Search Results for author:
Found 338 papers, 109 papers with code
Sparks of Artificial General Intelligence: Early experiments with GPT-4
We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models.
Ranked #32 on
Arithmetic Reasoning
on GSM8K
PSANet: Point-wise Spatial Attention Network for Scene Parsing
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #51 on
Semantic Segmentation
on Cityscapes test
PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
Through this method, we generate synthetic data using a large amount of unlabeled data in the target domain and then obtain a word segmentation model for the target domain.
DELTA: A DEep learning based Language Technology plAtform
In this paper we present DELTA, a deep learning based language technology platform.
Ranked #3 on
Text Classification
on Yahoo! Answers
RESA: Recurrent Feature-Shift Aggregator for Lane Detection
Lane detection is one of the most important tasks in self-driving.
Ranked #4 on
Lane Detection
on TuSimple
Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
Given the potential X-ray radiation risk to the patient, low-dose CT has attracted a considerable interest in the medical imaging field.
KBNet: Kernel Basis Network for Image Restoration
In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggregation.
Ranked #1 on
Color Image Denoising
on McMaster sigma50
What Makes Convolutional Models Great on Long Sequence Modeling?
We focus on the structure of the convolution kernel and identify two critical but intuitive principles enjoyed by S4 that are sufficient to make up an effective global convolutional model: 1) The parameterization of the convolutional kernel needs to be efficient in the sense that the number of parameters should scale sub-linearly with sequence length.
Ranked #6 on
Long-range modeling
on LRA
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
FoodSAM: Any Food Segmentation
Remarkably, this pioneering framework stands as the first-ever work to achieve instance, panoptic, and promptable segmentation on food images.
Ranked #1 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method
Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldom updated, which will reduce the computational cost both in the training and decoding, and potentially accelerate decoding in real-world applications.
IDR: Self-Supervised Image Denoising via Iterative Data Refinement
To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes.
Rethinking Noise Synthesis and Modeling in Raw Denoising
However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors.
Ranked #2 on
Image Denoising
on SID SonyA7S2 x100
Convolutional neural networks with low-rank regularization
Recently, tensor decompositions have been used for speeding up CNNs.
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
In this study, we propose a simple yet effective framework for video restoration.
Ranked #1 on
Deblurring
on GoPro
(using extra training data)
Context-aware Cross-level Fusion Network for Camouflaged Object Detection
Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings.
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
Compared to the state-of-the-art models, our skeleton-based model can generate significantly more coherent text according to human evaluation and automatic evaluation.
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of semantic segmentation, such as autonomous driving and medical image analysis.
Ranked #8 on
Anomaly Detection
on Road Anomaly
(using extra training data)
Learning Sentiment Memories for Sentiment Modification without Parallel Data
The task of sentiment modification requires reversing the sentiment of the input and preserving the sentiment-independent content.
Learning Degradation Representations for Image Deblurring
With the integration, MSDI-Net can handle various and complicated blurry patterns adaptively.
Ranked #13 on
Image Deblurring
on GoPro
Frequency-Modulated Point Cloud Rendering with Easy Editing
We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing.
Point, Segment and Count: A Generalized Framework for Object Counting
In this paper, we propose a generalized framework for both few-shot and zero-shot object counting based on detection.
Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation
In this work, we propose PolarBEV for vision-based uneven BEV representation learning.
DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
To better regularize the LDCT denoising model, this paper proposes a novel method, termed DU-GAN, which leverages U-Net based discriminators in the GANs framework to learn both global and local difference between the denoised and normal-dose images in both image and gradient domains.
Tailor Versatile Multi-modal Learning for Multi-label Emotion Recognition
Previous methods mainly focus on projecting multiple modalities into a common latent space and learning an identical representation for all labels, which neglects the diversity of each modality and fails to capture richer semantic information for each label from different perspectives.
RGB-D Salient Object Detection via 3D Convolutional Neural Networks
The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams.
Clinical Prompt Learning with Frozen Language Models
Prompt learning is a new paradigm in the Natural Language Processing (NLP) field which has shown impressive performance on a number of natural language tasks with common benchmarking text datasets in full, few-shot, and zero-shot train-evaluation setups.
Collaboration-Aware Graph Convolutional Network for Recommender Systems
Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect.
Vehicle Re-Identification Based on Complementary Features
Top performance in City-Scale Multi-Camera Vehicle Re-Identification demonstrated the advantage of our methods, and we got 5-th place in the vehicle Re-ID track of AIC2020.
Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11
With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states.
NatCS: Eliciting Natural Customer Support Dialogues
Existing task-oriented dialogue datasets, which were collected to benchmark dialogue systems mainly in written human-to-bot settings, are not representative of real customer support conversations and do not provide realistic benchmarks for systems that are applied to natural data.
HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention
Elucidating and accurately predicting the druggability and bioactivities of molecules plays a pivotal role in drug design and discovery and remains an open challenge.
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification
Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization.
Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R$^2$T is tailored to re-embed instance features online.
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
Motivated by the recent success of generative models in rigid object pose estimation, we propose 3D-aware Neural Body Fitting (3DNBF) - an approximate analysis-by-synthesis approach to 3D human pose estimation with SOTA performance and occlusion robustness.
Conversational Recommender System
A personalized conversational sales agent could have much commercial potential.
NeRF applied to satellite imagery for surface reconstruction
S-NeRF improves on the standard Neural Radiance Field (NeRF) method by considering the radiance as a function of the albedo and the irradiance.
Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems
Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data.
Topological Quantum Compiling with Reinforcement Learning
Quantum compiling, a process that decomposes the quantum algorithm into a series of hardware-compatible commands or elementary gates, is of fundamental importance for quantum computing.
ICNet: Intra-saliency Correlation Network for Co-Saliency Detection
Intra-saliency and inter-saliency cues have been extensively studied for co-saliency detection (Co-SOD).
Boosting Point Clouds Rendering via Radiance Mapping
In this work, we focus on boosting the image quality of point clouds rendering with a compact model design.
A Chinese Dataset with Negative Full Forms for General Abbreviation Prediction
However, due to the deficiency in the abbreviation corpora, such a task is limited in current studies, especially considering general abbreviation prediction should also include those full form expressions that do not have valid abbreviations, namely the negative full forms (NFFs).
Salient Object Ranking with Position-Preserved Attention
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving
The deployment of autonomous vehicles (AVs) has faced hurdles due to the dominance of rare but critical corner cases within the long-tail distribution of driving scenarios, which negatively affects their overall performance.
Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network
Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis.
CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization
First, CoreDiff utilizes LDCT images to displace the random Gaussian noise and employs a novel mean-preserving degradation operator to mimic the physical process of CT degradation, significantly reducing sampling steps thanks to the informative LDCT images as the starting point of the sampling process.
Facial Prior Based First Order Motion Model for Micro-expression Generation
To solve this problem, this paper tries to formulate a new task called micro-expression generation and then presents a strong baseline which combines the first order motion model with facial prior knowledge.
Comprehensive Competition Mechanism in Palmprint Recognition
The traditional competition mechanism focuses solely on selecting the winner of different channels without considering the spatial information of the features.
Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative Model
Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications.
A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications
Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.
Label Semantic Aware Pre-training for Few-shot Text Classification
Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction.
Unveiling Transformers with LEGO: a synthetic reasoning task
We study how the trained models eventually succeed at the task, and in particular, we manage to understand some of the attention heads as well as how the information flows in the network.
Vicinity Vision Transformer
Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity.
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
We show that training of generative adversarial network (GAN) may not have good generalization properties; e. g., training may appear successful but the trained distribution may be far from target distribution in standard metrics.
Depth Completion using Geometry-Aware Embedding
The ablation study gives more insights into our method that could achieve significant gains with a simple design, while having better generalization capability and stability.
DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT.
Learning Synergistic Attention for Light Field Salient Object Detection
We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms.
CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection
In the past few years, numerous deep learning methods have been proposed to address the task of segmenting salient objects from RGB images.
ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
In this paper, we propose a novel Anatomy-aware Supervised CONtrastive learning framework, termed ASCON, which can explore the anatomical semantics for low-dose CT denoising while providing anatomical interpretability.
Towards Easier and Faster Sequence Labeling for Natural Language Processing: A Search-based Probabilistic Online Learning Framework (SAPO)
We show that this method with fast training and theoretical guarantee of convergence, which is easy to implement, can support search-based optimization and obtain top accuracy.
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.
(Re)$^2$H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning
Autonomous driving and its widespread adoption have long held tremendous promise.
Parallel Data Augmentation for Formality Style Transfer
The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data.
Homogeneous Online Transfer Learning with Online Distribution Discrepancy Minimization
In this paper, we propose a novel online transfer learning method which seeks to find a new feature representation, so that the marginal distribution and conditional distribution discrepancy can be online reduced simultaneously.
FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
Specifically, we first propose a frequency-band-aware artifact modeling network (FreeNet), which learns artifact-related frequency-band attention in Fourier domain for better modeling the globally distributed streak artifact on the sparse-view CT images.
Personalized Re-ranking for Recommendation
Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users.
Learning to Decompose and Organize Complex Tasks
Both components of our graph induction solution are evaluated in experiments, demonstrating that our models outperform a state-of-the-art text generator significantly.
Semi-Supervised Learning with Multi-Head Co-Training
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning.
Aerial Vision-and-Dialog Navigation
To this end, we introduce Aerial Vision-and-Dialog Navigation (AVDN), to navigate a drone via natural language conversation.
From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping
Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities.
Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
In our work, we first design a new model called "high order LSTM" to predict multiple tags for the current token which contains not only the current tag but also the previous several tags.
AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion.
The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation
Existing methods suffer from the trade-off between the quality and diversity of generated images.
Dialogue Meaning Representation for Task-Oriented Dialogue Systems
We propose Dialogue Meaning Representation (DMR), a pliable and easily extendable representation for task-oriented dialogue.
Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Intent classification (IC) plays an important role in task-oriented dialogue systems.
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models
We first take into consideration all the linguistic information embedded in the past layers and then take a further step to engage the future information which is originally inaccessible for predictions.
SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
In order to address the challenge that the transferabilities of different sensors are different, we propose SALIENCE (unsupervised user adaptation model for multiple wearable sensors based human activity recognition) model.
Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging
The basic assumption of HyperFed is that the optimization problem for each institution can be divided into two parts: the local data adaption problem and the global CT imaging problem, which are implemented by an institution-specific hypernetwork and a global-sharing imaging network, respectively.
Robust Split Federated Learning for U-shaped Medical Image Networks
To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL.
SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data
This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023).
A Fixation-based 360° Benchmark Dataset for Salient Object Detection
Experimental results show a limitation of the current methods when used for SOD in panoramic images, which indicates the proposed dataset is challenging.
LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT
Compressed sensing (CS) computed tomography has been proven to be important for several clinical applications, such as sparse-view computed tomography (CT), digital tomosynthesis and interior tomography.
Unsupervised Camouflaged Object Segmentation as Domain Adaptation
To this end, we formulate the UCOS as a source-free unsupervised domain adaptation task (UCOS-DA), where both source labels and target labels are absent during the whole model training process.
CETN: Contrast-enhanced Through Network for CTR Prediction
Click-through rate (CTR) Prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search.
Ranked #4 on
Click-Through Rate Prediction
on Avazu
A microstructure estimation Transformer inspired by sparse representation for diffusion MRI
Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage.
Deep Image Semantic Communication Model for Artificial Intelligent Internet of Things
Particularly, at the transmitter side, a high-precision image semantic segmentation algorithm is proposed to extract the semantic information of the image to achieve significant compression of the image data.
Large Scale Product Graph Construction for Recommendation in E-commerce
Building a recommendation system that serves billions of users on daily basis is a challenging problem, as the system needs to make astronomical number of predictions per second based on real-time user behaviors with O(1) time complexity.
Modeling Fuzzy Cluster Transitions for Topic Tracing
Twitter can be viewed as a data source for Natural Language Processing (NLP) tasks.
Tracing Topic Transitions with Temporal Graph Clusters
Twitter serves as a data source for many Natural Language Processing (NLP) tasks.
SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
Salient human detection (SHD) in dynamic 360{\deg} immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality.
Prompted Contextual Transformer for Incomplete-View CT Reconstruction
To enjoy the multi-setting synergy in a single model, we propose a novel Prompted Contextual Transformer (ProCT) for incomplete-view CT reconstruction.
Not-So-Random Features
We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels.
Multiscale Sparsifying Transform Learning for Image Denoising
The data-driven sparse methods such as synthesis dictionary learning (e. g., K-SVD) and sparsifying transform learning have been proven effective in image denoising.
DFEE: Interactive DataFlow Execution and Evaluation Kit
DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks.
Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks
The nature of no word delimiter or inflection that can indicate segment boundaries or word semantics increases the difficulty of Chinese text understanding, and also intensifies the demand for word-level semantic knowledge to accomplish the tagging goal in Chinese segmenting and labeling tasks.
Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification
Subsequently, we introduce anchor models for short- and long-spectrum, which constrain the optimization directions of local models associated with long- and short-spectrum images.
UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media
As social media becomes increasingly popular, more and more activities related to public health emerge.
Balanced and Explainable Social Media Analysis for Public Health with Large Language Models
Furthermore, an LLMs explanation mechanism is proposed by prompting an LLM with the predicted results from BERT models.
Learning Shape Primitives via Implicit Convexity Regularization
In this work, a novel regularization term named Implicit Convexity Regularization (ICR) imposed on implicit primitive learning is proposed to tackle this problem.
ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation
Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions.
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets.
Localized Simple Multiple Kernel K-Means
After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix.
Design Challenges for a Multi-Perspective Search Engine
Naturally, identifying such responses within a document is a natural language understanding task.
Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models
Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks.
Efficient Full-Matrix Adaptive Regularization
Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive.
STS Classification with Dual-stream CNN
Inspired by the dual-stream hypothesis in neural science, we propose a novel dual-stream framework for modeling the interweaved spatiotemporal dependency, and develop a convolutional neural network within this framework that aims to achieve high adaptability and flexibility in STS configurations from various diagonals, i. e., sequential order, dependency range and features.
Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
Especially, the proposed approach improves the semantic consistency by 4\% in terms of human evaluation.
N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
Plantar pressure is one of which contains this information and it describes human walking features.
Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising
However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality.
3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
Based on the transfer learning from 2D to 3D, the 3D network converges faster and achieves a better denoising performance than that trained from scratch.
SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
But, this raises an important problem in active vision: given an {\bf infinite} data space, how to effectively sample a {\bf finite} subset to train a visual classifier?
Stronger generalization bounds for deep nets via a compression approach
Analysis of correctness of our compression relies upon some newly identified \textquotedblleft noise stability\textquotedblright properties of trained deep nets, which are also experimentally verified.
Spectral Filtering for General Linear Dynamical Systems
We give a polynomial-time algorithm for learning latent-state linear dynamical systems without system identification, and without assumptions on the spectral radius of the system's transition matrix.
LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT
Compressive sensing (CS) has proved effective for tomographic reconstruction from sparsely collected data or under-sampled measurements, which are practically important for few-view CT, tomosynthesis, interior tomography, and so on.
ICFVR 2017: 3rd International Competition on Finger Vein Recognition
The development of finger vein recognition algorithms heavily depends on large-scale real-world data sets.
Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor
A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed.
Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
The decoding of the complex structure model is regularized by the additionally trained simple structure model.
Theoretical limitations of Encoder-Decoder GAN architectures
Encoder-decoder GANs architectures (e. g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings.
Identifying Restaurant Features via Sentiment Analysis on Yelp Reviews
The main approach used in this paper is to use a support vector machine (SVM) model to decipher the sentiment tendency of each review from word frequency.
Do GANs actually learn the distribution? An empirical study
Do GANS (Generative Adversarial Nets) actually learn the target distribution?
Towards Understanding the Invertibility of Convolutional Neural Networks
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible.
Spectrum Monitoring for Radar Bands using Deep Convolutional Neural Networks
The core of our framework is a deep convolutional neural network (CNN) model that enables Measurement Capable Devices to identify the presence of radar signals in the radio spectrum, even when these signals are overlapped with other sources of interference, such as commercial LTE and WLAN.
Deep Embedding Forest: Forest-based Serving with Deep Embedding Features
Built on top of a representative DNN model called Deep Crossing, and two forest/tree-based models including XGBoost and LightGBM, a two-step Deep Embedding Forest algorithm is demonstrated to achieve on-par or slightly better performance as compared with the DNN counterpart, with only a fraction of serving time on conventional hardware.
Effective face landmark localization via single deep network
In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data.
A Fusion Method Based on Decision Reliability Ratio for Finger Vein Verification
Our work is first to define decision reliability ratio to quantify this confidence, and then propose the Maximum Decision Reliability Ratio (MDRR) fusion method incorporating Weighted Voting.
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision
We generate a large synthetic image dataset with automatically computed hazardous regions and analyze algorithms on these regions.
Prediction of Manipulation Actions
In psychophysical experiments, we evaluated human observers' skills in predicting actions from video sequences of different length, depicting the hand movement in the preparation and execution of actions before and after contact with the object.
Low-dose CT denoising with convolutional neural network
To reduce the potential radiation risk, low-dose CT has attracted much attention.
Conversational Recommendation System with Unsupervised Learning
We will explore and demonstrate the effectiveness of the learning solution even when there is no hand written rules or hand labeled training data.
Low-Dose CT via Deep Neural Network
In order to reduce the potential radiation risk, low-dose CT has attracted more and more attention.
Medical Physics
CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs.
A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification
However, the Seq2Seq model is not suitable for the MLTC task in essence.
On Reinforcement Learning for Full-length Game of StarCraft
The reinforcement training algorithm for this architecture is also investigated.
Hierarchical Reinforcement Learning
reinforcement-learning
+4
Sparse-View CT Reconstruction via Convolutional Sparse Coding
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features.
Visual Attention Network for Low Dose CT
Noise and artifacts are intrinsic to low dose CT (LDCT) data acquisition, and will significantly affect the imaging performance.
Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound
We compare the performance of the suggested deep network on both simulations and in-vivo rat brain scans, with a commonly practiced deep-network architecture and the fast iterative shrinkage algorithm, and show that our architecture exhibits better image quality and contrast.
Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks
In recent years, there has been a growing interest in applying convolutional neural networks (CNNs) to low-level vision tasks such as denoising and super-resolution.
Low-Dose CT via Deep CNN with Skip Connection and Network in Network
The use of deep convolutional (Conv) neural networks for noise reduction in Low-Dose CT (LDCT) images has recently shown a great potential in this important application.
TechKG: A Large-Scale Chinese Technology-Oriented Knowledge Graph
In this work, we introduce TechKG, a large scale Chinese knowledge graph that is technology-oriented.
Scalable Wide and Deep Learning for Computer Assisted Coding
In recent years the use of electronic medical records has accelerated resulting in large volumes of medical data when a patient visits a healthcare facility.
Deep Visual Analogy-Making
In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding.
Learning Multiple Tasks with a Sparse Matrix-Normal Penalty
In this paper, we propose a matrix-variate normal penalty with sparse inverse covariances to couple multiple tasks.
Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text
In an empirical study, we construct 190 different text classification tasks from a real-world benchmark, and the unlabeled documents are a mixture from all these tasks.
Do GANs learn the distribution? Some Theory and Empirics
Using this evidence is presented that well-known GANs approaches do learn distributions of fairly low support.
Towards Provable Control for Unknown Linear Dynamical Systems
We study the control of symmetric linear dynamical systems with unknown dynamics and a hidden state.
Blur Processing Using Double Discrete Wavelet Transform
We propose a notion of double discrete wavelet transform (DDWT) that is designed to sparsify the blurred image and the blur kernel simultaneously.
Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration
Fisheye image rectification and estimation of intrinsic parameters for real scenes have been addressed in the literature by using line information on the distorted images.
Information Extraction from German Patient Records via Hybrid Parsing and Relation Extraction Strategies
In this paper, we report on first attempts and findings to analyzing German patient records, using a hybrid parsing architecture and a combination of two relation extraction strategies.
Joint Grammar and Treebank Development for Mandarin Chinese with HPSG
We present the ongoing development of MCG, a linguistically deep and precise grammar for Mandarin Chinese together with its accompanying treebank, both based on the linguistic framework of HPSG, and using MRS as the semantic representation.
CLIMB grammars: three projects using metagrammar engineering
This paper introduces the CLIMB (Comparative Libraries of Implementations with Matrix Basis) methodology and grammars.
Extreme Tensoring for Low-Memory Preconditioning
State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption.
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems.
Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies
In Part I of this study, a general methodology for TSLG is proposed, and theoretical properties are investigated regarding the accuracy and efficiency of CAV evaluation.
Calibration, Entropy Rates, and Memory in Language Models
Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing.
Non-destructive three-dimensional measurement of hand vein based on self-supervised network
At present, supervised stereo methods based on deep neural network have achieved impressive results.
Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment
We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments.
Evidence-based Trustworthiness
This paper develops a general framework for estimating the trustworthiness of information sources in an environment where multiple sources provide claims and supporting evidence, and each claim can potentially be produced by multiple sources.
Many could be better than all: A novel instance-oriented algorithm for Multi-modal Multi-label problem
The quality of data collected from different channels are inconsistent and some of them may not benefit for prediction.
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.
Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting
We study sequence-to-sequence (seq2seq) pre-training with data augmentation for sentence rewriting.
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
Hierarchical neural networks are often used to model inherent structures within dialogues.
Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring
This paper describes the system submission of our team Amazon to the shared task on Cross Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).
Multi-Domain Goal-Oriented Dialogues (MultiDoGO): Strategies toward Curating and Annotating Large Scale Dialogue Data
With a total of over 81K dialogues harvested across six domains, MultiDoGO is over 8 times the size of MultiWOZ, the other largest comparable dialogue dataset currently available to the public.
RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
In this paper, we propose the Randomized Simulation as Augmentation (RSA) framework which augments real-world training data with synthetic data to improve the robustness of action recognition networks.
DASZL: Dynamic Action Signatures for Zero-shot Learning
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large.
Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
This can explain why an activity classification model usually fails to generalize to datasets it is not trained on.
Objects detection for remote sensing images based on polar coordinates
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via uses simpler object representation model and less regression parameters.
Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition
Subsequently, in temporal analysis, we use TCNs to extract temporal features and employ improved Squeeze-and-Excitation Networks (SENets) to strengthen the representational power of temporal features from each TCNs' layers.
Optimizing seed inputs in fuzzing with machine learning
Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.
Cryptography and Security
No-Regret Prediction in Marginally Stable Systems
This requires a refined regret analysis, including a structural lemma showing the current state of the system to be a small linear combination of past states, even if the state grows polynomially.
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.
Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition
To facilitate end-to-end training, we further develop a scenario context information extraction branch to extract context information from raw RGB video directly.
Ranked #83 on
Skeleton Based Action Recognition
on NTU RGB+D
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with the ReLU activation.
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
In contrast, for the non-convex formulation of a two layer linear network on the same instance, we show that both Reptile and multi-task representation learning can have new task sample complexity of $\mathcal{O}(1)$, demonstrating a separation from convex meta-learning.
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point.
Learning to Classify Intents and Slot Labels Given a Handful of Examples
Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets.
Detecting Problem Statements in Peer Assessments
We attempt to automate the process of deciding whether a review comment detects a problem.
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection
Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporally varying (i. e., moving) foreground objects from the static background in video, assuming the background frames to be low-rank while the foreground to be spatially sparse.
``Who said it, and Why?'' Provenance for Natural Language Claims
In an era where generating content and publishing it is so easy, we are bombarded with information and are exposed to all kinds of claims, some of which do not always rank high on the truth scale.
Democratizing the Edge: A Pervasive Edge Computing Framework
The needs of emerging applications, such as augmented and virtual reality, federated machine learning, and autonomous driving, have motivated edge computing--the push of computation capabilities to the edge.
Networking and Internet Architecture
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution.
On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems
Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches.
Audio and Speech Processing Sound
Tactical Decision Making for Emergency Vehicles Based on A Combinational Learning Method
The following approach reveals that DRL could complement rule-based avoiding strategy in generalization, and on the contrary, the rule-based avoiding strategy could complement DRL in stability, and their combination could lead to less response time, lower collision rate and smoother trajectory.
Reinforcement Learning on Computational Resource Allocation of Cloud-based Wireless Networks
This paper models this dynamic computational resource allocation problem into a Markov Decision Process (MDP) and designs a model-based reinforcement-learning agent to optimise the dynamic resource allocation of the CPU usage.
Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
However, this has not been made mathematically rigorous, and the hurdle is that the fully connected net can always simulate the convolutional net (for a fixed task).
DeepWiPHY: Deep Learning-based Receiver Design and Dataset for IEEE 802.11ax Systems
In this work, we develop DeepWiPHY, a deep learning-based architecture to replace the channel estimation, common phase error (CPE) correction, sampling rate offset (SRO) correction, and equalization modules of IEEE 802. 11ax based orthogonal frequency division multiplexing (OFDM) receivers.
Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography
Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs).
CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels
Current mainstream of CT reconstruction methods based on deep learning usually needs to fix the scanning geometry and dose level, which will significantly aggravate the training cost and need more training data for clinical application.
Construction and application of algebraic dual polynomial representations for finite element methods on quadrilateral and hexahedral meshes
It will be shown that a bilinear form of a primal and a dual representation is equal to the vector inner product of the expansion coefficients (degrees of freedom) of both representations.
Numerical Analysis Numerical Analysis
Three-dimensional cell culture model for hepatocytes opens a new avenue of real world research on liver
3-demensional (3D) culture model is a valuable in vitro tool to study liver biology, metabolism, organogenesis, tissue morphology, drug discovery and cell-based assays.
Testing Scenario Library Generation for Connected and Automated Vehicles: An Adaptive Framework
A customized testing scenario library for a specific CAV model is generated through an adaptive process.
Extension of causal decomposition in the mutual complex dynamic process
Causal decomposition depicts a cause-effect relationship that is not based on the concept of prediction, but based on the phase dependence of time series.
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Meta learning to classify intent and slot labels with noisy few shot examples
Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU).
Inflection Point: A New Perspective on Photonic Nanojets
When light propagates through the edge or middle part of microparticle's incoming interface, there is a basic rule that light converges and diverges rapidly or slowly at the output port.
Optics
