Search Results for author:
Found 242 papers, 117 papers with code
Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation
Finally, we propose a novel image segmentation algorithm, called graphlet cut, that leverages the learned graphlet distribution in measuring the homogeneity of a set of spatially structured superpixels.
Semi-supervised Node Splitting for Random Forest Construction
Node splitting is an important issue in Random Forest but robust splitting requires a large number of training samples.
Weakly Supervised Multiclass Video Segmentation
In this paper, we present a novel nearest neighbor-based label transfer scheme for weakly supervised video segmentation.
Semi-Supervised Coupled Dictionary Learning for Person Re-identification
In this paper, to bridge the human appearance variations across cameras, two coupled dictionaries that relate to the gallery and probe cameras are jointly learned in the training phase from both labeled and unlabeled images.
A Robust Point Sets Matching Method
Point sets matching method is very important in computer vision, feature extraction, fingerprint matching, motion estimation and so on.
Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).
Fully Convolutional Attention Networks for Fine-Grained Recognition
Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses.
Deep Embedding for Spatial Role Labeling
This paper introduces the visually informed embedding of word (VIEW), a continuous vector representation for a word extracted from a deep neural model trained using the Microsoft COCO data set to forecast the spatial arrangements between visual objects, given a textual description.
Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition
By designing a novel reward strategy, we are able to learn to locate regions that are spatially and semantically distinctive with reinforcement learning algorithm.
Dynamic Computational Time for Visual Attention
We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).
Deep Speaker: an End-to-End Neural Speaker Embedding System
We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity.
Kernel Pooling for Convolutional Neural Networks
We demonstrate how to approximate kernels such as Gaussian RBF up to a given order using compact explicit feature maps in a parameter-free manner.
Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding
This paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place.
Deep Metric Learning with Angular Loss
The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images.
Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
Experiment results on the challenging Kinetics dataset demonstrate that our proposed temporal modeling approaches can significantly improve existing approaches in the large-scale video recognition tasks.
Ranked #163 on
Action Classification
on Kinetics-400
Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
In this paper, however, we show that temporal information, especially longer-term patterns, may not be necessary to achieve competitive results on common video classification datasets.
Experimentally detecting a quantum change point via Bayesian inference
Detecting a change point is a crucial task in statistics that has been recently extended to the quantum realm.
CerfGAN: A Compact, Effective, Robust, and Fast Model for Unsupervised Multi-Domain Image-to-Image Translation
In principle, CerfGAN contains a novel component, i. e., a multi-class discriminator (MCD), which gives the model an extremely powerful ability to match multiple translation mappings.
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
YouTube for Patient Education: A Deep Learning Approach for Understanding Medical Knowledge from User-Generated Videos
YouTube presents an unprecedented opportunity to explore how machine learning methods can improve healthcare information dissemination.
Real-time Scholarly Retweeting Prediction System
At last, we combine scholarly features with the Tweet Scholar Blocks to predict whether a scholarly tweet will be retweeted.
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
Event extraction is of practical utility in natural language processing.
PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models
We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models.
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
Fine-grained Video Categorization with Redundancy Reduction Attention
Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.
Ranked #12 on
Action Recognition
on ActivityNet
StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
In this paper, in contrast to the existing CNN+RNN or pure 3D convolution based approaches, we explore a novel spatial temporal network (StNet) architecture for both local and global spatial-temporal modeling in videos.
Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding
Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem.
Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos
The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos.
DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features
As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days.
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.
Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks.
A Soft Label Strategy for Target-Level Sentiment Classification
In this paper, we propose a soft label approach to target-level sentiment classification task, in which a history-based soft labeling model is proposed to measure the possibility of a context word as an opinion word.
Open Domain Event Extraction Using Neural Latent Variable Models
We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters.
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Ranked #1 on
Action Recognition
on THUMOS’14
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.
Ranked #20 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
Jointly Learning Entity and Relation Representations for Entity Alignment
Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs).
Ranked #18 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
Coarse-To-Fine Visual Localization Using Semantic Compact Map
Robust visual localization for urban vehicles remains challenging and unsolved.
TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation
In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story.
Dynamic Instance Normalization for Arbitrary Style Transfer
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way.
Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently
Experimental data has revealed that in addition to feedforward connections, there exist abundant feedback connections in a neural pathway.
RIS Enhanced Massive Non-orthogonal Multiple Access Networks: Deployment and Passive Beamforming Design
A novel framework is proposed for the deployment and passive beamforming design of a reconfigurable intelligent surface (RIS) with the aid of non-orthogonal multiple access (NOMA) technology.
Artificial Intelligence Aided Next-Generation Networks Relying on UAVs
Artificial intelligence (AI) assisted unmanned aerial vehicle (UAV) aided next-generation networking is proposed for dynamic environments.
Predictions of 2019-nCoV Transmission Ending via Comprehensive Methods
Since the SARS outbreak in 2003, a lot of predictive epidemiological models have been proposed.
News-Driven Stock Prediction With Attention-Based Noisy Recurrent State Transition
Thanks to the use of attention over news events, our model is also more explainable.
Leveraging Planar Regularities for Point Line Visual-Inertial Odometry
To improve the accuracy of 3D mesh generation and localization, we propose a tightly-coupled monocular VIO system, PLP-VIO, which exploits point features and line features as well as plane regularities.
An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network
Pixel-wise operations between polarimetric images are important for processing polarization information.
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences.
TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning
This paper introduces our approach to the EmotioNet Challenge 2020.
Have you forgotten? A method to assess if machine learning models have forgotten data
In the era of deep learning, aggregation of data from several sources is a common approach to ensuring data diversity.
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences.
Using Noisy Self-Reports to Predict Twitter User Demographics
We present a method to identify self-reports of race and ethnicity from Twitter profile descriptions.
Neighborhood Matching Network for Entity Alignment
This paper presents Neighborhood Matching Network (NMN), a novel entity alignment framework for tackling the structural heterogeneity challenge.
Studying Product Competition Using Representation Learning
We show that, compared with state-of-the-art models, our approach is faster, and can produce more accurate demand forecasts and price elasticities.
Online non-convex learning for river pollution source identification
In this paper, novel gradient-based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, location, and time of a river pollution source based on downstream sensor data monitoring the pollution concentration.
Self-supervised Learning: Generative or Contrastive
As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years.
Resource Allocation for Multi-Cell IRS-Aided NOMA Networks
This paper proposes a novel framework of resource allocation in multi-cell intelligent reflecting surface (IRS) aided non-orthogonal multiple access (NOMA) networks, where an IRS is deployed to enhance the wireless service.
Reconfigurable Intelligent Surfaces: Principles and Opportunities
In this context, we provide a comprehensive overview of the state-of-the-art on RISs, with focus on their operating principles, performance evaluation, beamforming design and resource management, applications of machine learning to RIS-enhanced wireless networks, as well as the integration of RISs with other emerging technologies.
Dialogue State Induction Using Neural Latent Variable Models
Dialogue state modules are a useful component in a task-oriented dialogue system.
Disentangled Representations for Domain-generalized Cardiac Segmentation
Robust cardiac image segmentation is still an open challenge due to the inability of the existing methods to achieve satisfactory performance on unseen data of different domains.
Measuring the Biases and Effectiveness of Content-Style Disentanglement
In this paper, we conduct an empirical study to investigate the role of different biases in content-style disentanglement settings and unveil the relationship between the degree of disentanglement and task performance.
TP-LSD: Tri-Points Based Line Segment Detector
To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment.
Ranked #2 on
Line Segment Detection
on York Urban Dataset
Machine Learning Empowered Trajectory and Passive Beamforming Design in UAV-RIS Wireless Networks
The energy consumption minimizing problem is formulated by jointly designing the movement of the UAV, phase shifts of the RIS, power allocation policy from the UAV to MUs, as well as determining the dynamic decoding order.
Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
We discover that pixel normalization causes object entanglement by in-painting the area occupied by ablated objects.
Multi-Agent Reinforcement Learning in NOMA-aided UAV Networks for Cellular Offloading
Afterward, a mutual deep Q-network (MDQN) algorithm is proposed to jointly determine the optimal 3D trajectory and power allocation of UAVs.
NOMA in UAV-aided cellular offloading: A machine learning approach
A novel framework is proposed for cellular offloading with the aid of multiple unmanned aerial vehicles (UAVs), while non-orthogonal multiple access (NOMA) technique is employed at each UAV to further improve the spectrum efficiency of the wireless network.
Diversity in immunogenomics: the value and the challenge
With the advent of high-throughput sequencing technologies, the fields of immunogenomics and adaptive immune receptor repertoire research are facing both opportunities and challenges.
Language Models are Open Knowledge Graphs
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e. g., BERT, GPT-2/3), without human supervision.
Path Design and Resource Management for NOMA enhanced Indoor Intelligent Robots
Our simulation results demonstrate that 1) With the aid of NOMA techniques, the communication reliability of IRs is effectively improved; 2) The radio map is qualified to be a virtual training environment, and its statistical channel state information improves training efficiency by about 30%; 3) The proposed DT-DPG algorithm is superior to the conventional deep deterministic policy gradient (DDPG) algorithm in terms of optimization performance, training time, and anti-local optimum ability.
Intelligent Reflecting Surface Aided Multi-Cell NOMA Networks
This paper proposes a novel framework of resource allocation in intelligent reflecting surface (IRS) aided multi-cell non-orthogonal multiple access (NOMA) networks, where a sum-rate maximization problem is formulated.
Robotic Communications for 5G and Beyond: Challenges and Research Opportunities
Furthermore, dynamic trajectory design and resource allocation for both indoor and outdoor robots are provided to verify the performance of robotic communications in the context of typical robotic application scenarios.
Robotics Systems and Control Signal Processing Systems and Control
SID-NISM: A Self-supervised Low-light Image Enhancement Framework
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms.
Unbox the Blackbox: Predict and Interpret YouTube Viewership Using Deep Learning
Although deep learning champions viewership prediction, it lacks interpretability, which is fundamental to increasing the adoption of predictive models and prescribing measurements to improve viewership.
News-Driven Stock Prediction Using Noisy Equity State Representation
News-driven stock prediction investigates the correlation between news events and stock price movements.
Integrated 3C in NOMA-enabled Remote-E-Health Systems
A novel framework is proposed to integrate communication, control and computing (3C) into the fifth-generation and beyond (5GB) wireless networks for satisfying the ultra-reliable low-latency connectivity requirements of remote-e-Health systems.
Improved Signed Distance Function for 2D Real-time SLAM and Accurate Localization
In this paper, we propose an improved Signed Distance Function (SDF) for both 2D SLAM and pure localization to improve the accuracy of mapping and localization.
Artificial Intelligence Driven UAV-NOMA-MEC in Next Generation Wireless Networks
To this end, the fundamentals of this framework are first introduced.
GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.
Artificial Intelligence Enhanced Rapid and Efficient Diagnosis of Mycoplasma Pneumoniae Pneumonia in Children Patients
Artificial intelligence methods have been increasingly turning into a potentially powerful tool in the diagnosis and management of diseases.
A Novel Graph-based Computation Offloading Strategy for Workflow Applications in Mobile Edge Computing
To achieve better Quality of Service (QoS), for instance, faster response time and lower energy consumption, computation offloading is widely used in the MEC environment.
Edge-computing
Distributed, Parallel, and Cluster Computing
C.2.4
OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services
Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools.
Understanding WeChat User Preferences and "Wow" Diffusion
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning
Social and Information Networks
GPT Understands, Too
Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU).
GLM: General Language Model Pretraining with Autoregressive Blank Infilling
On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1. 25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.
Ranked #4 on
Language Modelling
on WikiText-103
(using extra training data)
Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
To begin with, the pre-trained denoiser is used to generate the pseudo clean images for the test images.
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Causal inference is the process of capturing cause-effect relationship among variables.
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Ranked #4 on
Image Inpainting
on CelebA-HQ
ELSD: Efficient Line Segment Detector and Descriptor
The line description ability of ELSD also outperforms the previous works on the line matching task.
Ranked #1 on
Line Segment Detection
on wireframe dataset
ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021
This report presents a brief description of our method for the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2021.
3rd Place Solution for Short-video Face Parsing Challenge
Benefiting from the edge information and edge attention loss, the proposed EANet achieves 86. 16\% accuracy in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the third place.
Pre-Trained Models: Past, Present and Future
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
A Self-supervised Method for Entity Alignment
We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs.
Multi-Granularity Network with Modal Attention for Dense Affective Understanding
Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation.
Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
We explicitly model the representations related to domain shifts.
1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition
In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021.
Boost-R: Gradient Boosted Trees for Recurrence Data
Boost-R constructs an ensemble of gradient boosted additive trees to estimate the cumulative intensity function of the recurrent event process, where a new tree is added to the ensemble by minimizing the regularized L2 distance between the observed and predicted cumulative intensity.
Controllable cardiac synthesis via disentangled anatomy arithmetic
Motivated by the ability to disentangle images into spatial anatomy (tensor) factors and accompanying imaging (vector) representations, we propose a framework termed "disentangled anatomy arithmetic", in which a generative model learns to combine anatomical factors of different input images such that when they are re-entangled with the desired imaging modality (e. g. MRI), plausible new cardiac images are created with the target characteristics.
Gaze Estimation with an Ensemble of Four Architectures
This paper presents a method for gaze estimation according to face images.
Unsupervised Neural Rendering for Image Hazing
To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i. e., unpaired real hazy images.
Locality-aware Channel-wise Dropout for Occluded Face Recognition
Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.
Rethinking Hard-Parameter Sharing in Multi-Domain Learning
One common sharing practice is to share the bottom layers of a deep neural network among domains while using separate top layers for each domain.
Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e. g., "dog $\to$ play $\to$ ball" in semantic structure for an image, and (ii) seeking explicit inter-modal structural and semantic correspondence between the visual and textual modalities.
UniCon: Unified Context Network for Robust Active Speaker Detection
Our solution is a novel, unified framework that focuses on jointly modeling multiple types of contextual information: spatial context to indicate the position and scale of each candidate's face, relational context to capture the visual relationships among the candidates and contrast audio-visual affinities with each other, and temporal context to aggregate long-term information and smooth out local uncertainties.
SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
Method Towards CVPR 2021 SimLocMatch Challenge
This report describes Megvii-3D team's approach towards SimLocMatch Challenge @ CVPR 2021 Image Matching Workshop.
Method Towards CVPR 2021 Image Matching Challenge
This report describes Megvii-3D team's approach towards CVPR 2021 Image Matching Workshop.
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
It simply encourages the variation of output caused by perturbations on different latent dimensions to be orthogonal, and the Jacobian with respect to the input is calculated to represent this variation.
Learning Disentangled Representations in the Imaging Domain
Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision.
LOF: Structure-Aware Line Tracking based on Optical Flow
Lines provide the significantly richer geometric structural information about the environment than points, so lines are widely used in recent Visual Odometry (VO) works.
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
We cast a suite of information extraction tasks into a text-to-triple translation framework.
Ranked #1 on
Open Information Extraction
on OIE2016
(using extra training data)
Learning the Representation of Behavior Styles with Imitation Learning
Imitation learning is one of the methods for reproducing expert demonstrations adaptively by learning a mapping between observations and actions.
P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training.
Deep Point Cloud Normal Estimation via Triplet Learning
It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector.
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
The first challenge is to determine what parameters to share across tasks to optimize for both memory efficiency and task accuracy.
Meta-learning for RIS-assisted NOMA Networks
Extensive simulation results demonstrate that the proposed QoS-based NOMA network achieves significantly higher transmission throughput compared to the conventional orthogonal multiple access (OMA) network.
Using Deep Learning to Identify Patients with Cognitive Impairment in Electronic Health Records
Automated mining of these notes presents an opportunity to label patients with cognitive impairment in EHR data.
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression
This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters.
MegLoc: A Robust and Accurate Visual Localization Pipeline
In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years.
TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images.
Ranked #8 on
3D Reconstruction
on DTU
Learning with Noisy Correspondence for Cross-modal Matching
Based on this observation, we reveal and study a latent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisy labels.
MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment
Large-scale Bundle Adjustment (BA) requires massive memory and computation resources which are difficult to be fulfilled by existing BA libraries.
All-in-One Image Restoration for Unknown Corruption
In this paper, we study a challenging problem in image restoration, namely, how to develop an all-in-one method that could recover images from a variety of unknown corruption types and levels.
3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning
While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data.
NeuraHealth: An Automated Screening Pipeline to Detect Undiagnosed Cognitive Impairment in Electronic Health Records with Deep Learning and Natural Language Processing
Dementia related cognitive impairment (CI) is a neurodegenerative disorder, affecting over 55 million people worldwide and growing rapidly at the rate of one new case every 3 seconds.
SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs
We present SelfKG with efficient strategies to optimize this objective for aligning entities without label supervision.
Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation
Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies.
Syntax-Aware Network for Handwritten Mathematical Expression Recognition
In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network.
Automatic Facial Paralysis Estimation with Facial Action Units
In this paper, we propose a novel Adaptive Local-Global Relational Network (ALGRNet) for facial AU detection and use it to classify facial paralysis severity.
A Tree-Structured Multi-Task Model Recommender
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL).
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
We probe PLMs and models with visual signals, including vision-language pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.
Privacy-Preserving Personalized Fitness Recommender System (P3FitRec): A Multi-level Deep Learning Approach
Recommender systems have been successfully used in many domains with the help of machine learning algorithms.
MGRR-Net: Multi-level Graph Relational Reasoning Network for Facial Action Units Detection
While the region-level feature learning from local face patches features via graph neural network can encode the correlation across different AUs, the pixel-wise and channel-wise feature learning via graph attention network can enhance the discrimination ability of AU features from global face features.
Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Semantic image synthesis is a challenging task with many practical applications.
Dynamic Prefix-Tuning for Generative Template-based Event Extraction
We consider event extraction in a generative manner with template-based conditional generation.
DeepStruct: Pretraining of Language Models for Structure Prediction
We introduce a method for improving the structural understanding abilities of language models.
Ranked #1 on
Open Information Extraction
on Penn Treebank
GraphMAE: Self-Supervised Masked Graph Autoencoders
Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields.
Ranked #1 on
Node Classification
on Cora: fixed 20 node per class
Improving Subgraph Representation Learning via Multi-View Augmentation
Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-property relationships and collective cellular function.
Regression Trees on Grassmann Manifold for Adapting Reduced-Order Models
When a ROM, constructed using the POD basis obtained from training data, is applied to new parameter settings, the model often lacks robustness against the change of parameters in design, control, and other real-time operation problems.
Physics-Informed Statistical Modeling for Wildfire Aerosols Process Using Multi-Source Geostationary Satellite Remote-Sensing Data Streams
Increasingly frequent wildfires significantly affect solar energy production as the atmospheric aerosols generated by wildfires diminish the incoming solar radiation to the earth.
Why patient data cannot be easily forgotten?
With the advent of AI learned on data, one can imagine that such rights can extent to requests for forgetting knowledge of patient's data within AI models.
vMFNet: Compositionality Meets Domain-generalised Segmentation
Moreover, with a reconstruction module, unlabeled data can also be used to learn the vMF kernels and likelihoods by recombining them to reconstruct the input image.
On Curating Responsible and Representative Healthcare Video Recommendations for Patient Education and Health Literacy: An Augmented Intelligence Approach
Studies suggest that one in three US adults use the Internet to diagnose or learn about a health concern.
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
By updating only 0. 1% of the model parameters, the prompt tuning strategy can help retrieval models achieve better generalization performance than traditional methods in which all parameters are updated.
BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion
During deployment, we combine the offline RL model with the LP model to generate a robust policy under the budget constraints.
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.
What is Healthy? Generative Counterfactual Diffusion for Lesion Localization
This requires training with healthy and unhealthy data in DPMs.
HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information
Maximisation of mutual information is achieved by introducing an auxiliary network and training with a latent regression loss.
Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries
In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies.
Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer
Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems.
PROD: Progressive Distillation for Dense Retrieval
It is common that a better teacher model results in a bad student via distillation due to the nonnegligible gap between teacher and student.
GLM-130B: An Open Bilingual Pre-trained Model
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.
Ranked #1 on
Language Modelling
on CLUE (OCNLI_50K)
Uplifting Message Passing Neural Network with Graph Original Information
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and have shown astonishing improvement in node classification tasks.
Ranked #5 on
Node Classification
on arXiv-year
HEGEL: Hypergraph Transformer for Long Document Summarization
Extractive summarization for long documents is challenging due to the extended structured input context.
Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient
Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Diffusion Models for Causal Discovery via Topological Ordering
We introduce theory for updating the learned Hessian without re-training the neural network, and we show that computing with a subset of samples gives an accurate approximation of the ordering, which allows scaling to datasets with more samples and variables.
Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario
Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way.
SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval
Thus, we propose a simple ambiguous negatives sampling method, SimANS, which incorporates a new sampling probability distribution to sample more ambiguous negatives.
IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models
Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs.
Does Debiasing Inevitably Degrade the Model Performance
We use our theoretical framework to explain why the current debiasing methods cause performance degradation.
Reason from Context with Self-supervised Learning
To better accommodate the object-centric nature of current downstream tasks such as object recognition and detection, various methods have been proposed to suppress contextual biases or disentangle objects from contexts.
Imperceptible Adversarial Attack via Invertible Neural Networks
Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples.
ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information
ClueWeb22, the newest iteration of the ClueWeb line of datasets, provides 10 billion web pages affiliated with rich information.
LEAD: Liberal Feature-based Distillation for Dense Retrieval
Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model.
An adaptive human-in-the-loop approach to emission detection of Additive Manufacturing processes and active learning with computer vision
More specifically, this paper will look at two scenarios: firstly, using convolutional neural networks (CNNs) to automatically inspect and classify emission data collected by in-situ monitoring and secondly, applying Active Learning techniques to the developed classification model to construct a human-in-the-loop mechanism in order to accelerate the labeling process of the emission data.
MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense vectors.
Inverse Models for Estimating the Initial Condition of Spatio-Temporal Advection-Diffusion Processes
The irregular sampling scheme is the general scenario, while computationally efficient solutions are available in the spectral domain for non-uniform and shifted uniform sampling.
Extractive Summarization via ChatGPT for Faithful Summary Generation
In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance.
GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner
Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data.
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
We present a comprehensive solution to learn and improve text-to-image models from human preference feedback.
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention
We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.
Ranked #1 on
Dialog Relation Extraction
on DialogRE
DiffuSum: Generation Enhanced Extractive Summarization with Diffusion
This paper proposes DiffuSum, a novel paradigm for extractive summarization, by directly generating the desired summary sentence representations with diffusion models and extracting sentences based on sentence representation matching.
Weighted Point Cloud Normal Estimation
Existing normal estimation methods for point clouds are often less robust to severe noise and complex geometric structures.
Unsupervised Dense Retrieval Training with Web Anchors
Based on their commonalities, we train an unsupervised dense retriever, Anchor-DR, with a contrastive learning task that matches the anchor text and the linked document.
AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance.
Boosting Event Extraction with Denoised Structure-to-Text Augmentation
Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations.
Multi-Task Models Adversarial Attacks
We then introduce a novel attack framework, the Gradient Balancing Multi-Task Attack (GB-MTA), which treats attacking a multi-task model as an optimization problem.
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses.
Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds
While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds.
Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration
We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW), which extends the maximum context lengths of language models, e. g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques.
SummIt: Iterative Text Summarization via ChatGPT
Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step.
Allies: Prompting Large Language Model with Beam Search
With the advance of large language models (LLMs), the research field of LLM applications becomes more and more popular and the idea of constructing pipelines to accomplish complex tasks by stacking LLM API calls come true.
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking.
Contrastive Hierarchical Discourse Graph for Scientific Document Summarization
The extended structural context has made scientific paper summarization a challenging task.
How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension
We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances.
WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM).
Compositionally Equivariant Representation Learning
By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings.
FLGo: A Fully Customizable Federated Learning Platform
Federated learning (FL) has found numerous applications in healthcare, finance, and IoT scenarios.
Random Walk on Multiple Networks
To take advantage of rich information in multiple networks and make better inferences on entities, in this study, we propose random walk on multiple networks, RWM.
LPN: Language-guided Prototypical Network for few-shot classification
Few-shot classification aims to adapt to new tasks with limited labeled examples.
Language-free Compositional Action Generation via Decoupling Refinement
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation.
Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing
The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process.
Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields
Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e. g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minutes but suffers from blurring or aliasing when rendering at various distances or resolutions due to ignoring the sampling area.
Random Sub-Samples Generation for Self-Supervised Real Image Denoising
With sufficient paired training samples, the supervised deep learning methods have attracted much attention in image denoising because of their superior performance.
AgentBench: Evaluating LLMs as Agents
We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.
Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer
To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner.
Ranked #1 on
Video Question Answering
on SUTD-TrafficQA
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding.
