Search Results for author:
Found 434 papers, 133 papers with code
融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition)
“在汉语等其他有省略代词习惯的语言中, 通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功, 但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型, 并引入篇章上下文来丰富指代信息。具体地, 该模型采用联合学习的框架, 在翻译模型基础上, 联合了一个分类任务, 即判别句子中省略代词在句子所表示的成分, 使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验, 验证了本文提出方法的有效性, 与基准模型相比, 翻译性能提升了1. 48个BLEU值。”
Toward Knowledge-Enriched Conversational Recommendation Systems
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
Non-Intrusive Load Monitoring for Feeder-Level EV Charging Detection: Sliding Window-based Approaches to Offline and Online Detection
Our experimental results demonstrate high-accuracy EV charging detection at the feeder level, achieving an F-Score of 98. 88% in offline detection and 93. 01% in online detection.
PAC Privacy Preserving Diffusion Models
Data privacy protection is garnering increased attention among researchers.
Quantum Langevin Dynamics for Optimization
Finally, based on the observations when comparing QLD with classical Fokker-Plank-Smoluchowski equation, we propose a time-dependent QLD by making temperature and $\hbar$ time-dependent parameters, which can be theoretically proven to converge better than the time-independent case and also outperforms a series of state-of-the-art quantum and classical optimization algorithms in many non-convex landscapes.
Eliminating Domain Bias for Federated Learning in Representation Space
Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities.
How Far Have We Gone in Vulnerability Detection Using Large Language Models
Given the significant successes of Large Language Models (LLMs) in various tasks, there is growing anticipation of their efficacy in vulnerability detection.
On the Noise Scheduling for Generating Plausible Designs with Diffusion Models
We delve into the impact of noise schedules of diffusion models on the plausibility of the outcome: there exists a range of noise levels at which the model's performance decides the result plausibility.
Enhancing Recommender System Performance by Histogram Equalization
As a preprocessing step to recommender system algorithms, histogram equalization could enhance both the accuracy and fairness metrics of the recommender system algorithms.
SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training
Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions.
APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation
To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.
ProAgent: From Robotic Process Automation to Agentic Process Automation
Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents.
Pre-trained Recommender Systems: A Causal Debiasing Perspective
In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data).
Is Human Culture Locked by Evolution?
Human culture has evolved for thousands of years and thrived in the era of Internet.
Self-Supervised Multi-Modality Learning for Multi-Label Skin Lesion Classification
The clinical diagnosis of skin lesion involves the analysis of dermoscopic and clinical modalities.
Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling
Multi-view or even multi-modal data is appealing yet challenging for real-world applications.
Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning
For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the generative paradigm and learns to reconstruct masked graph edges or node features.
Woodpecker: Hallucination Correction for Multimodal Large Language Models
Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content.
Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learning
Extracting meaningful entities belonging to predefined categories from Visually-rich Form-like Documents (VFDs) is a challenging task.
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game.
DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading
The use of visually-rich documents (VRDs) in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers.
A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems
Recommendation systems effectively guide users in locating their desired information within extensive content repositories.
Fact-based Agent modeling for Multi-Agent Reinforcement Learning
To eliminate this assumption and achieve agent modeling in unknown scenarios, Fact-based Agent modeling (FAM) method is proposed in which fact-based belief inference (FBI) network models other agents in partially observable environment only based on its local information.
Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control
Over the years, reinforcement learning has emerged as a popular approach to develop signal control and vehicle platooning strategies either independently or in a hierarchical way.
Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning
In this paper, we propose a joint optimization approach for traffic signal control and vehicle routing in signalized road networks.
Private Synthetic Data Meets Ensemble Learning
When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and real data.
B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
LAiW: A Chinese Legal Large Language Models Benchmark (A Technical Report)
We have completed the first phase of evaluation, which mainly focuses on the capability of basic legal NLP.
Continuous Invariance Learning
To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains.
Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models
We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks.
LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud
In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves.
Deep Learning-Based Connector Detection for Robotized Assembly of Automotive Wire Harnesses
The mating of connectors is essential in the final assembly of automotive wire harnesses due to the importance of connectors on wire harness connection and signal transmission.
A Systematic Literature Review of Computer Vision Applications in Robotized Wire Harness Assembly
This article presents a systematic literature review on computer vision applications that have been proposed for robotized wire harness assembly, derives challenges from existing studies, and identifies opportunities for future research to promote a more practical robotized assembly of wire harnesses.
Computer Vision Technology for Robotized Wire Harness Assembly
This paradigm shift places more demand on automotive wiring harnesses from the safety perspective and stresses the greater importance of high-quality wire harness assembly in vehicles.
Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
Time-Series Forecasting based on Cumulative Data (TSFCD) is a crucial problem in decision-making across various industrial scenarios.
SPGM: Prioritizing Local Features for enhanced speech separation performance
Dual-path is a popular architecture for speech separation models (e. g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships.
Collaborative Three-Stream Transformers for Video Captioning
Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions.
Community Battery Energy Storage Systems for Enhancing Distribution System Operation: A Multi-objective Optimization Approach
The results show significant improvements in voltage regulation and DER utilization, demonstrating the potential of C-BESS in enabling more reliable DN operation.
Cross-Entropy-Based Approach to Multi-Objective Electric Vehicle Charging Infrastructure Planning
Therefore, we are motivated to develop a comprehensive multi-objective framework for optimal CS placement in a traffic network overlaid by a distribution network, considering multiple stakeholders' interested factors, such as traffic flow, PEV charging time cost, PEV travel distance, and the reliability of the distribution network.
Hybrid Transformer-RNN Architecture for Household Occupancy Detection Using Low-Resolution Smart Meter Data
Residential occupancy detection has become an enabling technology in today's urbanized world for various smart home applications, such as building automation, energy management, and improved security and comfort.
MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange
This paper addresses the EV charging coordination by considering vehicle-to-vehicle (V2V) energy exchange as the flexibility to harness in EV charging stations.
kTrans: Knowledge-Aware Transformer for Binary Code Embedding
By feeding explicit knowledge as additional inputs to the Transformer, and fusing implicit knowledge with a novel pre-training task, kTrans provides a new perspective to incorporating domain knowledge into a Transformer framework.
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities.
ChatHaruhi: Reviving Anime Character in Reality via Large Language Model
Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters.
KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
However, the multi-faceted semantic orientation in the feature-semantic alignment has been neglected by previous work, i. e. the content of a node usually covers diverse topics that are relevant to the semantics of multiple labels.
Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey
Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market.
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices.
ConvFormer: Revisiting Transformer for Sequential User Modeling
Sequential user modeling, a critical task in personalized recommender systems, focuses on predicting the next item a user would prefer, requiring a deep understanding of user behavior sequences.
A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation
In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation?"
MFMAN-YOLO: A Method for Detecting Pole-like Obstacles in Complex Environment
To solve the problem that the feature information of pole-like obstacles in complex environments is easily lost, resulting in low detection accuracy and low real-time performance, a multi-scale hybrid attention mechanism detection algorithm is proposed in this paper.
Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesis
The potential of SA-ALAE is shown by generating engineering blueprints in a real automotive design task.
Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation
And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP).
Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging
Unlike traditional neural fields frameworks, LCNF incorporates a local conditional representation that promotes model generalization, learning multiscale information, and efficient processing of large-scale imaging data.
LogitMat : Zeroshot Learning Algorithm for Recommender Systems without Transfer Learning or Pretrained Models
Unlike other sectors such as fraud detection in the Fintech industry, recommender system is both deep and broad.
Optimal Bandwidth Selection for DENCLUE Algorithm
In 2007, a density-based clustering algorithm named DENCLUE was invented to solve clustering problem for nonlinear data structures.
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively.
Counterfactual Collaborative Reasoning
In this paper, we explore how the two reasoning abilities can be jointly modeled to enhance both accuracy and explainability of machine learning models.
Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networks
We introduce a novel Bayesian neural network-based architecture to estimate inter-rater uncertainty in medical image segmentation.
PMaF: Deep Declarative Layers for Principal Matrix Features
We explore two differentiable deep declarative layers, namely least squares on sphere (LESS) and implicit eigen decomposition (IED), for learning the principal matrix features (PMaF).
Energy Optimization for HVAC Systems in Multi-VAV Open Offices: A Deep Reinforcement Learning Approach
It takes only a total of 40 minutes for 5 epochs (about 7. 75 minutes per epoch) to train a network with superior performance and covering diverse conditions for its low-complexity architecture; therefore, it easily adapts to changes in the building setups, weather conditions, occupancy rate, etc.
Taxonomy-Structured Domain Adaptation
Domain adaptation aims to mitigate distribution shifts among different domains.
Skellam Rank: Fair Learning to Rank Algorithm Based on Poisson Process and Skellam Distribution for Recommender Systems
In this paper, we propose a fair recommender system algorithm that uses Poisson process and Skellam distribution.
Self-Interpretable Time Series Prediction with Counterfactual Explanations
Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving.
A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions
In this work, we propose a novel peer-to-peer federated continual learning strategy to improve low-dose CT imaging performance from multiple institutions.
Representation Reliability and Its Impact on Downstream Tasks
Self-supervised pre-trained models extract general-purpose representations from data, and quantifying how reliable they are is crucial because many downstream models use these representations as input for their own tasks.
A Survey on Large Language Models for Recommendation
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS).
DPFormer: Learning Differentially Private Transformer on Long-Tailed Data
The Transformer has emerged as a versatile and effective architecture with broad applications.
Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts
Accurate estimation of multiple quality variables is critical for building industrial soft sensor models, which have long been confronted with data efficiency and negative transfer issues.
Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models
To solve this problem, we construct the first Classical-Chinese-to-Kanbun dataset in the world.
MaGIC: Multi-modality Guided Image Completion
In this paper, we propose a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance (e. g., text, canny edge, sketch, segmentation, depth, and pose), but also adapts to arbitrarily customized combination of these modalities (i. e., arbitrary multi-modality) for image completion.
Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes
In particular, we adopt a self-developed broadband intelligent communication system 40MHz-Net (BICT-40N) terminal in order to fully acquire the channel information.
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
The exploration problem is one of the main challenges in deep reinforcement learning (RL).
Ranked #1 on
Atari Games
on Atari-57
Self-discipline on multiple channels
Comparative experimental results on both datasets show that SMC-2 outperforms Label Smoothing Regularizaion and Self-distillation From The Last Mini-batch on all models, and outperforms the state-of-the-art Sharpness-Aware Minimization method on 83% of the models. Compatibility of SMC-2 and data augmentation experimental results show that using both SMC-2 and data augmentation improves the generalization ability of the model between 0. 28% and 1. 80% compared to using only data augmentation.
A Reinforcement Learning-assisted Genetic Programming Algorithm for Team Formation Problem Considering Person-Job Matching
The RL-GP adopts the ensemble population strategies.
Fairness-Aware Optimization of Vehicle-to-Vehicle Interaction for Smart EV Charging Coordination
We formulate a cost minimization problem for an EV charging station to optimize the V2V schedule together with vehicle-to-grid (V2G), grid-to-vehicle (G2V) charging, as well as the use of renewable energy.
Network-Aware Electric Vehicle Coordination for Vehicle-to-Anything Value Stacking Considering Uncertainties
The EV coordination can provide value to the grid and generate benefits for EVs.
Optimal Energy Storage Scheduling for Wind Curtailment Reduction and Energy Arbitrage: A Deep Reinforcement Learning Approach
However, the variable nature of wind generation can undermine system reliability and lead to wind curtailment, causing substantial economic losses to wind power producers.
StarNet: Style-Aware 3D Point Cloud Generation
This paper investigates an open research task of reconstructing and generating 3D point clouds.
Evolution of the Online Rating Platform Data Structures and its Implications for Recommender Systems
Understanding the evolution pattern and its underlying mechanism is the key to understand the structures of input data for recommender systems.
Analysis and Visualization of the Parameter Space of Matrix Factorization-based Recommender Systems
We continue the research in this direction in this paper, and visualize the inner structure of the parameter space of matrix factorization technologies.
TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
We conduct extensive experiments to analyze each of our proposed components and show the efficacy of our framework in generating high-fidelity 3D textured and text-relevant shapes.
Distribution-restrained Softmax Loss for the Model Robustness
Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on.
A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide Images
These SSL approaches, however, are not designed for handling multi-resolution WSIs, which limits their performance in learning discriminative image features.
Betti Number for Point Sets
Topology is the foundation for many industrial applications ranging from CAD to simulation analysis.
PowerMat: context-aware recommender system without user item rating values that solves the cold-start problem
One important sub-field of recommender systems that has been stagnating is context-aware recommender systems.
Kernel-CF: Collaborative filtering done right with social network analysis and kernel smoothing
Collaborative filtering is the simplest but oldest machine learning algorithm in the field of recommender systems.
Effective Visualization and Analysis of Recommender Systems
Recommender system exists everywhere in the business world.
GUESR: A Global Unsupervised Data-Enhancement with Bucket-Cluster Sampling for Sequential Recommendation
Sequential Recommendation is a widely studied paradigm for learning users' dynamic interests from historical interactions for predicting the next potential item.
Hierarchical Fuel-Cell Airpath Control: an Efficiency-Aware MIMO Control Approach Combined with a Novel Constraint-Enforcing Reference Governor
Compared with a single-input single-output (SISO) air-flow control approach, the proposed MIMO control approach shows up to 7. 36 percent lower hydrogen fuel consumption.
TMoE-P: Towards the Pareto Optimum for Multivariate Soft Sensors
We further present a Task-aware Mixture-of-Experts framework for achieving the Pareto optimum (TMoE-P) in multi-variate soft sensor, which consists of a stacked OMoE module and a POR module.
AttentionMixer: An Accurate and Interpretable Framework for Process Monitoring
An accurate and explainable automatic monitoring system is critical for the safety of high efficiency energy conversion plants that operate under extreme working condition.
To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features
These features are then used to predict what algorithm to switch to.
Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
To address this challenge, we first provide a formal definition of domain index from the probabilistic perspective, and then propose an adversarial variational Bayesian framework that infers domain indices from multi-domain data, thereby providing additional insight on domain relations and improving domain adaptation performance.
Cross-Frequency Time Series Meta-Forecasting
Meta-forecasting is a newly emerging field which combines meta-learning and time series forecasting.
Benchmarking Algorithms for Submodular Optimization Problems Using IOHProfiler
Submodular functions play a key role in the area of optimization as they allow to model many real-world problems that face diminishing returns.
Real-Time High-Resolution Pedestrian Detection in Crowded Scenes via Parallel Edge Offloading
To identify dense and small-size pedestrians in surveillance systems, high-resolution cameras are widely deployed, where high-resolution images are captured and delivered to off-the-shelf pedestrian detection models.
Fair Recommendation by Geometric Interpretation and Analysis of Matrix Factorization
Matrix factorization-based recommender system is in effect an angle preserving dimensionality reduction technique.
More is Better: A Database for Spontaneous Micro-Expression with High Frame Rates
To solve the problem of ME data hunger, we construct a dynamic spontaneous ME dataset with the largest current ME data scale, called DFME (Dynamic Facial Micro-expressions), which includes 7, 526 well-labeled ME videos induced by 671 participants and annotated by more than 20 annotators throughout three years.
Deep Reinforcement Learning for Wind and Energy Storage Coordination in Wholesale Energy and Ancillary Service Markets
Simulations also show that using curtailed wind generation as a power source for charging the BESS can lead to additional financial gains.
First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting
Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.
Proximal Policy Optimization Based Reinforcement Learning for Joint Bidding in Energy and Frequency Regulation Markets
Driven by the global decarbonization effort, the rapid integration of renewable energy into the conventional electricity grid presents new challenges and opportunities for the battery energy storage system (BESS) participating in the energy market.
Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning
This paper investigates reinforcement learning, which gradually optimizes a fair PV curtailment strategy by interacting with the system.
Robust Perception through Equivariance
In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference.
Complete cavity map of the C. elegans connectome
This study reports for the first time a complete cavity map of C. elegans neural network, developing a new method for mining higher-order structures that can be applied by researchers in neuroscience, network science and other interdisciplinary fields to explore higher-order structural markers of complex systems.
PoissonMat: Remodeling Matrix Factorization using Poisson Distribution and Solving the Cold Start Problem without Input Data
Matrix Factorization is one of the most successful recommender system techniques over the past decade.
Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems
Famous algorithms such as Bayesian Personalized Ranking and Collaborative Less is More Filtering have left deep impact in both academia and industry.
AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data
In tunnel boring machine (TBM) underground projects, an accurate description of the rock-soil types distributed in the tunnel can decrease the construction risk ({\it e. g.} surface settlement and landslide) and improve the efficiency of construction.
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client.
The Monocular Depth Estimation Challenge
This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset.
The Hypervolume Indicator Hessian Matrix: Analytical Expression, Computational Time Complexity, and Sparsity
Also, for the general $m$-dimensional case, a compact recursive analytical expression is established, and its algorithmic implementation is discussed.
Fast Key Points Detection and Matching for Tree-Structured Images
The proposed algorithm is applicable to a variety of tree-structured image matching, but our focus is on dendrites, recently-developed visual identifiers.
R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents.
Federated Unlearning for On-Device Recommendation
It removes a user's contribution by rolling back and calibrating the historical parameter updates and then uses these updates to speed up federated recommender reconstruction.
Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications
As a basic research problem for building effective recommender systems, post-click conversion rate (CVR) estimation has long been plagued by sample selection bias and data sparsity issues.
Visual Prompt Tuning for Test-time Domain Adaptation
First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation.
Ranked #2 on
Domain Adaptation
on VisDA2017
1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)
Recent years have seen advances on principles and guidance relating to accountable and ethical use of artificial intelligence (AI) spring up around the globe.
ManiCLIP: Multi-Attribute Face Manipulation from Text
In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.
Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning
Automaton based approaches have enabled robots to perform various complex tasks.
Insurance Contract for High Renewable Energy Integration
A proper insurance design needs to resolve the following two challenges: (i) users' reliability preference is private information; and (ii) the insurance design is tightly coupled with the renewable energy investment decision.
LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images
Specifically, a channel separation-aggregation (CSA) structure is designed to simplify the complexity of stacked separable convolutions, and a dynamic receptive field (DRF) mechanism is developed to maintain high accuracy by customizing the convolution kernel and its perception range dynamically when reducing the network complexity.
Model Inversion Attacks against Graph Neural Networks
One famous privacy attack against data analysis models is the model inversion attack, which aims to infer sensitive data in the training dataset and leads to great privacy concerns.
Multi-Grained Angle Representation for Remote Sensing Object Detection
The existing AOOD methods face the challenges of ambiguity and high costs in angle representation.
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
We hope that this project will be the foundation of Chinese cognitive intelligence.
Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students
To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps.
Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
However, the inconsistent features for the localization and classification tasks in AOOD models may lead to ambiguity and low-quality object predictions, which constrains the detection performance.
Few-shot Incremental Event Detection
In practice, however, the lack of high-quality labeled data of new event classes makes it difficult to obtain enough data for model training.
IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verification
Then we integrate the multi-view contextual information to encode the evidence sentences to handle the task.
Soft MIMO Detection Using Marginal Posterior Probability Statistics
Soft demodulation of received symbols into bit log-likelihood ratios (LLRs) is at the very heart of multiple-input-multiple-output (MIMO) detection.
Online Learning Based NLOS Ranging Error Mitigation in 5G Positioning
The fifth-generation (5G) wireless communication is useful for positioning due to its large bandwidth and low cost.
Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation
Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i. e., iterative local computing + multi-round communications) of mobile devices in FL.
Image Quality Assessment with Gradient Siamese Network
In this work, we introduce Gradient Siamese Network (GSN) for image quality assessment.
A Screening Strategy for Structured Optimization Involving Nonconvex $\ell_{q,p}$ Regularization
In this paper, we develop a simple yet effective screening rule strategy to improve the computational efficiency in solving structured optimization involving nonconvex $\ell_{q, p}$ regularization.
Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval
When we do online paired data augmentation, we first generate augmented text through random token replacement, then pass the augmented text into the latent space alignment module to output the latent codes, which are finally fed to StyleGAN2 to generate the augmented images.
3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image
To this end, we discover the semantic meanings of StyleGAN latent space, such that we are able to produce face images of various expressions, poses, and lighting by controlling the latent codes.
Subgraph Frequency Distribution Estimation using Graph Neural Networks
Small subgraphs (graphlets) are important features to describe fundamental units of a large network.
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.
Ranked #1 on
Earth Surface Forecasting
on EarthNet2021 OOD Track
Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review
The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence.
Winning the CVPR'2022 AQTC Challenge: A Two-stage Function-centric Approach
Affordance-centric Question-driven Task Completion for Egocentric Assistant(AQTC) is a novel task which helps AI assistant learn from instructional videos and scripts and guide the user step-by-step.
Landscape Learning for Neural Network Inversion
Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics.
Beyond Adult and COMPAS: Fairness in Multi-Class Prediction
We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks.
DotMat: Solving Cold-start Problem and Alleviating Sparsity Problem for Recommender Systems
Cold-start and sparsity problem are two key intrinsic problems to recommender systems.
DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography
Digital holography is a 3D imaging technique by emitting a laser beam with a plane wavefront to an object and measuring the intensity of the diffracted waveform, called holograms.
Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems
Regularization is a popular technique to solve the overfitting problem of machine learning algorithms.
Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization
This work provides the exact expression of the probability distribution of the hypervolume improvement (HVI) for bi-objective generalization of Bayesian optimization.
"My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics
In this paper, we explore how to bring interpretability to data-driven DSMD.
High Dimensional Bayesian Optimization with Kernel Principal Component Analysis
Bayesian Optimization (BO) is a surrogate-based global optimization strategy that relies on a Gaussian Process regression (GPR) model to approximate the objective function and an acquisition function to suggest candidate points.
KL-Mat : Fair Recommender System via Information Geometry
Recommender system has intrinsic problems such as sparsity and fairness.
MovieMat: Context-aware Movie Recommendation with Matrix Factorization by Matrix Fitting
In this paper, we take advantage of the MatMat framework, which factorizes matrices by matrix fitting to build a context-aware movie recommender system that is superior to classic matrix factorization and comparable in the fairness metric.
RankMat : Matrix Factorization with Calibrated Distributed Embedding and Fairness Enhancement
Matrix Factorization is a widely adopted technique in the field of recommender system.
Extremal GloVe: Theoretically Accurate Distributed Word Embedding by Tail Inference
However, the initial formulation of GloVe is not theoretically sound in two aspects, namely the selection of the weighting function and its power exponent is ad-hoc.
Causal Transportability for Visual Recognition
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features.
Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks
The destruction to DNNs brought by the adversarial attack sparks the potential that adversarial examples serve as a new protection mechanism for privacy security in social networks.
Analyzing the Impact of Undersampling on the Benchmarking and Configuration of Evolutionary Algorithms
Particularly, we show that the number of runs used in many benchmarking studies, e. g., the default value of 15 suggested by the COCO environment, can be insufficient to reliably rank algorithms on well-known numerical optimization benchmarks.
Per-run Algorithm Selection with Warm-starting using Trajectory-based Features
In contrast to other recent work on online per-run algorithm selection, we warm-start the second optimizer using information accumulated during the first optimization phase.
Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction
To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i. e., preference topics generation, preference shift modeling, and social influence activation.
Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach
Coverage and capacity are the important metrics for performance evaluation in wireless networks, while the coverage and capacity have several conflicting relationships, e. g. high transmit power contributes to large coverage but high inter-cell interference reduces the capacity performance.
Switching between Numerical Black-box Optimization Algorithms with Warm-starting Policies
In this work, we build on the recent study of Vermetten et al. [GECCO 2020], who presented a data-driven approach to investigate promising switches between pairs of algorithms for numerical black-box optimization.
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.
Ranked #1 on
Action Triplet Recognition
on CholecT50 (Challenge)
(using extra training data)
Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.
ESCM$^2$: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation
In this paper, we theoretically demonstrate that ESMM suffers from the following two problems: (1) Inherent Estimation Bias (IEB), where the estimated CVR of ESMM is inherently higher than the ground truth; (2) Potential Independence Priority (PIP) for CTCVR estimation, where there is a risk that the ESMM overlooks the causality from click to conversion.
DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow
Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow.
OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks
This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors.
Knowledge Mining with Scene Text for Fine-Grained Recognition
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification.
On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
We first develop the domain-class transferability graph, and show that such transferability governs the success of learning in MDLT.
Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review
This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles.
Domain Adaptation with Factorizable Joint Shift
In this paper, we propose a new assumption, Factorizable Joint Shift (FJS), to handle the co-existence of sampling bias in covariates and labels.
Full RGB Just Noticeable Difference (JND) Modelling
Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.
Adversarial samples for deep monocular 6D object pose estimation
We also introduce a new U6DA-Linemod dataset for robustness study of the 6D pose estimation task.
