Search Results for author:
Found 200 papers, 63 papers with code
SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks.
Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation
Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations.
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
Ranked #1 on
Zero-Shot Object Detection
on MSCOCO
Exploring Social Media for Early Detection of Depression in COVID-19 Patients
Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression.
SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry
We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.
Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection
Specifically, node features are first mapped to a feature space through neighborhood aggregation and then generated samples for the minority class in the feature space.
Eliminating Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion
The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process.
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.
Ranked #2 on
Multi-Person Pose Estimation
on CrowdPose
(using extra training data)
Deep Learning for Short-Latency Epileptic Seizure Detection with Probabilistic Classification
In this manuscript, we propose a novel deep learning (DL)-based framework intended for obtaining short latency in real-time electroencephalogram-based epileptic seizure detection using multiscale 3D convolutional neural networks.
MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark
However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.
Ranked #1 on
Stance Detection
on MGTAB
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.
A 97 fJ/Conversion Neuron-ADC with Reconfigurable Sampling and Static Power Reduction
A bio-inspired Neuron-ADC with reconfigurable sampling and static power reduction for biomedical applications is proposed in this work.
Sub-1ms Instinctual Interference Adaptive GaN LNA Front-End with Power and Linearity Tuning
The system permits an LNA power consumption to tune from 500 mW to 2 W (4X increase) in order to adjust the linearity from P\textsubscript{1dB, IN}=-10. 5 dBm to 0. 5 dBm (>10X increase).
On Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple deep neural networks (DNNs) has shown state-of-the-art performances.
GreenPLM: Cross-lingual pre-trained language models conversion with (almost) no cost
While large pre-trained models have transformed the field of natural language processing (NLP), the high training cost and low cross-lingual availability of such models prevent the new advances from being equally shared by users across all languages, especially the less spoken ones.
MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation
To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement.
Progressive Motion Context Refine Network for Efficient Video Frame Interpolation
Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation.
AI enhanced finite element multiscale modelling and structural uncertainty analysis of a functionally graded porous beam
The error range of CNN models leads to an uncertain mechanical performance, which is further evaluated in a structural uncertainty analysis on the FG porous three-layer beam consisting of two thin high-density layers and a thick low-density one, where the imprecise CNN predicted moduli are represented as triangular fuzzy numbers in double parametric form.
3D Human Mesh Construction Leveraging Wi-Fi
In this paper, we present, Wi-Mesh, a WiFi vision-based 3D human mesh construction system.
Online LiDAR-Camera Extrinsic Parameters Self-checking
This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks.
A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption.
Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment
Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error.
Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond
In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications.
Robust Person Identification: A WiFi Vision-based Approach
In particular, we leverage multiple antennas on next-generation WiFi devices and 2D AoA estimation of the signal reflections to enable WiFi to visualize a person in the physical environment.
Rethinking and Recomputing the Value of ML Models
In this paper, we argue that the way we have been training and evaluating ML models has largely forgotten the fact that they are applied in an organization or societal context as they provide value to people.
METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets
To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9, 101 entities (in 5, 278 tweets).
YATO: Yet Another deep learning based Text analysis Open toolkit
Designed in a hierarchical structure, YATO supports free combinations of three types of features including 1) traditional neural networks (CNN, RNN, etc.
A Compact Online-Learning Spiking Neuromorphic Biosignal Processor
In this design, a compact online learning neuromorphic hardware architecture with ultra-low power consumption designed explicitly for biosignal processing is proposed.
SpikeSEE: An Energy-Efficient Dynamic Scenes Processing Framework for Retinal Prostheses
In this paper, we propose an energy-efficient dynamic scenes processing framework (SpikeSEE) that combines a spike representation encoding technique and a bio-inspired spiking recurrent neural network (SRNN) model to achieve intelligent processing and extreme low-power computation for retinal prostheses.
PTab: Using the Pre-trained Language Model for Modeling Tabular Data
The learning of an effective contextual representation requires meaningful features and a large amount of data.
An Online Sparse Streaming Feature Selection Algorithm
In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i. e., how to establish the uncertain relationship between sparse streaming features and labels.
ATCA: an Arc Trajectory Based Model with Curvature Attention for Video Frame Interpolation
Video frame interpolation is a classic and challenging low-level computer vision task.
Personalized Promotion Decision Making Based on Direct and Enduring Effect Predictions
To achieve a better lift return on investment (lift ROI) on the enduring effect of the promotion and improve customer retention and loyalty, we propose a framework of multiple treatment promotion decision making by modeling each customer's direct and enduring response.
Using Twitter Data to Understand Public Perceptions of Approved versus Off-label Use for COVID-19-related Medications
Time-trend analysis revealed that Hydroxychloroquine and Ivermectin received much more discussion than Molnupiravir and Remdesivir, particularly during COVID-19 surges.
Learning Deep Feature Correspondence for Unsupervised Anomaly Detection and Segmentation
We develop our DFC in an asymmetric dual network framework that consists of a generic feature extraction network and an elaborated feature estimation network, and detect the possible anomalies within images by modeling and evaluating the associated deep feature correspondence between the two dual network branches.
Ranked #1 on
Anomaly Detection
on BottleCap
(using extra training data)
Low-resource Accent Classification in Geographically-proximate Settings: A Forensic and Sociophonetics Perspective
Accented speech recognition and accent classification are relatively under-explored research areas in speech technology.
Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency
By aligning the class tokens and spatial attention maps of paired NBI and WL images at different levels, the Transformer achieves the ability to keep both global and local representation consistency for the above two modalities.
DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
Toward Unpaired Multi-modal Medical Image Segmentation via Learning Structured Semantic Consistency
Different from previous methods which adopted both modality-specific and modality-shared modules to accommodate the appearance variance of different modalities while extracting the common semantic information, our method is based on a single Transformer with a carefully designed External Attention Module (EAM) to learn the structured semantic consistency (i. e. semantic class representations and their correlations) between modalities in the training phase.
AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation
Constraint by the high cost of collecting and labeling 3D medical data, most of the deep learning models to date are driven by datasets with a limited number of organs of interest or samples, which still limits the power of modern deep models and makes it difficult to provide a fully comprehensive and fair estimate of various methods.
Binary Single-dimensional Convolutional Neural Network for Seizure Prediction
Nowadays, several deep learning methods are proposed to tackle the challenge of epileptic seizure prediction.
Modeling Image Composition for Complex Scene Generation
Compared to existing CNN-based and Transformer-based generation models that entangled modeling on pixel-level&patch-level and object-level&patch-level respectively, the proposed focal attention predicts the current patch token by only focusing on its highly-related tokens that specified by the spatial layout, thereby achieving disambiguation during training.
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications.
Ranked #1 on
Video Frame Interpolation
on Middlebury
Recent Trends and Future Prospects of Neural Recording Circuits and Systems: A Tutorial Brief
Recent years have seen fast advances in neural recording circuits and systems as they offer a promising way to investigate real-time brain monitoring and the closed-loop modulation of psychological disorders and neurodegenerative diseases.
An Event-Driven Compressive Neuromorphic System for Cardiac Arrhythmia Detection
Wearable electrocardiograph (ECG) recording and processing systems have been developed to detect cardiac arrhythmia to help prevent heart attacks.
Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images
In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions.
Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures
To identify the preictal region that precedes the onset of seizure, a large number of annotated EEG signals are required to train DL algorithms.
neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning
Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.
3D Human Pose Estimation for Free-from and Moving Activities Using WiFi
This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses WiFi devices at home.
Towards Fine-grained Causal Reasoning and QA
Understanding causality is key to the success of NLP applications, especially in high-stakes domains.
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
Sensor-based environmental perception is a crucial part of the autonomous driving system.
Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation
The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.
Online Learning of Trellis Diagram Using Neural Network for Robust Detection and Decoding
As an interesting by-product, we propose an enhancement to the BLE standard by introducing a bit interleaver to its physical layer; the resultant improvement of the receiver sensitivity can make it a better fit for some Internet of Things (IoT) communications.
REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening
Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge -- Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2).
Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search
Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.
BREAK: Bronchi Reconstruction by gEodesic transformation And sKeleton embedding
Since the volume of the peripheral bronchi may be much smaller than the large branches in an input patch, the common segmentation loss is not sensitive to the breakages among the distal branches.
On the Value of ML Models
We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by their model in practical applications.
Using Conversational Artificial Intelligence to Support Children's Search in the Classroom
Further, we discuss preliminary ideas on strategies for evaluation.
The Science of Rejection: A Research Area for Human Computation
We motivate why the science of learning to reject model predictions is central to ML, and why human computation has a lead role in this effort.
OctField: Hierarchical Implicit Functions for 3D Modeling
We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.
C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
AEFE: Automatic Embedded Feature Engineering for Categorical Features
The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial features from a large number of categorical features while preserving the interpretability of the method.
Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism
The aim of this study was to investigate whether a deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs.
Demographic Biases of Crowd Workers in Key Opinion Leaders Finding
Key Opinion Leaders (KOLs) are people that have a strong influence and their opinions are listened to by people when making important decisions.
3D Human Pose Estimation for Free-form Activity Using WiFi Signals
Our system tracks free-form activity by estimating a 3D skeleton pose that consists of a set of joints of the human body.
Context-guided Triple Matching for Multiple Choice Question Answering
The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer.
Visual Anomaly Detection for Images: A Survey
Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision.
Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet.
N24News: A New Dataset for Multimodal News Classification
Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification.
Ranked #1 on
News Classification
on N15News
Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images
Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing.
An End-to-End Deep Learning Approach for Epileptic Seizure Prediction
Conventional seizure prediction works usually rely on features extracted from Electroencephalography (EEG) recordings and classification algorithms such as regression or support vector machine (SVM) to locate the short time before seizure onset.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.
LightFuse: Lightweight CNN based Dual-exposure Fusion
Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.
Relationship between pulmonary nodule malignancy and surrounding pleurae, airways and vessels: a quantitative study using the public LIDC-IDRI dataset
The correlation between nodules and the counting number of airways and vessels that contact or project towards nodules are respectively (OR=22. 96, \chi^2=105. 04) and (OR=7. 06, \chi^2=290. 11).
Liquid Sensing Using WiFi Signals
Among those services, sensing the liquid level in a container is critical to building many smart home and mobile healthcare applications that improve the quality of life.
supervised adptive threshold network for instance segmentation
Currently, instance segmentation is attracting more and more attention in machine learning region.
Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach.
Stable and Effective One-Step Method for Person Search
In order to process divergence between detection and re-identification, we introduce switchable normalization and gradient centralization to improve the stability of the model.
A Novel Multi-scale Dilated 3D CNN for Epileptic Seizure Prediction
Accurate prediction of epileptic seizures allows patients to take preventive measures in advance to avoid possible injuries.
UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs.
Residual Enhanced Multi-Hypergraph Neural Network
Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.
Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels
Random Fourier Features (RFF) demonstrate wellappreciated performance in kernel approximation for largescale situations but restrict kernels to be stationary and positive definite.
FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only 1/10 computation of comparable networks to achieve on par accuracy.
Unsupervised Motion Representation Enhanced Network for Action Recognition
Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding.
A New Neuromorphic Computing Approach for Epileptic Seizure Prediction
Motivated by the energy-efficient spiking neural networks (SNNs), a neuromorphic computing approach for seizure prediction is proposed in this work.
Deep Deformation Detail Synthesis for Thin Shell Models
Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes.
Mobile-end Tone Mapping based on Integral Image and Integral Histogram
It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.
Deep Reformulated Laplacian Tone Mapping
The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.
OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow
Optical flow estimation is an essential step for many real-world computer vision tasks.
Tone Mapping Based on Multi-scale Histogram Synthesis
HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.
A Survey on Extraction of Causal Relations from Natural Language Text
Existing causality extraction techniques include knowledge-based, statistical machine learning(ML)-based, and deep learning-based approaches.
WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
Furthermore, we show the effect of different face detection procedures on the WDRIs in our database.
Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning
Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning.
Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies
However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training.
DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.
Ranked #43 on
Anomaly Detection
on MVTec AD
Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.
Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders
The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales.
Unsupervised anomaly segmentation via deep feature reconstruction
Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.
Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation
Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways.
Towards Robust Neural Networks via Orthogonal Diversity
Despite of the efficiency in defending specific attacks, adversarial training is benefited from the data augmentation, which does not contribute to the robustness of DNN itself and usually suffers from accuracy drop on clean data as well as inefficiency in unknown attacks.
Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases
To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States.
One-shot Distributed Algorithm for Generalized Eigenvalue Problem
Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.
RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval
Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures.
Integrated Communication and Localization in mmWave Systems
As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.
Learn Robust Features via Orthogonal Multi-Path
To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.
Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.
End-to-end Kernel Learning via Generative Random Fourier Features
In the second-stage process, a linear learner is conducted with respect to the mapped random features.
Improving Language Generation with Sentence Coherence Objective
Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community.
DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation
While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner.
Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects.
Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis
In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution.
Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning
Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy.
FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
Significant progress has been made for estimating optical flow using deep neural networks.
Ranked #4 on
Optical Flow Estimation
on KITTI 2012
Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces
In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).
Hierarchical Feature Embedding for Attribute Recognition
Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc.
Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
The crowd counting task aims at estimating the number of people located in an image or a frame from videos.
One-shot Distibuted Algorithm for PCA with RBF Kernels
This letter proposes a one-shot algorithm for feature-distributed kernel PCA.
Clustering via torque balance with mass and distance
Grouping similar objects is a fundamental tool of scientific analysis, ubiquitous in disciplines from biology and chemistry to astronomy and pattern recognition.
Sparse Generalized Canonical Correlation Analysis: Distributed Alternating Iteration based Approach
To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures.
Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples.
Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention
In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.
AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models.
A novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images
This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images.
Learning to Incorporate Structure Knowledge for Image Inpainting
This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works.
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet
AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.
Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval
Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities.
Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.
Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
Deep learning demands a huge amount of well-labeled data to train the network parameters.
CNN-Based Invertible Wavelet Scattering for the Investigation of Diffusion Properties of the In Vivo Human Heart in Diffusion Tensor Imaging
The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing.
A Human-AI Loop Approach for Joint Keyword Discovery and Expectation Estimation in Micropost Event Detection
Such approaches are, however, limited as they fail to reliably estimate the informativeness of a keyword and its expectation for model training.
Adaptive Initialization Method for K-means Algorithm
(c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets.
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.
Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search
Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage.
Training Data Augmentation for Detecting Adverse Drug Reactions in User-Generated Content
Social media provides a timely yet challenging data source for adverse drug reaction (ADR) detection.
LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
3D models are commonly used in computer vision and graphics.
Research Commentary on Recommendations with Side Information: A Survey and Research Directions
This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.
SDM-NET: Deep Generative Network for Structured Deformable Mesh
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
Mesh Variational Autoencoders with Edge Contraction Pooling
3D shape analysis is an important research topic in computer vision and graphics.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
AirwayNet: A Voxel-Connectivity Aware Approach for Accurate Airway Segmentation Using Convolutional Neural Networks
Airway segmentation on CT scans is critical for pulmonary disease diagnosis and endobronchial navigation.
Estimating brain age based on a healthy population with deep learning and structural MRI
Numerous studies have established that estimated brain age, as derived from statistical models trained on healthy populations, constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases.
A Review of Semi Supervised Learning Theories and Recent Advances
Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning.
An Effective Two-Branch Model-Based Deep Network for Single Image Deraining
Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).
A Regularization Approach for Instance-Based Superset Label Learning
As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms.
Multi-scale convolutional neural network for multi-focus image fusion
To address the above issues, we proposed a new MFIF method, which aims to learn feature extraction, fusion and reconstruction components together to produce a complete unsupervised end-to-end trainable deep CNN.
Online PCB Defect Detector On A New PCB Defect Dataset
To train the deep model, a dataset is established, namely DeepPCB, which contains 1, 500 image pairs with annotations including positions of 6 common types of PCB defects.
Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image
In this paper, we propose a novel method for highly efficient follicular segmentation of thyroid cytopathological WSIs.
Dynamic Curriculum Learning for Imbalanced Data Classification
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed.
Class-Aware Adversarial Lung Nodule Synthesis in CT Images
Synthesizing the objects of interests, such as lung nodules, in medical images based on the distribution of annotated datasets can be helpful for improving the supervised learning tasks, especially when the datasets are limited by size and class balance.
Discriminative analysis of the human cortex using spherical CNNs - a study on Alzheimer's disease diagnosis
In neuroimaging studies, the human cortex is commonly modeled as a sphere to preserve the topological structure of the cortical surface.
Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition
The performance of medical image analysis systems is constrained by the quantity of high-quality image annotations.
Subword Encoding in Lattice LSTM for Chinese Word Segmentation
Previous lattice LSTM model takes word embeddings as the lexicon input, we prove that subword encoding can give the comparable performance and has the benefit of not relying on any external segmentor.
Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks.
Generalization Properties of hyper-RKHS and its Applications
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.
Adversarial Attack Type I: Cheat Classifiers by Significant Changes
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations.
Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal
Reflections often obstruct the desired scene when taking photos through glass panels.
Learning Data-adaptive Nonparametric Kernels
Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.
A New Nonparametric Estimate of the Risk-Neutral Density with Applications to Variance Swaps
We develop a new nonparametric approach for estimating the risk-neutral density of asset prices and reformulate its estimation into a double-constrained optimization problem.
NCRF++: An Open-source Neural Sequence Labeling Toolkit
This paper describes NCRF++, a toolkit for neural sequence labeling.
Ranked #7 on
Chunking
on Penn Treebank
Design Challenges and Misconceptions in Neural Sequence Labeling
We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i. e. NER, Chunking, and POS tagging).
Deep Learning for Hand Gesture Recognition on Skeletal Data
In this paper, we introduce a new 3D hand gesture recognition approach based on a deep learning model.
Ranked #4 on
Hand Gesture Recognition
on DHG-14
Chinese NER Using Lattice LSTM
We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.
Ranked #13 on
Chinese Named Entity Recognition
on Resume NER
Bayesian active learning for choice models with deep Gaussian processes
In this paper, we propose an active learning algorithm and models which can gradually learn individual's preference through pairwise comparisons.
Leveraging Crowdsourcing Data For Deep Active Learning - An Application: Learning Intents in Alexa
Experiments show that our framework can accurately learn annotator expertise, infer true labels, and effectively reduce the amount of annotations in model training as compared to state-of-the-art approaches.
Robustness of classification ability of spiking neural networks
The numerical results show that there is not significant reduction in the classification ability of the network if the input signals are subject to sinusoidal and Gaussian perturbations.
YEDDA: A Lightweight Collaborative Text Span Annotation Tool
And the annotation time can be further compressed by 16. 47\% through intelligent recommendation.
Multi-stage Suture Detection for Robot Assisted Anastomosis based on Deep Learning
In robotic surgery, task automation and learning from demonstration combined with human supervision is an emerging trend for many new surgical robot platforms.
Mesh-based Autoencoders for Localized Deformation Component Analysis
Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing.
Graphics
Sparse Data Driven Mesh Deformation
This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied.
Graphics
Interacting Attention-gated Recurrent Networks for Recommendation
In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions.