Search Results for author:
Found 106 papers, 31 papers with code
Discriminating between standard Romanian and Moldavian tweets using filtered character ngrams
Our best model reached an F1 score of 0. 715 on the evaluation dataset of tweets, and 0. 667 on the held-out test dataset.
E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models
Enhancing the interpretability of text classification models can help increase the reliability of these models in real-world applications.
Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images
With the rapid advancement of deep learning, computational pathology has made significant progress in cancer diagnosis and subtyping.
EliGen: Entity-Level Controlled Image Generation with Regional Attention
Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image.
SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer
To resolve economical association computation, we introduce sparse proxy attention combined with table-based relative bias, which enables low-cost and precise interactions between proxy and point features.
Semi-Implicit Neural Ordinary Differential Equations
Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning.
PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects
Neural implicit surface reconstruction has achieved remarkable progress recently.
Predicting User Stances from Target-Agnostic Information using Large Language Models
We investigate Large Language Models' (LLMs) ability to predict a user's stance on a target given a collection of his/her target-agnostic social media posts (i. e., user-level stance prediction).
Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategy
In the domain of Camouflaged Object Segmentation (COS), despite continuous improvements in segmentation performance, the underlying mechanisms of effective camouflage remain poorly understood, akin to a black box.
MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question Answering
Recent advancements in retrieval-augmented generation (RAG) have demonstrated impressive performance in the question-answering (QA) task.
Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data
First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy.
Conversational Dueling Bandits in Generalized Linear Models
Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities.
GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection
Existing feature matching methods focus on homography and pose estimation in long-term visual localization, lacking references for geometric verification.
SWCF-Net: Similarity-weighted Convolution and Local-global Fusion for Efficient Large-scale Point Cloud Semantic Segmentation
In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features.
A note on the error analysis of data-driven closure models for large eddy simulations of turbulence
We also demonstrate that this error is significantly affected by the time step size and the Jacobian which play a role in amplifying the initial one-step error made by using the closure.
Redefining Information Retrieval of Structured Database via Large Language Models
Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning.
Prompt Learning for Oriented Power Transmission Tower Detection in High-Resolution SAR Images
The interaction of image-level and prompt-level features is utilized to address the clutter interference.
Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency
The SPM module incorporates a Severity Perception mechanism, guiding a Mask operation that enables our model to learn highly consistent features from the augmented scenes.
Study of the mechanism of electroacupuncture regulating ferroptosis, inhibiting bladder neck fibrosis, and improving bladder urination function after suprasacral spinal cord injury using proteomics
Purpose The aim of this study was to explore whether electroacupuncture regulates phenotypic transformation of smooth muscle cells by inhibiting ferroptosis and inhibiting fibrosis, thereby improving bladder urination function after suprasacral spinal cord injury (SSCI).
DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning
Secondly, we propose a class-aware parallel adaptation method that aligns class-level distributions for each source-target language pair, thereby alleviating the language pairs' language gap.
NocPlace: Nocturnal Visual Place Recognition via Generative and Inherited Knowledge Transfer
Visual Place Recognition (VPR) is crucial in computer vision, aiming to retrieve database images similar to a query image from an extensive collection of known images.
CANAMRF: An Attention-Based Model for Multimodal Depression Detection
Multimodal depression detection is an important research topic that aims to predict human mental states using multimodal data.
Memory-Efficient Reversible Spiking Neural Networks
In this paper, we propose the reversible spiking neural network to reduce the memory cost of intermediate activations and membrane potentials during training.
Enhancing Stance Classification on Social Media Using Quantified Moral Foundations
The results highlight the importance of considering deeper psychological attributes in stance analysis and underscores the role of moral foundations in guiding online social behavior.
RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box.
Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies
To our knowledge, our work is the first attempt to directly recover 3D structures of a temporally-varying particle from liquid-phase EM movies.
Cryogenic Electron Microscopy (cryo-EM)
Object Reconstruction
+1
DPSeq: A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers using Sequencer Architecture
Additionally, under the same experimental conditions using the same set of training and testing datasets, DPSeq surpassed 4 CNN (ResNet18, ResNet50, MobileNetV2, and EfficientNet) and 2 transformer (ViT and Swin-T) models, achieving the highest AUROC and AUPRC values in predicting MSI status, BRAF mutation, and CIMP status.
NPR: Nocturnal Place Recognition in Streets
Then we used this model to process existing large-scale VPR datasets to generate the VPR-Night datasets and demonstrated how to combine them with two popular VPR pipelines.
Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020
People who share similar opinions towards controversial topics could form an echo chamber and may share similar political views toward other topics as well.
DSDP: A Blind Docking Strategy Accelerated by GPUs
In this study, we take the advantage of both traditional and machine-learning based methods, and present a method Deep Site and Docking Pose (DSDP) to improve the performance of blind docking.
Prediction of SLAM ATE Using an Ensemble Learning Regression Model and 1-D Global Pooling of Data Characterization
One of the essential steps to achieve robustness and resilience is the ability of SLAM to have an integrity measure for its localization estimates, and thus, have internal fault tolerance mechanisms to deal with performance degradation.
A Convolutional-Transformer Network for Crack Segmentation with Boundary Awareness
And the BAM learns the boundary features from the dilated crack label.
Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines
However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images.
ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition
Typically, these approaches adopt a teacher-student architecture, where the teacher network is trained in the source language, and the student network seeks to learn knowledge from the teacher network and is expected to perform well in the target language.
L-MAE: Masked Autoencoders are Semantic Segmentation Datasets Augmenter
In detail, L-MAE adopts the fusion strategy that stacks the label and the corresponding image, namely fuse map.
RAPS: A Novel Few-Shot Relation Extraction Pipeline with Query-Information Guided Attention and Adaptive Prototype Fusion
Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances.
Novel 3D Scene Understanding Applications From Recurrence in a Single Image
We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image.
Optimizing SLAM Evaluation Footprint Through Dynamic Range Coverage Analysis of Datasets
Simultaneous Localization and Mapping (SLAM) is considered an ever-evolving problem due to its usage in many applications.
Prognostic Significance of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images in Colorectal Cancers
Methods We developed an automated, multiscale LinkNet workflow for quantifying cellular-level TILs for CRC tumors using H&E-stained images.
Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving SOTA predictive performance with fewer data using Swin Transformer
In this study, based on the latest Hierarchical Vision Transformer using Shifted Windows (Swin-T), we developed an efficient workflow for biomarkers in CRC (MSI, hypermutation, chromosomal instability, CpG island methylator phenotype, BRAF, and TP53 mutation) that only required relatively small datasets, but achieved the state-of-the-art (SOTA) predictive performance.
On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines.
Perspective Phase Angle Model for Polarimetric 3D Reconstruction
Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption.
Highlight Specular Reflection Separation based on Tensor Low-rank and Sparse Decomposition Using Polarimetric Cues
This regularization boosts the performance of the method to recover an accurate diffuse image by handling the color distortion, a common problem of chromaticity-based methods, especially in case of strong specular reflection.
Diagnostic Communication and Visual System based on Vehicle UDS Protocol
Unified Diagnostic Services (UDS) is a diagnostic communication protocol used in electronic control units (ECUs) within automotive electronics, which is specified in the ISO 14229-1.
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.
A memory-efficient neural ODE framework based on high-level adjoint differentiation
On the image classification problems, PNODE is up to two times faster than the vanilla neural ODE and up to 2. 3 times faster than the best existing reverse-accurate method.
FinBERT-MRC: financial named entity recognition using BERT under the machine reading comprehension paradigm
We conduct experiments on a publicly available Chinese financial dataset ChFinAnn and a real-word bussiness dataset AdminPunish.
A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations
In addition, compared to the published models for genetic alterations, AMIML provided a significant improvement for predicting a wide range of genes (e. g., KMT2C, TP53, and SETD2 for KIRC; ERBB2, BRCA1, and BRCA2 for BRCA; JAK1, POLE, and MTOR for UCEC) as well as produced outstanding predictive models for other clinically relevant gene mutations, which have not been reported in the current literature.
FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server
Despite achieving remarkable performance, Federated Learning (FL) suffers from two critical challenges, i. e., limited computational resources and low training efficiency.
Colorectal cancer survival prediction using deep distribution based multiple-instance learning
Several deep learning algorithms have been developed to predict survival of cancer patients using whole slide images (WSIs). However, identification of image phenotypes within the WSIs that are relevant to patient survival and disease progression is difficult for both clinicians, and deep learning algorithms.
Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder
We employ a high-level layer of a pre-trained CNN to generate features, and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time.
Sparse Optical Flow-Based Line Feature Tracking
To achieve this goal, an efficient two endpoint tracking (TET) method is presented: first, describe a given line feature with its two endpoints; next, track the two endpoints based on SOF to obtain two new tracked endpoints by minimizing a pixel-level grayscale residual function; finally, connect the two tracked endpoints to generate a new line feature.
Optimize Deep Learning Models for Prediction of Gene Mutations Using Unsupervised Clustering
We showed that unsupervised clustering of image patches could help identify predictive patches, exclude patches lack of predictive information, and therefore improve prediction on gene mutations in all three different cancer types, compared with the WSI based method without selection of image patches and models based on only tumor regions.
Deep Polarimetric HDR Reconstruction
This paper proposes a novel learning based high-dynamic-range (HDR) reconstruction method using a polarization camera.
DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking
Many multi-object tracking (MOT) methods follow the framework of "tracking by detection", which associates the target objects-of-interest based on the detection results.
DePS: An improved deep learning model for de novo peptide sequencing
De novo peptide sequencing from mass spectrometry data is an important method for protein identification.
Are We Ready for Robust and Resilient SLAM? A Framework For Quantitative Characterization of SLAM Datasets
In order to fill this void, characterization of the operating conditions of SLAM systems is essential in order to provide an environment for quantitative measurement of robustness and resilience.
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Finally, this LiDAR Net can serve as the teacher to transfer the learned knowledge to the baseline model.
Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model
The extracted features from the finetuned FTX2048 exhibited significantly higher accuracy for predicting tisue types of CRC compared to the off the shelf feature directly from Xception based on ImageNet database.
Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
In addition, we compare our online adaptation framework against the state-of-the-art pre-trained depth prediction CNNs to show that our online adapted depth prediction CNN outperforms the depth prediction CNNs that have been trained on a large collection of datasets.
A Retrospective Analysis using Deep-Learning Models for Prediction of Survival Outcome and Benefit of Adjuvant Chemotherapy in Stage II/III Colorectal Cancer
We developed a novel deep-learning algorithm (CRCNet) using whole-slide images from Molecular and Cellular Oncology (MCO) to predict survival benefit of adjuvant chemotherapy in stage II/III CRC.
Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
Vital importance has necessity to be attached to cooperation in multi-agent environments, as a result of which some reinforcement learning algorithms combined with graph neural networks have been proposed to understand the mutual interplay between agents.
Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
On CIFAR, we reach similar accuracy to SOTA methods with 15% and 24% higher FLOPs reduction.
Stiffness-aware neural network for learning Hamiltonian systems
We propose stiffness-aware neural network (SANN), a new method for learning Hamiltonian dynamical systems from data.
Rethinking Training from Scratch for Object Detection
The ImageNet pre-training initialization is the de-facto standard for object detection.
Deep Snapshot HDR Reconstruction Based on the Polarization Camera
In our approach, we first study the relationship among polarizer orientation, degree and angle of polarization of light to the exposure time of a pixel in the polarization image.
GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor
In this paper, we propose a framework to decouple network structure from operator search space, and use two BOHBs to search alternatively.
A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
This paper reviews the methods of WSI analysis based on machine learning.
Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
This paper is concerned with polarimetric dense map reconstruction based on a polarization camera with the help of relative depth information as a prior.
Mass-Conserving Implicit-Explicit Methods for Coupled Compressible Navier-Stokes Equations
Earth system models are composed of coupled components that separately model systems such as the global atmosphere, ocean, and land surface.
Numerical Analysis Numerical Analysis Computational Physics Fluid Dynamics 76N06, 65M08, 65L04
Direct Depth Learning Network for Stereo Matching
To make the Adaptive-Grained Depth Refinement stage robust to the coarse depth and adaptive to the depth range of the points, the Granularity Uncertainty is introduced to Adaptive-Grained Depth Refinement stage.
Full Matching on Low Resolution for Disparity Estimation
To this end, we first propose to decompose the full matching task into multiple stages of the cost aggregation module.
Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
Image-to-image translation has been revolutionized with GAN-based methods.
Object-aware Feature Aggregation for Video Object Detection
As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance.
A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models.
PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
This paper presents PL-VINS, a real-time optimization-based monocular VINS method with point and line features, developed based on the state-of-the-art point-based VINS-Mono \cite{vins}.
Fast ORB-SLAM without Keypoint Descriptors
ORB-SLAM2 \cite{orbslam2} is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe.
Robotics Computational Geometry I.4.0; I.4.9
A Siamese CNN for Image Steganalysis
On the assumption that natural image noise is similar between different image sub-regions, we propose an end-to-end, deep learning, novel solution for distinguishing steganography images from normal images that provides satisfying performance.
To Filter Prune, or to Layer Prune, That Is The Question
LayerPrune presents a set of layer pruning methods based on different criteria that achieve higher latency reduction than filter pruning methods on similar accuracy.
DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction
To this end, we use a visual SLAM algorithm to reliably recover the camera poses and semi-dense depth maps of the keyframes, and then use relative depth prediction to densify the semi-dense depth maps and refine the keyframe pose-graph.
Gated Path Selection Network for Semantic Segmentation
Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints.
Large-scale Multi-modal Person Identification in Real Unconstrained Environments
Person identification (P-ID) under real unconstrained noisy environments is a huge challenge.
Implicit Semantic Data Augmentation for Deep Networks
Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., adding sunglasses or changing backgrounds.
Improved Techniques for Training Adaptive Deep Networks
Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time.
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
In general, semi-supervised training is preferred as it does not suffer from the weaknesses of either supervised training, resulting from the difference in the cameras and the LiDARs field of view, or unsupervised training, resulting from the poor depth accuracy that can be recovered from a stereo pair.
Ranked #51 on
Monocular Depth Estimation
on KITTI Eigen split
Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning
This is achieved by removing the least important features with a novel joint end-to-end filter pruning.
Moving Object Detection under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition
We are interested in moving object detection in applications involving time-lapse image sequences for which current methods mistakenly group moving objects and illumination changes into foreground.
Single-step Options for Adversary Driving
In this paper, we use reinforcement learning for safety driving in adversary settings.
Fine-Grained Vehicle Classification with Unsupervised Parts Co-occurrence Learning
In addition, we achieve 95. 5% and 93. 19% on CompCars on both train-test splits, 70-30 and 50-50, outperforming the other methods by 4. 5% and 8% respectively.
Ranked #1 on
Fine-Grained Image Classification
on BoxCars116K
Human Pose Estimation with Spatial Contextual Information
With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information.
Ranked #10 on
Pose Estimation
on MPII Human Pose
Part-level Car Parsing and Reconstruction from Single Street View
As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views.
CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction
Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms.
Theoretical and Empirical Study of Adversarial Examples
We show that under some symmetrical assumptions, label smoothing, logit squeezing, weight decay, mix up and feature smoothing all produce an unbiased estimation of the decision boundary with smaller estimated variance.
Unsupervised Learning of Stereo Matching
However, due to the limitations of these datasets and the difficulty of collecting new stereo data, current methods fail in real-life cases.
Moving Object Detection in Time-Lapse or Motion Trigger Image Sequences Using Low-Rank and Invariant Sparse Decomposition
Next, we propose a low-rank and invariant sparse decomposition using the prior map to detect moving objects under significant illumination changes.
Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic applications due to the expensive time complexity.
Ranked #11 on
Shadow Detection
on SBU / SBU-Refine
Face Recognition using Multi-Modal Low-Rank Dictionary Learning
Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under illumination and pose variations.
Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding
A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution.
Multimedia
Object Classification with Joint Projection and Low-rank Dictionary Learning
To address these issues, we propose a joint projection and low-rank dictionary learning method using dual graph constraints (JP-LRDL).
On The Stability of Video Detection and Tracking
Lastly, based on this metric, we evaluate several existing methods for video detection and show how they affect accuracy and stability.
Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation
Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches.
Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints
To address this issue, we propose a joint projection and dictionary learning using low-rank regularization and graph constraints (JPDL-LR).
COROLA: A Sequential Solution to Moving Object Detection Using Low-rank Approximation
Extracting moving objects from a video sequence and estimating the background of each individual image are fundamental issues in many practical applications such as visual surveillance, intelligent vehicle navigation, and traffic monitoring.
Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detection
Deep convolutional neural networks (CNN) have recently been shown in many computer vision and pattern recog- nition applications to outperform by a significant margin state- of-the-art solutions that use traditional hand-crafted features.
Loop Closure Detection
Simultaneous Localization and Mapping
Stopping Rules for Bag-of-Words Image Search and Its Application in Appearance-Based Localization
We introduce a notion of difficulty for the image matching problems and propose methods that reduce the amount of computations required for the feature vector-quantization task in BoW by exploiting the fact that easier queries need less computational resources.
An Efficient Index for Visual Search in Appearance-based SLAM
Vector-quantization can be a computationally expensive step in visual bag-of-words (BoW) search when the vocabulary is large.
