Search Results for author:
Found 147 papers, 40 papers with code
PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity Recognition
Cross-domain Named Entity Recognition (NER) transfers the NER knowledge from high-resource domains to the low-resource target domain.
ActPerFL: Active Personalized Federated Learning
Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.
Fourier neural operators for spatiotemporal dynamics in two-dimensional turbulence
High-fidelity direct numerical simulation of turbulent flows for most real-world applications remains an outstanding computational challenge.
Early Joint Learning of Emotion Information Makes MultiModal Model Understand You Better
In this paper, we present our solutions for emotion recognition in the sub-challenges of Multimodal Emotion Recognition Challenge (MER2024).
Recognition of Schrodinger cat state based on CNN
We applied convolutional neural networks to the classification of cat states and coherent states.
SysBench: Can Large Language Models Follow System Messages?
In order to enable effective evaluation, SysBench constructs multi-turn user conversations covering various interaction relationships, based on six common types of constraints from system messages in real-world scenarios.
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs
The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications.
Closed-loop Diffusion Control of Complex Physical Systems
The control problems of complex physical systems have broad applications in science and engineering.
Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
However, this method may result in inefficient knowledge memorization due to a lack of awareness of knowledge utilization and imposes substantial demands on LLMs to simultaneously learn knowledge utilization and format alignment with limited training samples.
A Generative Approach to Control Complex Physical Systems
In this work, we introduce Diffusion Physical systems Control (DiffPhyCon), a new class of method to address the physical systems control problem.
PAS: Data-Efficient Plug-and-Play Prompt Augmentation System
This combination of high performance, efficiency, and flexibility makes PAS a valuable system for enhancing the usability and effectiveness of LLMs through improved prompt engineering.
Hybrid-Generative Diffusion Models for Attack-Oriented Twin Migration in Vehicular Metaverses
The vehicular metaverse is envisioned as a blended immersive domain that promises to bring revolutionary changes to the automotive industry.
MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation
This task is aimed at bridging the gap between colloquial language understanding and auditory expression within an AI model, with the ultimate goal of creating songs that accurately satisfy human auditory expectations and structurally align with musical norms.
Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model
Based on the benchmark results, our RWKV-SAM achieves outstanding performance in efficiency and segmentation quality compared to transformers and other linear attention models.
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Current universal segmentation methods demonstrate strong capabilities in pixel-level image and video understanding.
RTFormer: Re-parameter TSBN Spiking Transformer
The Spiking Neural Networks (SNNs), renowned for their bio-inspired operational mechanism and energy efficiency, mirror the human brain's neural activity.
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images
Building on this pipeline, we developed P2PFormer, which utilizes a transformer-based architecture to segment geometric primitives and predict their order.
Knowledge Enhanced Multi-intent Transformer Network for Recommendation
However, simply integrating KG into recommendation usually brings in negative feedback in industry, due to the ignorance of the following two factors: i) users' multiple intents, which involve diverse nodes in KG.
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion.
Ranked #1 on
Video Instance Segmentation
on OVIS validation
(using extra training data)
On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks
Federated learning is a promising technique for effectively training GAI models in mobile edge networks due to its data distribution.
Search Intenion Network for Personalized Query Auto-Completion in E-Commerce
Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions. Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process, the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model. 2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer. However, the current intention extracted from prefix may be contrary to the historical preferences.
Point Cloud Mamba: Point Cloud Learning via State Space Model
To enable Mamba to process 3-D point cloud data more effectively, we propose a novel Consistent Traverse Serialization method to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent.
A Quick Framework for Evaluating Worst Robustness of Complex Networks
Robustness is pivotal for comprehending, designing, optimizing, and rehabilitating networks, with simulation attacks being the prevailing evaluation method.
MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music
To this end, we present MuChin, the first open-source music description benchmark in Chinese colloquial language, designed to evaluate the performance of multimodal LLMs in understanding and describing music.
On Practical Diversified Recommendation with Controllable Category Diversity Framework
These neglected non-interaction preferences are especially important for broadening user's interests in alleviating echo chamber/filter bubble effects. Therefore, in this paper, we first define diversity as two distinct definitions, i. e., user-explicit diversity (U-diversity) and user-item non-interaction diversity (N-diversity) based on user historical behaviors.
Episodic-free Task Selection for Few-shot Learning
In this framework, episodic tasks are not used directly for training, but for evaluating the effectiveness of some selected episodic-free tasks from a task set that are performed for training the meta-learners.
Compositional Generative Inverse Design
In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes that are more complex than those in the training data.
Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation
Recently, a new recommendation scenario, called Trigger-Induced Recommendation (TIR), where users are able to explicitly express their instant interests via trigger items, is emerging as an essential role in many e-commerce platforms, e. g., Alibaba. com and Amazon.
Training and Serving System of Foundation Models: A Comprehensive Survey
Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems.
Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS).
Ranked #1 on
Video Semantic Segmentation
on VSPW
PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images
Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features.
Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting
We achieved 1st place in Detection, Tracking, and Forecasting on the E2E Forecasting track in Argoverse Challenges at CVPR 2023 WAD.
Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification
Then we merge the sentences selected for a specific aspect as the input for the summarizer to produce the aspect-based summary.
JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction
Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text.
CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.
Abstract Meaning Representation
Natural Language Understanding
DexCatch: Learning to Catch Arbitrary Objects with Dexterous Hands
Achieving human-like dexterous manipulation remains a crucial area of research in robotics.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving.
Comprehensive Analysis of Network Robustness Evaluation Based on Convolutional Neural Networks with Spatial Pyramid Pooling
However, the performance of the proposed CNN model varies: for evaluation tasks that are consistent with the trained network type, the proposed CNN model consistently achieves accurate evaluations of both attack curves and robustness values across all removal scenarios.
Flashlight Search Medial Axis: A Pixel-Free Pore-Network Extraction Algorithm
In this way, computational complexity of this method is greatly reduced compared to that of traditional pixel-based extraction methods, thus enabling large-scale pore-network extraction.
ReIDTrack: Multi-Object Track and Segmentation Without Motion
Association techniques mainly depend on the combination of motion and appearance information.
TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning
Emotion recognition is an important research direction in artificial intelligence, helping machines understand and adapt to human emotional states.
Enhancing Cross-lingual Transfer via Phonemic Transcription Integration
Particularly, we propose unsupervised alignment objectives to capture (1) local one-to-one alignment between the two different modalities, (2) alignment via multi-modality contexts to leverage information from additional modalities, and (3) alignment via multilingual contexts where additional bilingual dictionaries are incorporated.
Learning to Branch in Combinatorial Optimization with Graph Pointer Networks
The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions.
A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M).
Document-level RE with incomplete labeling
Metric Learning
+1
Privacy and Fairness in Federated Learning: on the Perspective of Trade-off
Federated learning (FL) has been a hot topic in recent years.
1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.
Differences in boundary behavior in the 3D vertex and Voronoi models
However, recent work in 2D has hinted that there may be differences between the two models in systems with heterotypic interfaces between two tissue types, and there is a burgeoning interest in 3D tissue models.
DVIS: Decoupled Video Instance Segmentation Framework
The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement.
Ranked #4 on
Video Panoptic Segmentation
on VIPSeg
SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning
Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples.
Semi-Supervised Federated Learning for Keyword Spotting
Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants.
How human-derived brain organoids are built differently from brain organoids derived of genetically-close relatives: A multi-scale hypothesis
We postulate that the enhancement of ZEB2 expression driving this intermediate state is potentially due to chromatin reorganization.
A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation
However, traditional methods have viewed motion planning and compliant control as two separate modules, which can lead to conflicts with the simultaneous change of the desired trajectory and impedance parameters in the presence of external forces and disturbances.
Adversarial Attack with Raindrops
Extensive experiments are carried out to demonstrate that the images crafted by AdvRD are visually and statistically close to the natural raindrop images, can work as strong attackers to DNN models, and also help improve the robustness of DNNs to raindrop attacks.
Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization
In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose.
Low-Rank Structured Clutter Covariance Matrix Estimation for Airborne STAP Radar
In space-time adaptive processing (STAP) of the airborne radar system, it is very important to realize sparse restoration of the clutter covariance matrix with a small number of samples.
EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator
The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.
A Policy Optimization Method Towards Optimal-time Stability
In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization.
Coevolutionary Framework for Generalized Multimodal Multi-objective Optimization
To address the above two issues, in this study, a novel coevolutionary framework termed CoMMEA for multimodal multi-objective optimization is proposed to better obtain both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs.
Deep Smart Contract Intent Detection
Nowadays, security activities in smart contracts concentrate on vulnerability detection.
BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction
Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images.
A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling
To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning.
Federated Learning with Server Learning: Enhancing Performance for Non-IID Data
Federated Learning (FL) has emerged as a means of distributed learning using local data stored at clients with a coordinating server.
Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking
To our best knowledge, the performance of the Spiking SiamFC++ outperforms the existing state-of-the-art approaches in SNN-based object tracking, which provides a novel path for SNN application in the field of target tracking.
Modeling Two-Way Selection Preference for Person-Job Fit
To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph.
Patient-Specific Game-Based Transfer Method for Parkinson's Disease Severity Prediction
Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction.
Kernel Relative-prototype Spectral Filtering for Few-shot Learning
In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS).
Large-scale matrix optimization based multi microgrid topology design with a constrained differential evolution algorithm
Binary matrix optimization commonly arise in the real world, e. g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints.
Multimodal Multi-objective Optimization: Comparative Study of the State-of-the-Art
Multimodal multi-objective problems (MMOPs) commonly arise in real-world problems where distant solutions in decision space correspond to very similar objective values.
A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object
Module I realizes the multi-target trajectory planning for two end-effectors within a large target space.
Challenges and Opportunities in Multi-device Speech Processing
We review current solutions and technical challenges for automatic speech recognition, keyword spotting, device arbitration, speech enhancement, and source localization in multidevice home environments to provide context for the INTERSPEECH 2022 special session, "Challenges and opportunities for signal processing and machine learning for multiple smart devices".
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle
Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model.
Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization
Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades.
CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping
In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background.
Deep Reinforcement Learning for Orienteering Problems Based on Decomposition
A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes.
Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer
The model is trained using a deep reinforcement learning method offline, and is used to optimize the UAV routing problem online.
Self-Aware Personalized Federated Learning
In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.
Leveraging Search History for Improving Person-Job Fit
As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.
SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo
In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume.
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation.
Ranked #97 on
Instance Segmentation
on COCO test-dev
RRL:Regional Rotation Layer in Convolutional Neural Networks
Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features.
Federated Learning Challenges and Opportunities: An Outlook
Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.
End-to-End Quality-of-Service Assurance with Autonomous Systems: 5G/6G Case Study
This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables.
Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses.
Bayesian Promised Persuasion: Dynamic Forward-Looking Multiagent Delegation with Informational Burning
A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.
End-to-end Alexa Device Arbitration
We introduce a variant of the speaker localization problem, which we call device arbitration.
MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack
However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks.
Pre-training Graph Neural Network for Cross Domain Recommendation
Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain.
FedProc: Prototypical Contrastive Federated Learning on Non-IID data
In this paper, we propose FedProc: prototypical contrastive federated learning, which is a simple and effective federated learning framework.
M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
Informational Design of Dynamic Multi-Agent System
We propose a direct information design approach that incentivizes each agent to select the signal sent by the principal, such that the design process avoids the predictions of the agents' strategic selection behaviors.
Low Pass Filter for Anti-aliasing in Temporal Action Localization
This paper aims to verify the existence of aliasing in TAL methods and investigate utilizing low pass filters to solve this problem by inhibiting the high-frequency band.
Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images.
GnetDet: Object Detection Optimized on a 224mW CNN Accelerator Chip at the Speed of 106FPS
Object detection is widely used on embedded devices.
On the Equilibrium Elicitation of Markov Games Through Information Design
An obedient principle is established which states that it is without loss of generality to focus on the direct information design when the information design incentivizes each agent to select the signal sent by the designer, such that the design process avoids the predictions of the agents' strategic selection behaviors.
Deep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problems
This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP).
Hyperspectral Image Denoising With Realistic Data
On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.
Generative Partial Visual-Tactile Fused Object Clustering
More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.
Improving the Certified Robustness of Neural Networks via Consistency Regularization
A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably robust to the attacker.
On Front-end Gain Invariant Modeling for Wake Word Spotting
Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.
Investigating Constraint Relationship in Evolutionary Many-Constraint Optimization
This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.
Correlated Differential Privacy: Feature Selection in Machine Learning
In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover, the privacy issue of data correlation in learning is guaranteed.
Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination
A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.
Fairness Constraints in Semi-supervised Learning
Extensive experiments show that our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.
Re-weighting and 1-Point RANSAC-Based PnP Solution to Handle Outliers
We propose a fast PnP solution named R1PPnP to handle outliers by utilizing a soft re-weighting mechanism and the 1-point RANSAC scheme.
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture
Aiming at channel compression, a novel convolutional construction named compact convolution is proposed to embrace the progress in spatial convolution, channel grouping and pooling operation.
MIE: A Medical Information Extractor towards Medical Dialogues
Electronic Medical Records (EMRs) have become key components of modern medical care systems.
Evolving Metric Learning for Incremental and Decremental Features
Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.
Bootstrap inference for quantile-based modal regression
Specifically, we propose to estimate the conditional mode by minimizing the derivative of the estimated conditional quantile function defined by smoothing the linear quantile regression estimator, and develop two bootstrap methods, a novel pivotal bootstrap and the nonparametric bootstrap, for our conditional mode estimator.
Statistics Theory Methodology Statistics Theory
kDecay: Just adding k-decay items on Learning-Rate Schedule to improve Neural Networks
On the ImageNet, accuracy is improved by 1. 25\%.
MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing
Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types.
Adaptive Trajectory Estimation with Power Limited Steering Model under Perturbation Compensation
The experiment of trajectory estimation demonstrates the convergence of AdaTE, and the better robust to the biased prior statistics and the observation drift compared with EKF, UKF and sparse MAP.
Information Theory Robotics Systems and Control Systems and Control Information Theory G.3.13; J.2.7
Visual Tactile Fusion Object Clustering
To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering.
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks
As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.
Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network
Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.
Hyperspectral Image Reconstruction Using Deep External and Internal Learning
To solve the low spatial and/or temporal resolution problem which the conventional hypelrspectral cameras often suffer from, coded snapshot hyperspectral imaging systems have attracted more attention recently.
Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.
Ranked #3 on
Link Prediction
on FB15k
(MR metric)
Mixed-Supervised Dual-Network for Medical Image Segmentation
The model is trained jointly in a multi-task learning setting.
FC$^2$N: Fully Channel-Concatenated Network for Single Image Super-Resolution
Most current image super-resolution (SR) methods based on convolutional neural networks (CNNs) use residual learning in network structural design, which favors to effective back propagation and hence improves SR performance by increasing model scale.
ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks.
Data-Driven Machine Learning Techniques for Self-healing in Cellular Wireless Networks: Challenges and Solutions
As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation.
Deep Reinforcement Learning for Multi-objective Optimization
The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.
A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes.
Imbalanced Sentiment Classification Enhanced with Discourse Marker
Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.
SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction
Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI).
Acceleration of the NVT-flash calculation for multicomponent mixtures using deep neural network models
Phase equilibrium calculation, also known as flash calculation, has been extensively applied in petroleum engineering, not only as a standalone application for separation process but also an integral component of compositional reservoir simulation.
Single MR Image Super-Resolution via Channel Splitting and Serial Fusion Network
Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images.
Channel Splitting Network for Single MR Image Super-Resolution
The proposed CSN model divides the hierarchical features into two branches, i. e., residual branch and dense branch, with different information transmissions.
Ranked #3 on
Image Super-Resolution
on IXI
SEQUENCE MODELLING WITH AUTO-ADDRESSING AND RECURRENT MEMORY INTEGRATING NETWORKS
Processing sequential data with long term dependencies and learn complex transitions are two major challenges in many deep learning applications.
Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).
Convolutional Neural Networks based Intra Prediction for HEVC
To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.
Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data.
A Survey of Model Compression and Acceleration for Deep Neural Networks
Methods of parameter pruning and quantization are described first, after that the other techniques are introduced.
Limits on Axion Couplings from the first 80-day data of PandaX-II Experiment
We report new searches for the solar axions and galactic axion-like dark matter particles, using the first low-background data from PandaX-II experiment at China Jinping Underground Laboratory, corresponding to a total exposure of about $2. 7\times 10^4$ kg$\cdot$day.
High Energy Physics - Experiment Solar and Stellar Astrophysics High Energy Physics - Phenomenology
A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.
Bootstrapping Face Detection with Hard Negative Examples
Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks.
Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK
In this paper we investigate user learning in authoritative technology adoption by developing an agent-based model using the case of council-led smart meter deployment in the UK City of Leeds.
Modelling Office Energy Consumption: An Agent Based Approach
In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, based on a case study, to simulate the energy consumption in office buildings.
Dynamic Privacy For Distributed Machine Learning Over Network
Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data.
Modelling Electricity Consumption in Office Buildings: An Agent Based Approach
In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, to simulate the electricity consumption in office buildings.
