we develop a novel mechanism called customer sharing mechanism (CSM) which incentivizes all sellers to share each other's sale information to their private customer groups.
There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction.
This allows the system to achieve a smoother and more robust performance by optimizing in an alternate space.
We benchmark the astonishing accuracy of our method on three diverse and challenging problems in: biology, medicine, and engineering.
In this paper, we present a CNN solution by using raw DCT (discrete cosine transformation) coefficients from JPEG images as input.
Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different levels of information freshness and different response times across the servers, which can be exploited to minimize the expected AoI at the user's side.
Networking and Internet Architecture
The challenge to the seller is to design a mechanism to incentivize the buyers, who are aware of the auction, to further propagate the information to their neighbors so that more buyers will participate in the auction and hence, the seller will be able to make a higher revenue.
Computer Science and Game Theory
The k-fold cross-validation is commonly used to evaluate the effectiveness of SVMs with the selected hyper-parameters.