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.
We propose to train a model by maximizing its expressiveness while at the same time incorporating general priors such as model smoothness.
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.
Generating personalized responses is one of the major challenges in natural human-robot interaction.
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.
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.
In this paper, we demonstrate that the discriminator in GANs is sensitive to such high-frequency differences that can not be distinguished by humans and the high-frequency components of images are not conducive to the training of GANs.
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 #2 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
In this paper, a new CFR variant, Recursive CFR, is proposed, in which the cumulative regrets are recovered by Recursive Substitute Values (RSVs) that are recursively defined and independently calculated between iterations.
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 #36 on Object Detection on COCO test-dev (using extra training data)
With this discovery, we propose a Direct Adversarial Training (DAT) method for the training process of GANs to improve its performance.
In this work, we conduct a comprehensive survey on the regularization and normalization techniques from different perspectives of GANs training.
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, assisted by millimeter-wave band 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.
Online portfolio selection has been attracting increasing interests from artificial intelligence community in recent decades.
This article aims to provide a timely and comprehensive survey for both machine learning and data mining researchers in academia and quantitative portfolio managers in the financial industry to help them understand the state-of-the-art and facilitate their research and practical applications.
In this letter, we propose an adaptive SC (Successive Cancellation)-List decoder for polar codes with CRC.
Information Theory Information Theory
Machine learning techniques have been adopted to select portfolios from financial markets in some emerging intelligent business applications.