Search Results for author:
Found 107 papers, 31 papers with code
Topology Imbalance and Relation Inauthenticity Aware Hierarchical Graph Attention Networks for Fake News Detection
However, little attention is paid to the issues of both authenticity of the relationships and topology imbalance in the structure of NPG, which trick existing methods and thus lead to incorrect prediction results.
Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection
In this paper, we propose an asymmetric two-stream architecture taking account of the inherent differences between RGB and depth data for saliency detection.
Ranked #19 on
Thermal Image Segmentation
on RGB-T-Glass-Segmentation
A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
This paper proposes a special-purpose system to achieve high-accuracy and high-efficiency machine learning (ML) molecular dynamics (MD) calculations.
A Monkey Swing Counting Algorithm Based on Object Detection
This paper focuses on proposing a deep learning-based monkey swing counting algorithm.
ESCL: Equivariant Self-Contrastive Learning for Sentence Representations
Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.
An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking
Specifically, when the student models are in cross-encoder architecture, a pairwise loss of hard labels is critical for training student models, whereas the distillation objectives of intermediate Transformer layers may hurt performance.
On the impact of spatial heterogeneity and drift rate in a three-patch two-species Lotka-Volterra competition model over a stream
In this paper, we study a three-patch two-species Lotka-Volterra competition patch model over a stream network.
Evolution of dispersal in advective patchy environments with varying drift rates
In this paper, we study a two stream species Lotka-Volterra competition patch model with the patches aligned along a line.
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network
However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction.
Ranked #22 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection
The model is developed from an assembly of 14 datasets with 3, 410 CT scans and evaluated on 6, 162 external CT scans from 3 datasets.
Ranked #1 on
Organ Segmentation
on BTCV
CCFL: Computationally Customized Federated Learning
Federated learning (FL) is a method to train model with distributed data from numerous participants such as IoT devices.
MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages
Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time.
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution
In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details.
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.
Ranked #1 on
SMAC
on SMAC 3s5z_vs_3s6z
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling
By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.
Improving the Modality Representation with Multi-View Contrastive Learning for Multimodal Sentiment Analysis
At the second stage, a self-supervised contrastive learning is designed for the improvement of the distilled unimodal representations after cross-modal interaction.
Multi-Granularity Cross-Modality Representation Learning for Named Entity Recognition on Social Media
With social media posts tending to be multimodal, Multimodal Named Entity Recognition (MNER) for the text with its accompanying image is attracting more and more attention since some textual components can only be understood in combination with visual information.
CEntRE: A paragraph-level Chinese dataset for Relation Extraction among Enterprises
Enterprise relation extraction aims to detect pairs of enterprise entities and identify the business relations between them from unstructured or semi-structured text data, and it is crucial for several real-world applications such as risk analysis, rating research and supply chain security.
An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks
To improve the prediction accuracy of the neural network, we also introduce a novel auxiliary line strategy and an efficient network model during meshing.
Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference
In this talk, we introduce Merlin HugeCTR.
Multi-Scale Wavelet Transformer for Face Forgery Detection
To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection.
Boost CTR Prediction for New Advertisements via Modeling Visual Content
To overcome the limitations of behavior ID features in modeling new ads, we exploit the visual content in ads to boost the performance of CTR prediction models.
Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising
How to pair the video ads with the user search is the core task of Baidu video advertising.
A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and Retrieval
As such they have made great improvements in many tasks of dermoscopy images.
Multi-features based Semantic Augmentation Networks for Named Entity Recognition in Threat Intelligence
Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis.
MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning
Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields.
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels.
Ranked #17 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution.
FedCos: A Scene-adaptive Federated Optimization Enhancement for Performance Improvement
On the other hand, it enlarges the distances between local models, resulting in an aggregated global model with poor performance.
SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
By exploiting computational geometry analysis and properties of segmentation, we design three complementary regularizers, i. e. volume regularization, anchor guidance, convex guarantee, to approximate the true SimT.
Open Set Recognition using Vision Transformer with an Additional Detection Head
However, in a more realistic open set scenario, traditional classifiers with incomplete knowledge cannot tackle test data that are not from the training classes.
Privacy protection based on mask template
Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy.
Cross-domain User Preference Learning for Cold-start Recommendation
With user history represented by a domain-aware sequential model, a frequency encoder is applied to the underlying tags for user content preference learning.
AdaDM: Enabling Normalization for Image Super-Resolution
We found that the standard deviation of the residual feature shrinks a lot after normalization layers, which causes the performance degradation in SR networks.
Auto robust relative radiometric normalization via latent change noise modelling
Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.
Approaching the Limit of Image Rescaling via Flow Guidance
In this paper, instead of directly applying the LR guidance, we propose an additional invertible flow guidance module (FGM), which can transform the downscaled representation to the visually plausible image during downscaling and transform it back during upscaling.
Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans
Our TS-MDL first adopts an end-to-end \emph{i}MeshSegNet method (i. e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan.
Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
To address this challenge, we propose a small-big model framework that deploys a big model in the cloud and a small model on the edge devices.
Federated Learning with Dynamic Transformer for Text to Speech
Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets.
From General to Specific: Online Updating for Blind Super-Resolution
As a result, most previous methods may suffer a performance drop when the degradations of test images are unknown and various (i. e. the case of blind SR).
Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation
However, they fail to fully leverage the high-order appearance relationships between multi-scale features among the support-query image pairs, thus leading to an inaccurate localization of the query objects.
Detecting and Correcting IMU Movements During Joint Angle Estimation
The results demonstrate our method is a promising solution to detecting and correcting IMU movements during JAE.
Anchor-based Plain Net for Mobile Image Super-Resolution
Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward.
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report
Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices.
Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
LAI Estimation of Cucumber Crop Based on Improved Fully Convolutional Network
How to measure LAI accurately and efficiently is the key to the crop yield estimation problem.
Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining.
Aspect Sentiment Triplet Extraction
Machine Reading Comprehension
+2
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
Truncation-Free Matching System for Display Advertising at Alibaba
When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds.
Few-Shot Semantic Segmentation With Cyclic Memory Network
Specifically, we first generate N pairs (key and value) of multi-resolution query features guided by the support feature and its mask.
Dynamic Context-Sensitive Filtering Network for Video Salient Object Detection
Our bidirectional dynamic fusion strategy encourages the interaction of spatial and temporal information in a dynamic manner.
Ranked #11 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
However, there are several issues between the image-based training and video-based inference, including domain differences, lack of positive samples, and temporal smoothness.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
The item selection problem for user cold-start recommendation
When a new user just signs up on a website, we usually have no information about him/her, i. e. no interaction with items, no user profile and no social links with other users.
Adaptive Gradient Method with Resilience and Momentum
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e. g., Adam and RMSProp).
Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things
To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type.
Residual Feature Distillation Network for Lightweight Image Super-Resolution
Thanks to FDC, we can rethink the information multi-distillation network (IMDN) and propose a lightweight and accurate SISR model called residual feature distillation network (RFDN).
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation
Evaluating with 20, 480 input problems, we show that Smartfluidnet achieves 1. 46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.
Poet: Product-oriented Video Captioner for E-commerce
Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.
Hiring Now: A Skill-Aware Multi-Attention Model for Job Posting Generation
To deal with this task, we devise a data-driven global Skill-Aware Multi-Attention generation model, named SAMA.
Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction
The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously.
Residual Feature Aggregation Network for Image Super-Resolution
To maximize the power of the RFA framework, we further propose an enhanced spatial attention (ESA) block to make the residual features to be more focused on critical spatial contents.
Deep Convolutional Neural Network-based Bernoulli Heatmap for Head Pose Estimation
This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image.
Triaging moderate COVID-19 and other viral pneumonias from routine blood tests
The COVID-19 is sweeping the world with deadly consequences.
Stochastic Learning for Sparse Discrete Markov Random Fields with Controlled Gradient Approximation Error
We study the $L_1$-regularized maximum likelihood estimator/estimation (MLE) problem for discrete Markov random fields (MRFs), where efficient and scalable learning requires both sparse regularization and approximate inference.
A Comprehensive Survey of Grammar Error Correction
More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods.
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2
Experimental results show that the Chinese GPT2 can generate better essay endings with \eop.
Computational Performance of a Germline Variant Calling Pipeline for Next Generation Sequencing
With the booming of next generation sequencing technology and its implementation in clinical practice and life science research, the need for faster and more efficient data analysis methods becomes pressing in the field of sequencing.
InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks.
FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors
How to accurately and efficiently label data on a mobile device is critical for the success of training machine learning models on mobile devices.
CTM: Collaborative Temporal Modeling for Action Recognition
In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition.
iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention
The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost.
Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning
At high latitudes, many cities adopt a centralized heating system to improve the energy generation efficiency and to reduce pollution.
Model Embedded DRL for Intelligent Greenhouse Control
Greenhouse environment is the key to influence crops production.
Learning to Predict More Accurate Text Instances for Scene Text Detection
At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks.
Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
In this paper, we present a new angle to analyze the quantization error, which decomposes the quantization error into norm error and direction error.
Creating Auxiliary Representations from Charge Definitions for Criminal Charge Prediction
Thus, we propose to create auxiliary fact representations from charge definitions to augment fact descriptions representation.
Understanding and Improving Proximity Graph based Maximum Inner Product Search
Then we explain the good performance of ip-NSW as matching the norm bias of the MIPS problem - large norm items have big in-degrees in the ip-NSW proximity graph and a walk on the graph spends the majority of computation on these items, thus effectively avoids unnecessary computation on small norm items.
AI for Earth: Rainforest Conservation by Acoustic Surveillance
Saving rainforests is a key to halting adverse climate changes.
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
In this work, we alleviate the NAS search cost down to less than 3 hours, while achieving state-of-the-art image classification results under mobile latency constraints.
Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices
In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models.
Single-Path NAS: Device-Aware Efficient ConvNet Design
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device?
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device?
Ranked #787 on
Image Classification
on ImageNet
Rotated Feature Network for multi-orientation object detection
General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks.
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
In this work, we propose to train CNNs from images annotated with multiple tags, to enhance the quality of visual representation of the trained CNN model.
Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS and several algorithms including $L_2$-ALSH, Sign-ALSH and Simple-LSH have been proposed.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
On the Acceleration of L-BFGS with Second-Order Information and Stochastic Batches
This paper proposes a framework of L-BFGS based on the (approximate) second-order information with stochastic batches, as a novel approach to the finite-sum minimization problems.
A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification
In this paper we propose a novel Spatial and Temporal Features Mixture Model (STFMM) based on convolutional neural network (CNN) and recurrent neural network (RNN), in which the human body is split into $N$ parts in horizontal direction so that we can obtain more specific features.
Question Answering over Freebase via Attentive RNN with Similarity Matrix based CNN
To preserve more original information, we propose an attentive recurrent neural network with similarity matrix based convolutional neural network (AR-SMCNN) model, which is able to capture comprehensive hierarchical information utilizing the advantages of both RNN and CNN.
MLE-induced Likelihood for Markov Random Fields
Especially as the size of the MRF increases, both the numerical performance and the computational cost of our approach remain consistently satisfactory, whereas Laplace approximation deteriorates and pseudolikelihood becomes computationally unbearable.
Stochastic Recursive Gradient Algorithm for Nonconvex Optimization
In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses.
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems.
Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption
We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD).
Topic Aware Neural Response Generation
We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots.
Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting
Our method first performs a deterministic step (computation of the gradient of the objective function at the starting point), followed by a large number of stochastic steps.
mS2GD: Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting
Our method first performs a deterministic step (computation of the gradient of the objective function at the starting point), followed by a large number of stochastic steps.
A new hierarchical method for inter-patient heartbeat classification using random projections and RR intervals
This was done in order to improve the classification performance of these two classes of heartbeats by using different features and classification methods.
Ranked #2 on
Heartbeat Classification
on MIT-BIH AR
Defuzzify firstly or finally: Dose it matter in fuzzy DEMATEL under uncertain environment?
The results of defuzzification at the first step are not coincide with the results of defuzzification at the final step. It seems that the alternative is to defuzzification in the final step in fuzzy DEMATEL.
Bayesian Estimation of Latently-grouped Parameters in Undirected Graphical Models
In large-scale applications of undirected graphical models, such as social networks and biological networks, similar patterns occur frequently and give rise to similar parameters.
A brief network analysis of Artificial Intelligence publication
In this paper, we present an illustration to the history of Artificial Intelligence(AI) with a statistical analysis of publish since 1940.
