Search Results for author:
Found 88 papers, 38 papers with code
Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition
Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.
COVID-19 in Bulgarian Social Media: Factuality, Harmfulness, Propaganda, and Framing
With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first global infodemic.
Contrastive Learning Is Spectral Clustering On Similarity Graph
Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works.
Disentangling Writer and Character Styles for Handwriting Generation
In light of this, we propose to disentangle the style representations at both writer and character levels from individual handwritings to synthesize realistic stylized online handwritten characters.
Towards Stable Test-Time Adaptation in Dynamic Wild World
In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability.
Free Lunch for Domain Adversarial Training: Environment Label Smoothing
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #2 on
Domain Adaptation
on Office-Home
Bidirectional Propagation for Cross-Modal 3D Object Detection
Recent works have revealed the superiority of feature-level fusion for cross-modal 3D object detection, where fine-grained feature propagation from 2D image pixels to 3D LiDAR points has been widely adopted for performance improvement.
A Comprehensive Study and Comparison of the Robustness of 3D Object Detectors Against Adversarial Attacks
Deep learning-based 3D object detectors have made significant progress in recent years and have been deployed in a wide range of applications.
Expanding Small-Scale Datasets with Guided Imagination
The two criteria are verified to be essential for effective dataset expansion: GIF-SD obtains 13. 5\% higher model accuracy on natural image datasets than unguided expansion with SD.
Consistent and Truthful Interpretation with Fourier Analysis
For many interdisciplinary fields, ML interpretations need to be consistent with what-if scenarios related to the current case, i. e., if one factor changes, how does the model react?
Moment Estimation for Nonparametric Mixture Models Through Implicit Tensor Decomposition
We present an alternating least squares type numerical optimization scheme to estimate conditionally-independent mixture models in $\mathbb{R}^n$, with minimal additional distributional assumptions.
Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving
Specifically, DucTeacher consists of two curriculums, i. e., (1) domain evolving curriculum seeks to learn from the data progressively to handle data distribution discrepancy by estimating the similarity between domains, and (2) distribution matching curriculum seeks to estimate the class distribution for each unlabeled domain to handle class distribution shifts.
Leveraging Artificial Intelligence on Binary Code Comprehension
We propose to develop Artificial Intelligence (AI) models that aid human comprehension of binary code.
COMBO: Pre-Training Representations of Binary Code Using Contrastive Learning
To the best of our knowledge, COMBO is the first language representation model that incorporates source code, binary code, and comments into contrastive code representation learning and unifies multiple tasks for binary code analysis.
Recurrent LSTM-based UAV Trajectory Prediction with ADS-B Information
It is noted that the recurrent neural network (RNN) is available for the UAV trajectory prediction, in which the long short-term memory (LSTM) is specialized in dealing with the time-series data.
Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification
Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains even without any annotations in these domains.
Quantized Adaptive Subgradient Algorithms and Their Applications
Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.
CTooth+: A Large-scale Dental Cone Beam Computed Tomography Dataset and Benchmark for Tooth Volume Segmentation
This work provides a new benchmark for the tooth volume segmentation task, and the experiment can serve as the baseline for future AI-based dental imaging research and clinical application development.
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
2) Prototype-based alignment and replay: based on the identified label prototypes, we align both domains and enforce the model to retain previous knowledge.
Unsupervised Visual Representation Learning by Synchronous Momentum Grouping
In this paper, we propose a genuine group-level contrastive visual representation learning method whose linear evaluation performance on ImageNet surpasses the vanilla supervised learning.
Ranked #19 on
Self-Supervised Image Classification
on ImageNet
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects, then propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables.
Ranked #1 on
3D Object Detection
on KITTI Cars Easy
PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient
First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student.
Efficient Test-Time Model Adaptation without Forgetting
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w. r. t.
Semantic Segmentation by Early Region Proxy
Typical vision backbones manipulate structured features.
Boost Test-Time Performance with Closed-Loop Inference
Motivated by this, we propose to predict those hard-classified test samples in a looped manner to boost the model performance.
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection.
QCRI's COVID-19 Disinformation Detector: A System to Fight the COVID-19 Infodemic in Social Media
Fighting the ongoing COVID-19 infodemic has been declared as one of the most important focus areas by the World Health Organization since the onset of the COVID-19 pandemic.
A Generative Car-following Model Conditioned On Driving Styles
Car-following (CF) modeling, an essential component in simulating human CF behaviors, has attracted increasing research interest in the past decades.
Adaptive Channel Encoding Transformer for Point Cloud Analysis
Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis.
Adaptive Channel Encoding for Point Cloud Analysis
Attention mechanism plays a more and more important role in point cloud analysis and channel attention is one of the hotspots.
Lightweight Transformer Backbone for Medical Object Detection
Specifically, we propose a novel modification of visual transformer (ViT) on image feature patches to connect the feature patches of a tumor with healthy backgrounds of breast images and form a more robust backbone for tumor detection.
Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
In our study, we use real data sets and the state-of-the-art machine learning model to evaluate our attack detection scheme and the results confirm the effectiveness of our detection method.
Deep Long-Tailed Learning: A Survey
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution.
Generalizable Person Re-identification Without Demographics
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
How Well Does Self-Supervised Pre-Training Perform with Streaming ImageNet?
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
A Second Pandemic? Analysis of Fake News About COVID-19 Vaccines in Qatar
While COVID-19 vaccines are finally becoming widely available, a second pandemic that revolves around the circulation of anti-vaxxer fake news may hinder efforts to recover from the first one.
Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis
To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification.
Opinion Prediction with User Fingerprinting
Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.
Ranked #5 on
Long-tail Learning
on iNaturalist 2018
AdaXpert: Adapting Neural Architecture for Growing Data
To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
(2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes.
Ranked #9 on
Domain Adaptation
on VisDA2017
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model.
AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy
Accurate evaluation of the treatment result on X-ray images is a significant and challenging step in root canal therapy since the incorrect interpretation of the therapy results will hamper timely follow-up which is crucial to the patients' treatment outcome.
How Well Does Self-Supervised Pre-Training Perform with Streaming Data?
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.
Efficient Spatialtemporal Context Modeling for Action Recognition
Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition.
Learning Defense Transformers for Counterattacking Adversarial Examples
Relying on this, we learn a defense transformer to counterattack the adversarial examples by parameterizing the affine transformations and exploiting the boundary information of DNNs.
Improving Authorship Verification using Linguistic Divergence
It is also one of the first to use Deep Language Models in this setting.
High-Resolution Segmentation of Tooth Root Fuzzy Edge Based on Polynomial Curve Fitting with Landmark Detection
As the most economical and routine auxiliary examination in the diagnosis of root canal treatment, oral X-ray has been widely used by stomatologists.
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose.
Random matrix description of dynamically backscattered coherent waves propagating in a wide-field-illuminated random medium
We find that the dynamic speckle patterns can be utilized to decouple the singly and multiply backscattered components.
Optics Applied Physics
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning.
Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution
In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM).
The Twelvefold Way of Non-Sequential Lossless Compression
Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions.
Information Theory Information Theory
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.
Ranked #18 on
Skeleton Based Action Recognition
on NTU RGB+D
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
Deep learning based medical image diagnosis has shown great potential in clinical medicine.
Improving Chinese Segmentation-free Word Embedding With Unsupervised Association Measure
Recent work on segmentation-free word embedding(sembei) developed a new pipeline of word embedding for unsegmentated language while avoiding segmentation as a preprocessing step.
Birds of a Feather Flock Together: Satirical News Detection via Language Model Differentiation
In this work, we propose a method that differentiates the satirical news and true news.
Relation-Aware Transformer for Portfolio Policy Learning
One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.
Exemplar Loss for Siamese Network in Visual Tracking
In general, Siamese tracking algorithms, supervised by logistic loss and triplet loss, increase the value of inner product between exemplar template and positive sample while reduce the value of inner product with background sample.
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
As deep learning brings excellent performances to object detection algorithms, Tracking by Detection (TBD) has become the mainstream tracking framework.
Energy-Efficient Cyclical Trajectory Design for UAV-Aided Maritime Data Collection in Wind
We aim to minimize the UAV's energy consumption in completing the task by jointly optimizing the communication time scheduling among the buoys and the UAV's flight trajectory subject to wind effect, which is a non-convex problem and difficult to solve optimally.
Prta: A System to Support the Analysis of Propaganda Techniques in the News
However, little attention has been paid to the specific rhetorical and psychological techniques used to convey propaganda messages.
COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.
Disturbance-immune Weight Sharing for Neural Architecture Search
To alleviate the performance disturbance issue, we propose a new disturbance-immune update strategy for model updating.
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.
ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting
Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature.
Correcting for Selection Bias in Learning-to-rank Systems
Click data collected by modern recommendation systems are an important source of observational data that can be utilized to train learning-to-rank (LTR) systems.
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.
Online Adaptive Asymmetric Active Learning with Limited Budgets
In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).
Multi-marginal Wasserstein GAN
Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.
Tanbih: Get To Know What You Are Reading
We introduce Tanbih, a news aggregator with intelligent analysis tools to help readers understanding what's behind a news story.
Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.
Ranked #44 on
Skeleton Based Action Recognition
on NTU RGB+D
Interpretable Complex-Valued Neural Networks for Privacy Protection
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features.
Training Binary Weight Networks via Semi-Binary Decomposition
In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix.
Two-Step Quantization for Low-Bit Neural Networks
In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes.
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #2 on
3D Action Recognition
on Assembly101
Adaptive Cost-sensitive Online Classification
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost.
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks With Spatiotemporal Transformer Modules
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses.
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously.
QCRI Live Speech Translation System
This paper presents QCRI{'}s Arabic-to-English live speech translation system.
Leveraging Multiple Domains for Sentiment Classification
In addition, the learned feature representation can be used as classifier since our model defines the meaning of feature value and arranges high-level features in a prefixed order, so it is not necessary to train another classifier on top of the new features.
The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition
For language modelling, we made available over 110M words crawled from Aljazeera Arabic website Aljazeera. net for a 10 year duration 2000-2011.
Constrained Clustering and Its Application to Face Clustering in Videos
As a result, many pairwise constraints between faces can be easily obtained from the temporal and spatial knowledge of the face tracks.
