Search Results for author:
Found 253 papers, 87 papers with code
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
融合情感分析的隐式反问句识别模型(Implicit Rhetorical Questions Recognition Model Combined with Sentiment Analysis)
“反问是现代汉语中一种常用的修辞手法, 根据是否含有反问标记可分为显式反问句与隐式反问句。其中隐式反问句表达的情感更为丰富, 表现形式也十分复杂, 对隐式反问句的识别更具挑战性。本文首先扩充了汉语反问句语料库, 语料库规模达到10000余句, 接着针对隐式反问句的特点, 提出了一种融合情感分析的隐式反问句识别模型。模型考虑了句子的语义信息, 上下文信息, 并借助情感分析任务辅助识别隐式反问句。实验结果表明, 本文提出的模型在隐式反问句识别任务上取得了良好的性能。”
BIT-Xiaomi’s System for AutoSimTrans 2022
This system paper describes the BIT-Xiaomi simultaneous translation system for Autosimtrans 2022 simultaneous translation challenge.
Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network
Specifically, a phase estimation network is introduced for the input single image, and the gait cycle reconstruction network exploits the estimated phase to mitigate the dependence of an encoded feature on the phase of that single image.
Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network
Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance.
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning.
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022
Our system is built based on the Transformer model with novel techniques borrowed from our recent research work.
Meta-Learning Siamese Network for Few-Shot Text Classification
Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO).
Structure Flow-Guided Network for Real Depth Super-Resolution
Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).
Recurrent Structure Attention Guidance for Depth Super-Resolution
Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.
Decision-Making Context Interaction Network for Click-Through Rate Prediction
Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems.
SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking
In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE).
Towards Spatial Equilibrium Object Detection
In this paper, we study the spatial disequilibrium problem of modern object detectors and propose to quantify this ``spatial bias'' by measuring the detection performance over zones.
DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution
We develop a hybrid dynamic-Transformer block(HDTB) that integrates the MHDLSA and SparseGSA for both local and global feature exploration.
Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Weighted Negative Samples
We take node embeddings in the coarse view as anchors, and construct positive and negative samples from the fine-grained view.
Recovering Surveillance Video Using RF Cues
We make use of an auto-encoder-based structure to extract pose features from WiFi frames.
Near-optimal Policy Identification in Active Reinforcement Learning
Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces.
One-Stage Cascade Refinement Networks for Infrared Small Target Detection
Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection.
LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving
In this paper, we present a more artful framework, LiDAR-guided Weakly Supervised Instance Segmentation (LWSIS), which leverages the off-the-shelf 3D data, i. e., Point Cloud, together with the 3D boxes, as natural weak supervisions for training the 2D image instance segmentation models.
Curriculum Temperature for Knowledge Distillation
In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature.
Panoramic Video Salient Object Detection with Ambisonic Audio Guidance
In this paper, we aim to tackle the video salient object detection problem for panoramic videos, with their corresponding ambisonic audios.
Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval
Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i. e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i. e., target domain).
Ranked #1 on
Image Retrieval
on PKU-Reid
Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors
Recent diffusion-based generative models combined with vision-language models are capable of creating realistic images from natural language prompts.
DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation.
Realization of Causal Representation Learning to Adjust Confounding Bias in Latent Space
Causal graphs are usually considered in a 2D plane, but it has rarely been noticed that within multiple relatively independent timelines, which is comparatively common in causality machine learning, the individual-level differences may lead to Causal Representation Bias (CRB).
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.
Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training
In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation.
TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
Adaptive gradient methods have shown their ability to adjust the stepsizes on the fly in a parameter-agnostic manner, and empirically achieve faster convergence for solving minimization problems.
Disentangled and Robust Representation Learning for Bragging Classification in Social Media
Researching bragging behavior on social media arouses interest of computational (socio) linguists.
Pixel-Aligned Non-parametric Hand Mesh Reconstruction
The decoder aggregate both local image features in pixels and geometric features in vertices.
Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint
To tackle the challenge, we introduce an intermediate variable for grasp contact areas to constrain the grasp generation; in other words, we factorize the mapping into two sequential stages by assuming that grasping poses are fully constrained given contact maps: 1) we first learn contact map distributions to generate the potential contact maps for grasps; 2) then learn a mapping from the contact maps to the grasping poses.
Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding
In this paper, to address these problems, we introduce a seminal knowledge prompting paradigm and further propose a knowledge-prompting-based PLM framework KP-PLM.
Mini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications
To address this issue, we further propose a new strategy which augments a training segment with an initial value of the target variable from the timestep right before the starting of the training segment.
Probabilistic Inverse Modeling: An Application in Hydrology
We propose uncertainty based learning method that offers 6\% improvement in $R^2$ for streamflow prediction (forward modeling) from inverse model inferred basin characteristic estimates, 17\% reduction in uncertainty (40\% in presence of noise) and 4\% higher coverage rate for basin characteristics.
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure
To interpret these models, some probing methods have been applied.
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.
Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder
In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challenging problems.
Ranking-Enhanced Unsupervised Sentence Representation Learning
This results in inadequate supervision signals for capturing a semantic similarity of similar sentences.
Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction
To learn it applicably, we propose a general clause-level encoding model named EA-GAT comprising E-GAT and Activation Sort.
Towards Cross-speaker Reading Style Transfer on Audiobook Dataset
This paper aims to introduce a chunk-wise multi-scale cross-speaker style model to capture both the global genre and the local prosody in audiobook speeches.
SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization
Recent advances in data processing have stimulated the demand for learning graphs of very large scales.
Online Video Instance Segmentation via Robust Context Fusion
We propose a robust context fusion network to tackle VIS in an online fashion, which predicts instance segmentation frame-by-frame with a few preceding frames.
DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection
Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels.
R^2VOS: Robust Referring Video Object Segmentation via Relational Multimodal Cycle Consistency
We leverage the cycle consistency to discriminate the semantic consensus, thus advancing the primary task.
Ranked #4 on
Referring Expression Segmentation
on Refer-YouTube-VOS (2021 public validation)
(using extra training data)
Referring Expression Segmentation
Referring Video Object Segmentation
+2
RAW-GNN: RAndom Walk Aggregation based Graph Neural Network
Due to the homophily assumption of Graph Convolutional Networks (GCNs) that these methods use, they are not suitable for heterophily graphs where nodes with different labels or dissimilar attributes tend to be adjacent.
Neural Neural Textures Make Sim2Real Consistent
Unpaired image translation algorithms can be used for sim2real tasks, but many fail to generate temporally consistent results.
Dual Power Spectrum Manifold and Toeplitz HPD Manifold: Enhancement and Analysis for Matrix CFAR Detection
These advantages benefit from the geometry of the Toeplitz Hermitian positive definite (HPD) manifold $\mathcal{M}_{\mathcal{T}H_{++}}$, but the sophisticated geometry also results in some challenges for geometric detectors, such as the implementation of the enhanced detector to improve the SCR (signal-to-clutter ratio) and the analysis of the detection performance.
Bear the Query in Mind: Visual Grounding with Query-conditioned Convolution
With our proposed QCM, the downstream fusion module receives visual features that are more discriminative and focused on the desired object described in the expression, leading to more accurate predictions.
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels.
Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization
Adaptive algorithms like AdaGrad and AMSGrad are successful in nonconvex optimization owing to their parameter-agnostic ability -- requiring no a priori knowledge about problem-specific parameters nor tuning of learning rates.
CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
As most of the existing graph neural networks yield effective graph representations of a single graph, little effort has been made for jointly learning two graph representations and calculating their similarity score.
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy.
Ranked #26 on
Object Detection
on COCO minival
AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System
Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages.
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.
Weakly Supervised Text Classification using Supervision Signals from a Language Model
In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals.
A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components.
Lexical Knowledge Internalization for Neural Dialog Generation
We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models.
Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation
Speech Emotion Recognition (SER) is a fundamental task to predict the emotion label from speech data.
An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer
Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task.
PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance.
Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
In this paper, we propose a new perspective for context-aware users' behavior modeling by including the whole page-wisely exposed products and the corresponding feedback as contextualized page-wise feedback sequence.
A Learning Convolutional Neural Network Approach for Network Robustness Prediction
Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors; 2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability; 3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations; 4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures.
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.
EEG based Emotion Recognition: A Tutorial and Review
Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.
RecursiveMix: Mixed Learning with History
In semantic segmentation, RM also surpasses the baseline and CutMix by 1. 9 and 1. 1 mIoU points under UperNet on ADE20K, respectively.
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.
A density peaks clustering algorithm with sparse search and K-d tree
It is proved that the algorithm can effectively reduce the computational complexity of the original DPC from $O(n^2K)$ to $O(n(n^{1-1/K}+k))$.
WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models
Motivated by the observation that model-free methods like behavioral retargeting (BR) and item-based collaborative filtering (ItemCF) hit different parts of the user-item relevance compared to neural sequential recommendation models, we propose a novel model-agnostic training approach called WSLRec, which adopts a three-stage framework: pre-training, top-$k$ mining, and fine-tuning.
Benchmarking of DL Libraries and Models on Mobile Devices
Deploying deep learning (DL) on mobile devices has been a notable trend in recent years.
Multi-modal Sensor Fusion for Auto Driving Perception: A Survey
Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers.
Forgery Attack Detection in Surveillance Video Streams Using Wi-Fi Channel State Information
The cybersecurity breaches expose surveillance video streams to forgery attacks, under which authentic streams are falsified to hide unauthorized activities.
Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems
As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks.
Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning
Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability.
Polyak-Ruppert-Averaged Q-Learning is Statistically Efficient
We study synchronous Q-learning with Polyak-Ruppert averaging (a. k. a., averaged Q-learning) in a $\gamma$-discounted MDP.
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation
Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively.
Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation
Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames.
Shallow geothermal energy potential for heating and cooling of buildings with regeneration under climate change scenarios
Shallow ground-source heat pumps (GSHPs) are a promising technology for contributing to the decarbonisation of the energy sector.
Reinforcement Learning Enhanced Explainer for Graph Neural Networks
To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning.
Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network
We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.
Generative Dynamic Patch Attack
Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods.
Improved Loss Function-Based Prediction Method of Extreme Temperatures in Greenhouses
By increasing the weight of extreme temperature samples and reducing the possibility of misjudging extreme temperature as normal, the proposed loss function can enhance the prediction results in extreme situations.
Unified Style Transfer
Currently, it is hard to compare and evaluate different style transfer algorithms due to chaotic definitions of style and the absence of agreed objective validation methods in the study of style transfer.
Video Instance Segmentation by Instance Flow Assembly
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
Reinforcement Learning (RL) can be considered as a sequence modeling task: given a sequence of past state-action-reward experiences, an agent predicts a sequence of next actions.
Feasible Architecture for Quantum Fully Convolutional Networks
Fully convolutional networks are robust in performing semantic segmentation, with many applications from signal processing to computer vision.
Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm.
Interpretable Multi-hop Reasoning for Forecasting Future Links on Temporal Knowledge Graphs
The interpretability of the current temporal KG forecasting models is manifested in providing the reasoning paths.
Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology
Furthermore, we show that KGSSL is relatively more robust to distortion than baseline methods, and outperforms the baseline model by 35\% when plugging in KGSSL inferred characteristics.
Fine-Grained Few Shot Learning with Foreground Object Transformation
As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks.
Cost-Effective Federated Learning in Mobile Edge Networks
Federated learning (FL) is a distributed learning paradigm that enables a large number of mobile devices to collaboratively learn a model under the coordination of a central server without sharing their raw data.
Statistical Estimation and Inference via Local SGD in Federated Learning
Both the methods are communication efficient and applicable to online data.
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Monocular depth estimation aims at predicting depth from a single image or video.
HITSZ-HLT at SemEval-2021 Task 5: Ensemble Sequence Labeling and Span Boundary Detection for Toxic Span Detection
This paper presents the winning system that participated in SemEval-2021 Task 5: Toxic Spans Detection.
RigNet: Repetitive Image Guided Network for Depth Completion
However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes
To achieve this, we treat the shape segmentation as a point labeling problem in the metric space.
THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS
Our solution focuses on solving two problems in automated audio captioning: data insufficiency and word selection indeterminacy.
Ranked #1 on
Audio captioning
on Clotho
(using extra training data)
A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning
Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.
PVT v2: Improved Baselines with Pyramid Vision Transformer
We hope this work will facilitate state-of-the-art Transformer researches in computer vision.
Ranked #57 on
Object Detection
on COCO minival
Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task.
The Image Local Autoregressive Transformer
To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.
Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions.
Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation
A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information.
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
Neural networks are susceptible to artificially designed adversarial perturbations.
Ranked #1 on
Adversarial Attack
on CIFAR-10
PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text.
Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.
Towards Multi-Scale Style Control for Expressive Speech Synthesis
This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis.
Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection
Predictive risk scores for COVID-19 severe outcomes ("CO-RISK" score) were derived from model output and evaluated on the testing dataset, as well as compared to human performance.
Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
Graph classification is a highly impactful task that plays a crucial role in a myriad of real-world applications such as molecular property prediction and protein function prediction. Aiming to handle the new classes with limited labeled graphs, few-shot graph classification has become a bridge of existing graph classification solutions and practical usage. This work explores the potential of metric-based meta-learning for solving few-shot graph classification. We highlight the importance of considering structural characteristics in the solution and propose a novel framework which explicitly considers global structure and local structure of the input graph.
Privacy-Preserving Distributed SVD via Federated Power
The low communication and computation power of such devices, and the possible privacy breaches of users' sensitive data make the computation of SVD challenging.
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.
Ranked #5 on
Semantic Segmentation
on SynPASS
vrCAPTCHA: Exploring CAPTCHA Designs in Virtual Reality
With the popularity of online access in virtual reality (VR) devices, it will become important to investigate exclusive and interactive CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) designs for VR devices.
Human-Computer Interaction
SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
Collaborative filtering has been largely used to advance modern recommender systems to predict user preference.
Bridging Unpaired Facial Photos And Sketches By Line-drawings
In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data.
Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications
In this work, we study a novel class of projection-based algorithms for linearly constrained problems (LCPs) which have a lot of applications in statistics, optimization, and machine learning.
Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos
Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.
Time Series
Video Forensics
Cryptography and Security
Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
We show that our Generative MMC (GMMC) can be trained discriminatively, generatively, or jointly for image classification and generation.
Box-To-Box Transformation for Modeling Joint Hierarchies
In Patel et al. (2020), the authors demonstrate that only the transitive reduction is required, and further extend box embeddings to capture joint hierarchies by augmenting the graph with new nodes.
Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types.
Cost-Effective Federated Learning Design
In this paper, we analyze how to design adaptive FL that optimally chooses these essential control variables to minimize the total cost while ensuring convergence.
Modeling Homophone Noise for Robust Neural Machine Translation
In this paper, we propose a robust neural machine translation (NMT) framework.
Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling
To strike a balance in this trade-off, we propose Elapsed-Time Sampling Delayed Feedback Model (ES-DFM), which models the relationship between the observed conversion distribution and the true conversion distribution.
Physics Guided Machine Learning Methods for Hydrology
The goal of this work is to incorporate our understanding of physical processes and constraints in hydrology into machine learning algorithms, and thus bridge the performance gap while reducing the need for large amounts of data compared to traditional data-driven approaches.
Neuron-level Structured Pruning using Polarization Regularizer
Experimentally, we show that structured pruning using polarization regularizer achieves much better results than using L1 regularizer.
Reading Comprehension as Natural Language Inference:A Semantic Analysis
We transform one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.
Deep Metric Learning-based Image Retrieval System for Chest Radiograph and its Clinical Applications in COVID-19
These results demonstrate our deep metric learning based image retrieval model is highly efficient in the CXR retrieval, diagnosis and prognosis, and thus has great clinical value for the treatment and management of COVID-19 patients.
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #54 on
Object Detection
on COCO test-dev
PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data
Further, this classifier is incorporated into the generative adversarial framework to help the generator to yield higher quality imputation results.
Retrieving and ranking short medical questions with two stages neural matching model
Internet hospital is a rising business thanks to recent advances in mobile web technology and high demand of health care services.
Finding the Near Optimal Policy via Adaptive Reduced Regularization in MDPs
Regularized MDPs serve as a smooth version of original MDPs.
3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds
In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds.
3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence
In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.
Reading Comprehension as Natural Language Inference: A Semantic Analysis
We transform the one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.
Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector
Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.
Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks
In recent years, the Natural Language Inference (NLI) task has garnered significant attention, with new datasets and models achieving near human-level performance on it.
Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration
To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process.
Object Detection in the Context of Mobile Augmented Reality
Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.
Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data
In this paper, we focus on nonlinear learning with kernels, and propose a federated doubly stochastic kernel learning (FDSKL) algorithm for vertically partitioned data.
Robust Image Matching By Dynamic Feature Selection
Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.
GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor
More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets.
FGRec: A Fine-Grained Point-of-Interest Recommendation Framework by Capturing Intrinsic Influences
Recent studies mainly utilize social information, categorical information and/or geographical information to supplement the highly sparse check-in data.
Simulating multi-exit evacuation using deep reinforcement learning
We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping.
Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task
This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair.
DeepTracking-Net: 3D Tracking with Unsupervised Learning of Continuous Flow
In this paper, we aim at handling the problem of 3D tracking, which provides the tracking of the consecutive frames of 3D shapes.
3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction
To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time.
Disentangling User Interest and Conformity for Recommendation with Causal Embedding
We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.
Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds
Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.
Few-shot Object Detection on Remote Sensing Images
In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories.
Unsupervised Learning of 3D Point Set Registration
Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment.
Geometry-Aware Segmentation of Remote Sensing Images via Implicit Height Estimation
Recent studies have shown the benefits of using additional elevation data (e. g., DSM) for enhancing the performance of the semantic segmentation of aerial images.
Modeling Discourse Structure for Document-level Neural Machine Translation
Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder.
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #101 on
Object Detection
on COCO test-dev
CAST: A Correlation-based Adaptive Spectral Clustering Algorithm on Multi-scale Data
We study the problem of applying spectral clustering to cluster multi-scale data, which is data whose clusters are of various sizes and densities.
FGCRec: Fine-Grained Geographical Characteristics Modeling for Point-of-Interest Recommendation
With the popularity of location-based social networks (LBSNs), Point-of-Interest (POI) recommendation has become an essential location-based service to help people explore novel locations.
Height estimation from single aerial images using a deep ordinal regression network
Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multi-view image matching.
Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features
Existing gait recognition approaches typically focus on learning identity features that are invariant to covariates (e. g., the carrying status, clothing, walking speed, and viewing angle) and seldom involve learning features from the covariate aspect, which may lead to failure modes when variations due to the covariate overwhelm those due to the identity.
Convolutional Neural Network for Behavioral Modeling and Predistortion of Wideband Power Amplifiers
We design a pre-designed filter using the convolutional layer to extract the basis functions required for the PA forward or reverse modeling.
One-Shot Object Detection without Fine-Tuning
Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited.
A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning
In aligning, we characterize the global and local structures of multiple labels to be high-rank and low-rank, respectively.
Airborne LiDAR Point Cloud Classification with Graph Attention Convolution Neural Network
To achieve point cloud classification, previous studies proposed point cloud deep learning models that can directly process raw point clouds based on PointNet-like architectures.
TEDL: A Text Encryption Method Based on Deep Learning
Firstly, both communication parties establish a word vector table by training a deep learning model according to specified hyperparameters.
Adversarial Multimodal Representation Learning for Click-Through Rate Prediction
Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations.
Communication-Efficient Distributed SVD via Local Power Iterations
As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments.
Representing Joint Hierarchies with Box Embeddings
Box Embeddings [Vilnis et al., 2018, Li et al., 2019] represent concepts with hyperrectangles in $n$-dimensional space and are shown to be capable of modeling tree-like structures efficiently by training on a large subset of the transitive closure of the WordNet hypernym graph.
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.