Search Results for author:
Found 97 papers, 24 papers with code
Evolutionary Topology Search for Tensor Network Decomposition
Tensor network (TN) decomposition is a promising framework to represent extremely high-dimensional problems with few parameters.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems
Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives.
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks
Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients.
Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma
In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction.
L3C-Stereo: Lossless Compression for Stereo Images
To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module.
End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
Recently, researchers have found that the performance of CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term user behavior sequence.
Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data.
Integrating Large Circular Kernels into CNNs through Neural Architecture Search
We first substitute the $3 \times 3$ square kernels with the corresponding circular kernels or our proposed integrated kernels in the typical ResNet architecture, and the modified models after training yield similar or even competitive performance.
Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized.
Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
Recently, transform-based tensor nuclear norm minimization methods are considered to capture low-rank tensor structures to recover third-order tensors in multi-dimensional image processing applications.
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for user-generated text in the Chinese language.
Ranked #1 on
Chinese Spell Checking
on SIGHAN 2015
Egocentric Activity Recognition and Localization on a 3D Map
Our model takes the inputs of a Hierarchical Volumetric Representation (HVR) of the environment and an egocentric video, infers the 3D action location as a latent variable, and recognizes the action based on the video and contextual cues surrounding its potential locations.
Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network
An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed.
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction
Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging.
BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification
The proposed BrainNetGAN is a generative adversarial network variant to augment the brain structural connectivity matrices for binary dementia classification tasks.
NeRD: Neural Representation of Distribution for Medical Image Segmentation
We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.
On the Memory Mechanism of Tensor-Power Recurrent Models
Tensor-power (TP) recurrent model is a family of non-linear dynamical systems, of which the recurrence relation consists of a p-fold (a. k. a., degree-p) tensor product.
T3AB: Transparent and Trustworthy Third-party Authority using Blockchain
To address such trust issues, various transparency frameworks and approaches have been recently proposed in the literature.
Cryptography and Security Networking and Internet Architecture
Measuring Decentralization in Bitcoin and Ethereum using Multiple Metrics and Granularities
Decentralization has been widely acknowledged as a core virtue of blockchains.
Cryptography and Security Databases
Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma
EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration.
On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.
Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation
The distributed tensor representations are dispersed on multiple clouds / fogs or servers / devices with metadata privacy, this provides both distributed trust and management to seamlessly secure big data storage, communication, sharing, and computation.
Adversarial Attack on Deep Cross-Modal Hamming Retrieval
Specifically, given a target model, we first construct its substitute model to exploit cross-modal correlations within hamming space, with which we create adversarial examples by limitedly querying from a target model.
Improving BERT with Syntax-aware Local Attention
Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks.
NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
We propose a novel framework, NN-EMD, to train DNN over multiple encrypted datasets collected from multiple sources.
Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients
Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes.
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Channel Pruning via Multi-Criteria based on Weight Dependency
However, these methods ignore a small part of weights in the next layer which disappears as the feature map is removed.
An Empirical-cum-Statistical Approach to Power-Performance Characterization of Concurrent GPU Kernels
Growing deployment of power and energy efficient throughput accelerators (GPU) in data centers demands enhancement of power-performance co-optimization capabilities of GPUs.
Distributed, Parallel, and Cluster Computing Hardware Architecture Graphics
How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting.
Architectural Implications of Graph Neural Networks
Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures.
Joint Generative Learning and Super-Resolution For Real-World Camera-Screen Degradation
Firstly, the downsampling degradation GAN(DD-GAN) is trained to model the degradation and produces more various of LR images, which is validated to be efficient for data augmentation.
Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
The key lies in the design of the graph structure, which encodes skeleton topology information.
Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
In the classic volumetric fusion-based framework, a mesh is usually extracted from the TSDF volume as the canonical surface representation to help estimating deformation field.
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
On ResNet-32, PFGDF reduced the convolution filter by 21:92%.
NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
For track 2, some existing methods are evaluated, showing promising solutions to the weakly-supervised video quality mapping problem.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration
We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications.
H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution
It is a challenging task to restore images from their variants with combined distortions.
Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization
In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR.
Cross-Modal Learning with Adversarial Samples
Extensive experiments on two cross-modal benchmark datasets show that the adversarial examples produced by our CMLA are efficient in fooling a target deep cross-modal hashing network.
Single Image Reflection Removal through Cascaded Refinement
IBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade is transferred using an LSTM.
TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation
In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story.
Hierarchical hidden community detection for protein complex prediction
Results: We propose a method called HirHide (Hierarchical Hidden Community Detection), which can be combined with traditional community detection methods to enable them to discover hierarchical hidden communities.
Molecular Networks
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.
Ranked #54 on
Image Classification
on CIFAR-10
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
User independent Emotion Recognition with Residual Signal-Image Network
To the best of author's knowledge, our method is the first attempt to classify large scale subject-independent emotion with 7962 pieces of EDA signals from 457 subjects.
Best Practices for Learning Domain-Specific Cross-Lingual Embeddings
Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages.
Multi-Objective Pruning for CNNs Using Genetic Algorithm
In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity.
Guaranteed Matrix Completion Under Multiple Linear Transformations
Low-rank matrix completion (LRMC) is a classical model in both computer vision (CV) and machine learning, and has been successfully applied to various real applications.
Collaborative Spatiotemporal Feature Learning for Video Action Recognition
By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other.
Ranked #12 on
Action Classification
on Moments in Time
Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks.
POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion
In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.
Adversarial Defense Through Network Profiling Based Path Extraction
Recently, researchers have started decomposing deep neural network models according to their semantics or functions.
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items.
Shared Predictive Cross-Modal Deep Quantization
In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search.
CryptoNN: Training Neural Networks over Encrypted Data
To tackle the above issue, we propose a CryptoNN framework that supports training a neural network model over encrypted data by using the emerging functional encryption scheme instead of SMC or HE.
Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification
Recent years have witnessed the quick progress of the hyperspectral images (HSI) classification.
Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification
The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel active learning strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross-dataset and intra-image; 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representation.
Tensor-Ring Nuclear Norm Minimization and Application for Visual Data Completion
Tensor ring (TR) decomposition has been successfully used to obtain the state-of-the-art performance in the visual data completion problem.
Predicting Research Trends From Arxiv
By extrapolation, we predict that these topics will remain lead problems/approaches in their fields in the short- and mid-term.
Semantic Adversarial Network with Multi-scale Pyramid Attention for Video Classification
Two-stream architecture have shown strong performance in video classification task.
Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval
In recent years, hashing has attracted more and more attention owing to its superior capacity of low storage cost and high query efficiency in large-scale cross-modal retrieval.
Collaborative Spatio-temporal Feature Learning for Video Action Recognition
By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other.
Anomaly Detection for an E-commerce Pricing System
Our system detects anomalies both in batch and real-time streaming settings, and the items flagged are reviewed and actioned based on priority and business impact.
Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction
Dimensionality reduction is an essential technique for multi-way large-scale data, i. e., tensor.
Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising
This is done by first learning a low-dimensional projection and the related reduced image from the noisy HSI.
Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
To build an open-domain multi-turn conversation system is one of the most interesting and challenging tasks in Artificial Intelligence.
Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling
We demonstrate this by compressing the convolutional layers via randomly-shuffled tensor decomposition (RsTD) for a standard classification task using CIFAR-10.
Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion
In this paper, by exploiting the low-rank structure of the TR latent space, we propose a novel tensor completion method which is robust to model selection.
ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
This paper proposes a real-time dynamic scene reconstruction method capable of reproducing the motion, geometry, and segmentation simultaneously given live depth stream from a single RGB-D camera.
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling
Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis.
Rank Minimization on Tensor Ring: A New Paradigm in Scalable Tensor Decomposition and Completion
In low-rank tensor completion tasks, due to the underlying multiple large-scale singular value decomposition (SVD) operations and rank selection problem of the traditional methods, they suffer from high computational cost and high sensitivity of model complexity.
High Performance Visual Tracking with Circular and Structural Operators
Based on the proposed circular and structural operators, a set of primal confidence score maps can be obtained by circular correlating feature maps with their corresponding structural correlation filters.
A Complementary Tracking Model with Multiple Features
Discriminative Correlation Filters based tracking algorithms exploiting conventional handcrafted features have achieved impressive results both in terms of accuracy and robustness.
Large Margin Structured Convolution Operator for Thermal Infrared Object Tracking
To the best of our knowledge, we are the first to incorporate the advantages of DCF and SOSVM for TIR object tracking.
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets.
Ranked #2 on
Skeleton Based Action Recognition
on PKU-MMD
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations.
Model Trees for Identifying Exceptional Players in the NHL Draft
Successful previous approaches have built a predictive model based on player features, or derived performance predictions from the observed performance of comparable players in a cohort.
Combining Linear Non-Gaussian Acyclic Model with Logistic Regression Model for Estimating Causal Structure from Mixed Continuous and Discrete Data
Most existing causal discovery methods either ignore the discrete data and apply a continuous-valued algorithm or discretize all the continuous data and then apply a discrete Bayesian network approach.
Generative Adversarial Positive-Unlabelled Learning
However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks.
Cascade Region Proposal and Global Context for Deep Object Detection
Deep region-based object detector consists of a region proposal step and a deep object recognition step.
AutoEncoder Inspired Unsupervised Feature Selection
High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty.
Leveraging Weak Semantic Relevance for Complex Video Event Classification
In this paper, we propose a novel approach to automatically maximize the utility of weak semantic annotations (formalized as the semantic relevance of video shots to the target event) to facilitate video event classification.
Deep Speaker: an End-to-End Neural Speaker Embedding System
We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity.
Skeleton-based Action Recognition with Convolutional Neural Networks
Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN).
Ranked #3 on
Skeleton Based Action Recognition
on PKU-MMD
Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs
Leveraging large data sets, deep Convolutional Neural Networks (CNNs) achieve state-of-the-art recognition accuracy.
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection
As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images.
Co-Saliency Detection via Looking Deep and Wide
In the proposed framework, the wide and deep information are explored for the object proposal windows extracted in each image, and the co-saliency scores are calculated by integrating the intra-image contrast and intra group consistency via a principled Bayesian formulation.
Canonical Polyadic Decomposition with Auxiliary Information for Brain Computer Interface
Unlike vector-based methods that destroy data structure, Canonical Polyadic Decomposition (CPD) aims to process physiological signals in the form of multi-way array, which considers relationships between dimensions and preserves structure information contained by the physiological signal.
Multi-tensor Completion for Estimating Missing Values in Video Data
Thus one question raised whether such the relationship can improve the performance of data completion or not?