last week in computer science

402

new preprints about computer science in the last week

arXiv

most active server in computer science in the last week

state of the art

48 preprints

State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG

In this paper we first demonstrate continuous noisy speech recognition using electroencephalography (EEG) signals on English vocabulary using different types of state of the art end-to-end automatic speech recognition (ASR) models, we further provide results obtained using EEG data...
5 days ago
arXiv

The Next 700 Policy Miners: A Universal Method for Building Policy Miners

In the case of ABAC, it even outperforms the state of the art.
3 days ago
arXiv

One-proton and one-neutron knockout reactions from $N = Z = 28$ $^{56}$Ni to the $A = 55$ mirror pair $^{55}$Co and $^{55}$Ni

We present a high-resolution in-beam $\gamma$-ray spectroscopy study of excited states in the mirror nuclei $^{55}$Co and $^{55}$Ni following one-nucleon knockout from a projectile beam of $^{56}$Ni.
3 days ago
arXiv

machine learning

16 preprints

Efficient prediction of vitamin B deficiencies via machine-learning using routine blood test results in patients with intense psychiatric episode

Discussion: This study demonstrates that machine-learning can efficiently predict some vitamin deficiencies in patients with active psychiatric symptoms, based on the largest cohort to date with intense psychiatric episode.
6 days ago
medRxiv

Deep Learning and Machine Learning in Hydrological Processes, Climate Change and Earth Systems: A Systematic Review

On the other hand, machine learning methods are already established in the fields, and novel methods with higher performance are emerging through ensemble techniques and hybridization.
5 days ago
Preprints.org

Constrained Multi-Objective Optimization for Automated Machine Learning

Incorporation of multiple objectives and constraints in the model exploration and selection process provides the flexibility needed to satisfy trade-offs necessary in practical machine learning applications.
6 days ago
arXiv

deep learning

15 preprints

Deep Learning and Machine Learning in Hydrological Processes, Climate Change and Earth Systems: A Systematic Review

The paper concludes that deep learning is still in the first stages of development, and the research is still progressing.
5 days ago
Preprints.org

SHIFT: speedy histological-to-immunofluorescent translation of whole slide images enabled by deep learning

We show that deep learning-extracted feature representations of histological images can guide representative sample selection, which improves SHIFT generalizability.
4 days ago
bioRxiv

Deep learning brain conductivity mapping using a patch-based 3D U-net

Results: High quality of reconstructions from networks trained on simulations with and without noise confirms the potential of deep learning for EPT.
7 days ago
arXiv

neural networks

13 preprints

Muon Identification Using Deep Neural Networks with the Muon Telescope Detector at STAR

The installation of the muon telescope detector opened new possibilities for studying dimuon production at STAR.
4 days ago
arXiv

Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy

We propose a novel domain specific loss, which is a differentiable loss function based on the dose volume histogram, and combine it with an adversarial loss for the training of deep neural networks to generate Pareto optimal dose distributions.
3 days ago
arXiv

Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on resource-limited devices like mobile phones.
5 days ago
arXiv

reinforcement learning

11 preprints

Playing a Strategy Game with Knowledge-Based Reinforcement Learning

Overall, the reported experiment supports the idea that, based on human knowledge and empowered by reinforcement learning, the KB-RL system can deliver a strong solution to the complex, multi-strategic problems, and, mainly, to improve the solution with increased experience.
4 days ago
arXiv

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective

We also describe a number of tweaks to the reinforcement learning objective that prevent incentives for reward tampering.
6 days ago
arXiv

Model-based Lookahead Reinforcement Learning

However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods.
4 days ago
arXiv

paper presents

8 preprints

A Simple and Intuitive Algorithm for Preventing Directory Traversal Attacks

This paper presents an analysis of some currently used directory traversal attack defenses and presents a new, stack-based algorithm to help prevent these attacks by safely canonicalizing user-supplied path strings.
6 days ago
arXiv

An empirical study linking additive manufacturing design process to success in manufacturability

This paper presents empirical data from the design processes of six graduate student engineering designers as they re-design a traditionally designed part for additive manufacturing.
6 days ago
engrXiv

Envelope polyhedra

This paper presents an additional class of regular polyhedra--envelope polyhedra--made of regular polygons, where the arrangement of polygons (creating a single surface) around each vertex is identical; but dihedral angles between faces need not be identical, and some of the dihedral angles are 0 degrees (i.e., some...
5 days ago
arXiv

art performance

8 preprints

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background.
6 days ago
arXiv

Is Deep Reinforcement Learning Really Superhuman on Atari?

Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art performance.
6 days ago
arXiv

FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks

State-of-the-art performance is dominated by two-stages top-down methods.
4 days ago
arXiv

decision making

8 preprints

History biases reveal novel dissociations between perceptual and metacognitive decision-making

We propose that recent choices and subjective confidence represent heuristics which inform 1st and 2nd order decisions in the absence of more relevant evidence.
1 hours ago
bioRxiv

Properties of decision-making tasks govern the tradeoff between model-based and model-free learning

We studied model-free and model-based learning using serial decision-making tasks in which subjects selected a rule and then used it to flexibly act on visual stimuli.
5 days ago
bioRxiv

Decision making in dynamic and interactive environments based on cognitive hierarchy theory: Formulation, solution, and application to autonomous driving

In this paper, we describe a framework for autonomous decision making in a dynamic and interactive environment based on cognitive hierarchy theory.
7 days ago
arXiv

question answering

8 preprints

Reasoning-Driven Question-Answering for Natural Language Understanding

This primary goal has been studied under different tasks, such as Question Answering (QA) and Textual Entailment (TE).
6 days ago
arXiv

VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering

The goal of this dataset is to assess question-answering performance from nearly-ideal navigation paths, while considering a much more complete variety of questions than current instantiations of the EQA task.
5 days ago
arXiv

AmazonQA: A Review-Based Question Answering Task

Observing that many questions can be answered based upon the available product reviews, we propose the task of review-based QA.
7 days ago
arXiv

object detection

7 preprints

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

In this paper, we address the semi-supervised video salient object detection task using pseudo-labels.
7 days ago
arXiv

Matrix Nets: A New Deep Architecture for Object Detection

We present Matrix Nets (xNets), a new deep architecture for object detection. xNets map objects with different sizes and aspect ratios into layers where the sizes and the aspect ratios of the objects within their layers are nearly uniform.
6 days ago
arXiv

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

Experiment results show that our methods can achieve close accuracy on object detection to state-of-the-art fully-supervised methods on two large scale datasets, ImageNet and OpenImages, with only a small fraction of fully annotated classes.
5 days ago
arXiv

new state

7 preprints

Is Deep Reinforcement Learning Really Superhuman on Atari?

Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art performance.
6 days ago
arXiv

Simplify the Usage of Lexicon in Chinese NER

As a representative work in this line, Lattice-LSTM \cite{zhang2018chinese} has achieved new state-of-the-art performance on several benchmark Chinese NER datasets.
3 days ago
arXiv

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

The proposed model is end-to-end trainable, and achieves new state-of-the-art scores and outperforms all previous methods by a great margin on the SQuAD benchmark.
6 days ago
arXiv

state of the art performance

7 preprints

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background.
6 days ago
arXiv

Is Deep Reinforcement Learning Really Superhuman on Atari?

Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art performance.
6 days ago
arXiv

FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks

State-of-the-art performance is dominated by two-stages top-down methods.
4 days ago
arXiv

real world applications

6 preprints

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation.
4 days ago
arXiv

FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks

Despite the leading results, these methods are impractical for real-world applications due to their separated architectures and complicated calculation.
4 days ago
arXiv

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Nonetheless, two main challenges still exist and hamper its deployment to real-world applications.
3 days ago
arXiv

natural language

6 preprints

Reasoning-Driven Question-Answering for Natural Language Understanding

In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning.
6 days ago
arXiv

Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review

Further efforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and...
4 days ago
arXiv

Temporal Collaborative Ranking Via Personalized Transformer

In particular, the SASRec model, inspired by the popular Transformer model in natural languages processing, has achieved state-of-art results in the temporal collaborative ranking problem and enjoyed more than 10x speed-up when compared to earlier CNN/RNN-based methods.
4 days ago
arXiv

multi task

5 preprints

Double-Coupling Learning for Multi-Task Data Stream Classification

Instead of handling them separately, it is beneficial to consider the correlations among the multi-task data streams for data stream modeling tasks.
5 days ago
arXiv

Variational Multi-Task MRI Reconstruction: Joint Reconstruction, Registration and Super-Resolution

Motion degradation is a central problem in Magnetic Resonance Imaging (MRI).
3 days ago
arXiv

Feature Partitioning for Efficient Multi-Task Architectures

We benchmark on Visual Decathlon, demonstrating that we can automatically search for and identify multi-task architectures that effectively make trade-offs between task resource requirements while achieving a high level of final performance.
7 days ago
arXiv

data structure

5 preprints

"LOADS of Space": Local Order Agnosticism and Bit Flip Efficient Data Structure Codes

We found that because these data structures have a limited set of valid values and transitions, that bit flipping wins should be possible without the use of additional hardware.
4 days ago
arXiv

stdgpu: Efficient STL-like Data Structures on the GPU

In this work, we present stdgpu, an open-source library which defines several generic GPU data structures for fast and reliable data management.
3 days ago
arXiv

Three-dimensional Density Structure of a Solar Coronal Streamer Observed by SOHO/LASCO and STEREO/COR2 in Quadrature

The streamer plasma sheet contains a number of brighter and darker ray-like structures with the density contrast up to about a factor 3 between them.
5 days ago
arXiv

language understanding

5 preprints

StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding

As a result, the new model is adapted to different levels of language understanding required by downstream tasks.
6 days ago
arXiv

Reasoning-Driven Question-Answering for Natural Language Understanding

Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research.
6 days ago
arXiv

VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering

The desired outcome is that the agent learns to combine capabilities such as scene understanding, navigation and language understanding in order to perform complex reasoning in the visual world.
5 days ago
arXiv

multi agent

4 preprints

Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking

In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to improve the competitive abilities for agents.
6 days ago
arXiv

Massive Multi-Agent Data-Driven Simulations of the GitHub Ecosystem

Two reasons for the success of these agents were their use of a distinct characterization of each agent, and that GitHub users change their behavior relatively slowly.
4 days ago
arXiv

Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real

In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach.
6 days ago
arXiv

fine grained

4 preprints

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

We achieve this by utilizing the correlations between coarse-grained and fine-grained classes with shared backbone, soft-attention based proposal re-ranking, and a dual-level memory module.
5 days ago
arXiv

Fine-grained Information Status Classification Using Discourse Context-Aware Self-Attention

On the ISNotes corpus (Markert et al., 2012), our model with the contextually-encoded word representations (BERT) (Devlin et al., 2018) achieves new state-of-the-art performances on fine-grained IS classification, obtaining a 4.1% absolute overall accuracy improvement compared to Hou et al. (2013a).
6 days ago
arXiv

Cross-Layer Scheduling and Beamforming in Smart Grid Powered Small-Cell Networks

As a result, a practical two-scale algorithm is proposed to allocate the user scheduling indicators and ScBS sleeping variables at the coarse-grained granularity (frame) as well as obtain the beamforming vectors at the fine-grained granularity (slot).
6 days ago
arXiv

semi supervised

4 preprints

Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

On several standard benchmarks - PASCAL VOC 2012, PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.
4 days ago
arXiv

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

Experimental results demonstrate that our proposed semi-supervised method even greatly outperforms all the state-of-the-art fully supervised methods across three public benchmarks of VOS, DAVIS, and FBMS.
7 days ago
arXiv

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

To deal with this issue, we propose a novel Progressive Cross-camera Soft-label Learning (PCSL) framework for the semi-supervised person Re-ID task, which can generate cross-camera soft-labels and utilize them to optimize the network.
5 days ago
arXiv

social networks

4 preprints

How often should I access my online social networks?

The retention of users on online social networks has important implications, encompassing economic, psychological and infrastructure aspects.
6 days ago
arXiv

Extended hormone-phenotypes shape the structure, stability, and assortment of social networks

We found that the manakin social networks with high-testosterone dominant individuals were less specialized, less stable, and had more negative behavioral assortment.
3 days ago
bioRxiv

Homophily on social networks changes evolutionary advantage in competitive information diffusion

Using microscopic Markov chain approach, we first derive the phase diagram of competing diffusion results and examine how competitive information spreads and evolves on social networks.
3 days ago
arXiv

multi view

3 preprints

Multi-View Fuzzy Clustering with The Alternative Learning between Shared Hidden Space and Partition

The experimental result shows that the proposed multi-view clustering method has better performance than many related clustering methods.
7 days ago
arXiv

Multi-view Clustering with the Cooperation of Visible and Hidden Views

The results of extensive experiments on UCI multi-view datasets and real-world image multi-view datasets show that the clustering performance of the proposed algorithm is competitive with or even better than that of the existing algorithms.
7 days ago
arXiv

3D Human Pose Estimation under limited supervision using Metric Learning

Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.
5 days ago
arXiv

in the wild

3 preprints

Modeling Personality vs. Modeling Personalidad: In-the-wild Mobile Data Analysis in Five Countries Suggests Cultural Impact on Personality Models

We unpack differences in personality models across the five countries, highlight the most predictive data categories (location, noise, unlocks, accelerometer), and provide takeaways to technologists and social scientists interested in passive personality assessment.
6 days ago
arXiv

3D Human Pose Estimation under limited supervision using Metric Learning

Estimating 3D human pose from monocular images demands large amounts of 3D pose and in-the-wild 2D pose annotated datasets which are costly and require sophisticated systems to acquire.
5 days ago
arXiv

Predicting 3D Human Dynamics from Video

Our approach can be trained on video sequences obtained in-the-wild without 3D ground truth labels.
6 days ago
arXiv

recommender systems

3 preprints

FCNHSMRA_HRS: Improve the performance of the movie hybrid recommender system using resource allocation approach

Collaborative filtering offering active user suggestions based on the rating of a set of users is one of the simplest and most comprehensible and successful models for finding people in the same tastes in the recommender systems.
6 days ago
arXiv

On Gossip-based Information Dissemination in Pervasive Recommender Systems

In order to address both, we propose Propagate and Filter, a method that translates the traditional approach of finding similar peers and exchanging item preferences among each other from the field of decentralized to that of pervasive recommender systems.
4 days ago
arXiv

Evaluation of a Recommender System for Assisting Novice Game Designers

We conducted quantitative studies that showed the recommender system increases users' levels of accuracy and computational affect, and decreases their levels of workload.
6 days ago
arXiv

machine to machine

2 preprints

Estimating & Mitigating the Impact of Acoustic Environments on Machine-to-Machine Signalling

The performance of the final algorithm is evaluated on quality metrics as well as the performance of a real machine-to-machine decoder.
6 days ago
arXiv

Network Lifetime Maximization in Wireless Mesh Networks for Machine-to-Machine Communication

In this paper we present new optimization formulations for maximizing the network lifetime in wireless mesh networks performing data aggregation and dissemination for machine-to-machine communication in the Internet of Things.
5 days ago
arXiv