Search Results for author:
Found 345 papers, 134 papers with code
Image Representation Learning Using Graph Regularized Auto-Encoders
We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning.
Place classification with a graph regularized deep neural network model
Furthermore, results show that the features automatically learned from the raw input range data can achieve competitive results to the features constructed based on statistical and geometrical information.
Noise Robust IOA/CAS Speech Separation and Recognition System For The Third 'CHIME' Challenge
This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks
As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples.
Robust Object Tracking with a Hierarchical Ensemble Framework
A discriminative model which accounts for the matching degree of local patches is adopted via a bottom ensemble layer, and a generative model which exploits holistic templates is used to search for the object through the middle ensemble layer as well as an adaptive Kalman filter.
RISAS: A Novel Rotation, Illumination, Scale Invariant Appearance and Shape Feature
This paper presents a novel appearance and shape feature, RISAS, which is robust to viewpoint, illumination, scale and rotation variations.
Simple and Efficient Learning using Privileged Information
The Support Vector Machine using Privileged Information (SVM+) has been proposed to train a classifier to utilize the additional privileged information that is only available in the training phase but not available in the test phase.
Improved Recurrent Neural Networks for Session-based Recommendations
Recurrent neural networks (RNNs) were recently proposed for the session-based recommendation task.
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation
Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.
Real-time 3D Human Tracking for Mobile Robots with Multisensors
An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D).
Large Margin Object Tracking with Circulant Feature Maps
Structured output support vector machine (SVM) based tracking algorithms have shown favorable performance recently.
Robust Cost-Sensitive Learning for Recommendation with Implicit Feedback
Morever, the proposed algorithm can be scaled up to large-sized datasets after a relaxation.
Robust Visual SLAM with Point and Line Features
In this paper, we develop a robust efficient visual SLAM system that utilizes heterogeneous point and line features.
Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
Context is important for accurate visual recognition.
AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy
Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot.
SL$^2$MF: Predicting Synthetic Lethality in Human Cancers via Logistic Matrix Factorization
Moreover, we also incorporate biological knowledge about genes from protein-protein interaction (PPI) data and Gene Ontology (GO).
Adaptive Re-ranking of Deep Feature for Person Re-identification
First, we propose a Deep Feature Fusion (DFF) method to exploit the diverse information embedded in a deep feature.
Multi-Class Learning: From Theory to Algorithm
In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.
A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions
In Question Entity Discovery and Linking (QEDL) problem, traditional methods are challenged because multiple entities in one short question are difficult to be discovered entirely and the incomplete information in short text makes entity linking hard to implement.
Constructing Ontology-Based Cancer Treatment Decision Support System with Case-Based Reasoning
Disease Ontology (DO) that pertains to cancer's clinical stages and their corresponding information components is utilized to improve the reasoning ability of a decision support system (DSS).
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream.
Approach for Semi-automatic Construction of Anti-infective Drug Ontology Based on Entity Linking
Experiments show that our selected features have achieved a precision rate of 86. 77%, a recall rate of 89. 03% and an F1 score of 87. 89%.
Max-Diversity Distributed Learning: Theory and Algorithms
We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.
Very Long Term Field of View Prediction for 360-degree Video Streaming
In this work, we treat the FoV prediction as a sequence learning problem, and propose to predict the target user's future FoV not only based on the user's own past FoV center trajectory but also other users' future FoV locations.
Efficient Cross-Validation for Semi-Supervised Learning
In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).
Multi-Scale Quasi-RNN for Next Item Recommendation
To this end, architectural inductive biases such as Markov-Chains, Recurrent models, Convolutional networks and many others have demonstrated reasonable success on this task.
Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation
Interactive recommendation that models the explicit interactions between users and the recommender system has attracted a lot of research attentions in recent years.
Attention-based 3D Convolutional Network for Alzheimer’s Disease Diagnosis and Biomarkers Exploration
Modern advancements in deep learning provide a powerful framework for disease classification based on neuroimaging data.
An Evaluation of Transfer Learning for Classifying Sales Engagement Emails at Large Scale
Our results show that fine-tuning of the BERT model outperforms with as few as 300 labeled samples, but underperforms with fewer than 300 labeled samples, relative to all the feature-based approaches using different embeddings.
Recent Advances in Diversified Recommendation
With the rapid development of recommender systems, accuracy is no longer the only golden criterion for evaluating whether the recommendation results are satisfying or not.
Audio2Face: Generating Speech/Face Animation from Single Audio with Attention-Based Bidirectional LSTM Networks
We propose an end to end deep learning approach for generating real-time facial animation from just audio.
FReeNet: Multi-Identity Face Reenactment
This paper presents a novel multi-identity face reenactment framework, named FReeNet, to transfer facial expressions from an arbitrary source face to a target face with a shared model.
Converse Attention Knowledge Transfer for Low-Resource Named Entity Recognition
In the process of translation, CAN obtain the attention matrices that align the two languages.
Low Resource Named Entity Recognition
named-entity-recognition
+4
Towards Sharp Analysis for Distributed Learning with Random Features
In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.
PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning
The feature-encoding module encodes the short-term motion feature in an image pair, while the memory-propagating module captures the long-term motion feature in the consecutive image pairs.
Bandit Learning for Diversified Interactive Recommendation
Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions.
Multi-Instance Multi-Scale CNN for Medical Image Classification
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x, y (and also z in 3D images) dimensions.
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems
ASN characterizes different actions' influence on other agents using neural networks based on the action semantics between them.
PD-GAN: Adversarial Learning for Personalized Diversity-Promoting Recommendation
This paper proposes Personalized Diversity-promoting GAN (PD-GAN), a novel recommendation model to generate diverse, yet relevant recommendations.
Face-to-Parameter Translation for Game Character Auto-Creation
Character customization system is an important component in Role-Playing Games (RPGs), where players are allowed to edit the facial appearance of their in-game characters with their own preferences rather than using default templates.
PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud
In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud.
From Few to More: Large-scale Dynamic Multiagent Curriculum Learning
In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents.
Pose Estimation for Ground Robots: On Manifold Representation, Integration, Re-Parameterization, and Optimization
In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors.
LIC-Fusion: LiDAR-Inertial-Camera Odometry
This paper presents a tightly-coupled multi-sensor fusion algorithm termed LiDAR-inertial-camera fusion (LIC-Fusion), which efficiently fuses IMU measurements, sparse visual features, and extracted LiDAR points.
Robotics
Semi-supervised Vector-valued Learning: Improved Bounds and Algorithms
Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-task learning and transfer learning.
Automated Spectral Kernel Learning
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.
Automatic Data Augmentation by Learning the Deterministic Policy
By introducing an unified optimization goal, DeepAugNet intends to combine the data augmentation and the deep model training in an end-to-end training manner which is realized by simultaneously training a hybrid architecture of dueling deep Q-learning algorithm and a surrogate deep model.
Weighted Distributed Differential Privacy ERM: Convex and Non-convex
By detailed theoretical analysis, we show that in distributed setting, the noise bound and the excess empirical risk bound can be improved by considering different weights held by multiple parties.
Visual-Inertial Localization for Skid-Steering Robots with Kinematic Constraints
While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators.
Multi-Agent Game Abstraction via Graph Attention Neural Network
Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents.
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning
The proposed method is able to efficiently generalize the previously learned task by model fusion to solve the environment adaptation problem.
RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization
The proposed RoboCoDraw system takes a real human face image as input, converts it to a stylized avatar, then draws it with a robotic arm.
Robotics Graphics
Variational Quantum Circuits for Quantum State Tomography
We demonstrate our method by performing numerical simulations for the tomography of the ground state of a one-dimensional quantum spin chain, using a variational quantum circuit simulator.
AttentionAnatomy: A unified framework for whole-body organs at risk segmentation using multiple partially annotated datasets
Organs-at-risk (OAR) delineation in computed tomography (CT) is an important step in Radiation Therapy (RT) planning.
Input Perturbation: A New Paradigm between Central and Local Differential Privacy
By adding noise to the original training data and training with the `perturbed data', we achieve ($\epsilon$,$\delta$)-differential privacy on the final model, along with some kind of privacy on the original data.
Data Heterogeneity Differential Privacy: From Theory to Algorithm
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).
Convolutional Spectral Kernel Learning
Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.
Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
Meanwhile, we propose a M-bit Inputs and N-bit Weights Network (MINW-Net) trained by AQE, a quantized neural network with 1-3 bits weights and activations.
Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss and RKHS
However, the studies on learning theory for general loss functions and hypothesis spaces remain limited.
Nearly Optimal Clustering Risk Bounds for Kernel K-Means
In this paper, we study the statistical properties of kernel $k$-means and obtain a nearly optimal excess clustering risk bound, substantially improving the state-of-art bounds in the existing clustering risk analyses.
Extended Feature Pyramid Network for Small Object Detection
Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels.
Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
On the one hand, we adopt the deforming autoencoder to disentangle identity and pose representations.
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #2 on
Optical Flow Estimation
on KITTI 2012 unsupervised
A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
Furthermore, we also design a shift vector processing element (SVPE) array to replace all 16-bit multiplications with SHIFT operations in convolution operation on FPGAs.
Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
To make CNNs more invariant to transformations, we propose "Feature Lenses", a set of ad-hoc modules that can be easily plugged into a trained model (referred to as the "host model").
Learning Hierarchical Review Graph Representations for Recommendation
Therefore, they may not be effective in capturing the global dependency between words, and tend to be easily biased by noise review information.
Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation.
Towards Persona-Based Empathetic Conversational Models
To this end, we propose a new task towards persona-based empathetic conversations and present the first empirical study on the impact of persona on empathetic responding.
APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
Audio-guided face reenactment aims at generating photorealistic faces using audio information while maintaining the same facial movement as when speaking to a real person.
Hierarchical and Efficient Learning for Person Re-Identification
Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e. g. model size and latency, which are critical for practical application.
Collision-free Trajectory Planning for Autonomous Surface Vehicle
We apply a numerical optimization method in the back-end to generate the trajectory.
Robotics
Neural Architecture Optimization with Graph VAE
The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.
Dive Deeper Into Box for Object Detection
Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods.
Targetless Calibration of LiDAR-IMU System Based on Continuous-time Batch Estimation
Sensor calibration is the fundamental block for a multi-sensor fusion system.
Robotics
DTVNet: Dynamic Time-lapse Video Generation via Single Still Image
The proposed DTVNet consists of two submodules: \emph{Optical Flow Encoder} (OFE) and \emph{Dynamic Video Generator} (DVG).
LIC-Fusion 2.0: LiDAR-Inertial-Camera Odometry with Sliding-Window Plane-Feature Tracking
Only the tracked planar points belonging to the same plane will be used for plane initialization, which makes the plane extraction efficient and robust.
Robotics
Semantic Graph Based Place Recognition for 3D Point Clouds
First, we propose a novel semantic graph representation for the point cloud scenes by reserving the semantic and topological information of the raw point cloud.
Frequency Response Study on the ERCOT under High Photovoltaic (PV) Penetration Conditions
Solar photovoltaic (PV) generation is growing rapidly around the world.
F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking
A main challenge in 3D single object tracking is how to reduce search space for generating appropriate 3D candidates.
Pre-training Graph Transformer with Multimodal Side Information for Recommendation
Side information of items, e. g., images and text description, has shown to be effective in contributing to accurate recommendations.
APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment
Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio.
CL-MAPF: Multi-Agent Path Finding for Car-Like Robots with Kinematic and Spatiotemporal Constraints
In this paper, we give a mathematical formalization of Multi-Agent Path Finding for Car-Like robots (CL-MAPF) problem.
Robotics Multiagent Systems
Moving Forward in Formation: A Decentralized Hierarchical Learning Approach to Multi-Agent Moving Together
We also deploy and validate our method in a real world scenario.
Robotics Multiagent Systems
HILONet: Hierarchical Imitation Learning from Non-Aligned Observations
In this work, we propose a new imitation learning approach called Hierarchical Imitation Learning from Observation(HILONet), which adopts a hierarchical structure to choose feasible sub-goals from demonstrated observations dynamically.
Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain
Specifically, FP-GANs firstly divides an MR image into low-frequency global approximation and high-frequency anatomical texture in wavelet domain.
DLPAlign: A Deep Learning based Progressive Alignment Method for Multiple Protein Sequences
This paper proposed a novel and straightforward approach to improve the accuracy of progressive multiple protein sequence alignment method.
Ranked #1 on
Multiple Sequence Alignment
on OXBench
HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
To obtainmore accurate depth estimation in large gradient regions, itis necessary to obtain high-resolution features with spatialand semantic information.
Ranked #7 on
Unsupervised Monocular Depth Estimation
on KITTI-C
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability.
FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion
Then, a refined depth map is further obtained using a residual learning strategy in the coarse-to-fine stage with a coarse depth map and color image as input.
Keyword-Guided Neural Conversational Model
We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast.
Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
State-of-the-art CNN segmentation models apply either 2D or 3D convolutions on input images, with pros and cons associated with each method: 2D convolution is fast, less memory-intensive but inadequate for extracting 3D contextual information from volumetric images, while the opposite is true for 3D convolution.
CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth
In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings.
A Hybrid Bandit Framework for Diversified Recommendation
Previous interactive recommendation methods primarily focus on learning users' personalized preferences on the relevance properties of an item set.
Fast Estimation for Privacy and Utility in Differentially Private Machine Learning
In this paper, we deduce the influence of $\epsilon$ on utility private learning models through strict mathematical derivation, and propose a novel approximate approach for estimating the utility of any $\epsilon$ value.
Effective Distributed Learning with Random Features: Improved Bounds and Algorithms
In this paper, we study the statistical properties of distributed kernel ridge regression together with random features (DKRR-RF), and obtain optimal generalization bounds under the basic setting, which can substantially relax the restriction on the number of local machines in the existing state-of-art bounds.
Optimizing Quantized Neural Networks with Natural Gradient
Quantized Neural Networks (QNNs) have achieved an enormous step in improving computational efficiency, making it possible to deploy large models to mobile and miniaturized devices.
RFNet: Recurrent Forward Network for Dense Point Cloud Completion
The RFE extracts multiple global features from the incomplete point clouds for different recurrent levels, and the FDC generates point clouds in a coarse-to-fine pipeline.
Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning
In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning.
Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.
One-shot Face Reenactment Using Appearance Adaptive Normalization
The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.
Large topological Hall effect near room temperature in noncollinear ferromagnet LaMn2Ge2 single crystal
Non-trivial spin structures in itinerant magnets can give rise to topological Hall effect (THE) due to the interacting local magnetic moments and conductive electrons.
Strongly Correlated Electrons
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models.
Ranked #3 on
Transferability
on classification benchmark
A Quantitative Metric for Privacy Leakage in Federated Learning
In addition, using the proposed metric, we investigate the influential factors of risk level.
DeepMI: Deep Multi-lead ECG Fusion for Identifying Myocardial Infarction and its Occurrence-time
We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level.
Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training
The pre-trained neural models have recently achieved impressive performances in understanding multimodal content.
Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.
KECRS: Towards Knowledge-Enriched Conversational Recommendation System
The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions.
Medical Image Segmentation Using Squeeze-and-Expansion Transformers
Medical image segmentation is important for computer-aided diagnosis.
Ranked #1 on
Brain Tumor Segmentation
on BRATS 2019
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.
TransVOS: Video Object Segmentation with Transformers
Recently, Space-Time Memory Network (STM) based methods have achieved state-of-the-art performance in semi-supervised video object segmentation (VOS).
Concurrent Adversarial Learning for Large-Batch Training
Current methods usually use extensive data augmentation to increase the batch size, but we found the performance gain with data augmentation decreases as batch size increases, and data augmentation will become insufficient after certain point.
Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID).
SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure
LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue.
SSC: Semantic Scan Context for Large-Scale Place Recognition
We also present a two-step global semantic ICP to obtain the 3D pose (x, y, yaw) used to align the point cloud to improve matching performance.
Ranked #1 on
Visual Place Recognition
on KITTI
SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.
Few-Shot Domain Adaptation with Polymorphic Transformers
Thus, the chance of overfitting the annotations is greatly reduced, and the model can perform robustly on the target domain after being trained on a few annotated images.
Improved Learning Rates for Stochastic Optimization: Two Theoretical Viewpoints
the sample size $n$ for ERM and SGD with milder assumptions in convex learning and similar high probability rates of order $\mathcal{O} (1/n)$ in nonconvex learning, rather than in expectation.
Adaptive Course Recommendation System
In this paper, we propose a novel course recommendation framework, named Dynamic Attention and hierarchical Reinforcement Learning (DARL), to improve the adaptivity of the recommendation model.
Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction
Then two hypergraphs are constructed from the latent representations and the adversarial network based on graph convolution is employed to narrow the distribution difference of hyperedge features.
Characterization Multimodal Connectivity of Brain Network by Hypergraph GAN for Alzheimer's Disease Analysis
Using multimodal neuroimaging data to characterize brain network is currently an advanced technique for Alzheimer's disease(AD) Analysis.
A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
Fusing medical images and the corresponding 3D shape representation can provide complementary information and microstructure details to improve the operational performance and accuracy in brain surgery.
3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image
A branching predictor and several hierarchical attention pipelines are constructed to generate point clouds that accurately describe the incomplete images and then complete these point clouds with high quality.
Go Wider Instead of Deeper
To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or model compressing along with the depth.
Ranked #663 on
Image Classification
on ImageNet
Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation
Meanwhile, to guarantee that the day and night images contain the same information, the domain-separated network takes the day-time images and corresponding night-time images (generated by GAN) as input, and the private and invariant feature extractors are learned by orthogonality and similarity loss, where the domain gap can be alleviated, thus better depth maps can be expected.
ActionCLIP: A New Paradigm for Video Action Recognition
Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune".
Ranked #2 on
Action Recognition In Videos
on Kinetics-400
A Survey on Reinforcement Learning for Recommender Systems
To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems.
Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds
Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information.
Ranked #4 on
3D Semantic Scene Completion
on SemanticKITTI
Up-to-Down Network: Fusing Multi-Scale Context for 3D Semantic Scene Completion
An efficient 3D scene perception algorithm is a vital component for autonomous driving and robotics systems.
Ranked #6 on
3D Semantic Scene Completion
on SemanticKITTI
Manifold Micro-Surgery with Linearly Nearly Euclidean Metrics
The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular.
Riemannian Manifold Embeddings for Straight-Through Estimator
Quantized Neural Networks (QNNs) aim at replacing full-precision weights $\boldsymbol{W}$ with quantized weights $\boldsymbol{\hat{W}}$, which make it possible to deploy large models to mobile and miniaturized devices easily.
Geometry-Entangled Visual Semantic Transformer for Image Captioning
However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement.
Sharpness-Aware Minimization in Large-Batch Training: Training Vision Transformer In Minutes
Large-batch training is an important direction for distributed machine learning, which can improve the utilization of large-scale clusters and therefore accelerate the training process.
Mask and Understand: Evaluating the Importance of Parameters
Influence functions are classic techniques from robust statistics based on first-order Taylor approximations that have been widely used in the machine learning community to estimate small perturbations of datasets accurately to the model.
Improved Generalization Risk Bounds for Meta-Learning with PAC-Bayes-kl Analysis
In particular, we identify that when the number of training task is large, utilizing a prior generated from an informative hyperposterior can achieve the same order of PAC-Bayes-kl bound as that obtained through setting a localized distribution-dependent prior for a novel task.
High Probability Generalization Bounds for Minimax Problems with Fast Rates
In this paper, we provide improved generalization analyses for almost all existing generalization measures of minimax problems, which enables the minimax problems to establish sharper bounds of order $\mathcal{O}\left( 1/n \right)$, significantly, with high probability.
Inductive Representation Learning in Temporal Networks via Mining Neighborhood and Community Influences
Therefore, we propose a new inductive network representation learning method called MNCI by mining neighborhood and community influences in temporal networks.
A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Disease
The proposed model can evaluate characteristics of abnormal brain connections at different stages of Alzheimer's disease, which is helpful for cognitive disease study and early treatment.
DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease
In this work, a novel decoupling generative adversarial network (DecGAN) is proposed to detect abnormal neural circuits for AD.
Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation
In this paper, we propose a novel explanation generation framework, named Hierarchical Aspect-guided explanation Generation (HAG), for explainable recommendation.
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
(2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top $K$ ranked PTMs via a Bayesian procedure that we propose.
Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking
Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions.
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation
Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary.
Ranked #3 on
Instance Segmentation
on LVIS v1.0 val
Learning Rates for Nonconvex Pairwise Learning
We first successfully establish learning rates for these algorithms in a general nonconvex setting, where the analysis sheds insights on the trade-off between optimization and generalization and the role of early-stopping.
A layer-stress learning framework universally augments deep neural network tasks
Here we presented a layer-stress deep learning framework (x-NN) which implemented automatic and wise depth decision on shallow or deep feature map in a deep network through firstly designing enough number of layers and then trading off them by Multi-Head Attention Block.
Thoughts on the Consistency between Ricci Flow and Neural Network Behavior
During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.
Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application
Benefiting from the strong ability of the pre-trained model, the research on Chinese Word Segmentation (CWS) has made great progress in recent years.
MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation
Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions.
Ranked #1 on
Referring Expression Segmentation
on G-Ref test B
Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN
In this work, a novel Multidirectional Perception Generative Adversarial Network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages.
Refined Learning Bounds for Kernel and Approximate $k$-Means
In this paper, we study the statistical properties of kernel $k$-means and Nystr\"{o}m-based kernel $k$-means, and obtain optimal clustering risk bounds, which improve the existing risk bounds.
Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation
In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation.
Towards Sharper Generalization Bounds for Structured Prediction
In the smoothness scenario, we provide generalization bounds that are not only a logarithmic dependency on the label set cardinality but a faster convergence rate of order $\mathcal{O}(\frac{1}{n})$ on the sample size $n$.
MSP : Refine Boundary Segmentation via Multiscale Superpixel
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
Searching Parameterized AP Loss for Object Detection
In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Network
To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild.
Dynamically Stable Poincaré Embeddings for Neural Manifolds
As a result, we prove that, if initial metrics have an $L^2$-norm perturbation which deviates from the Hyperbolic metric on the Poincar\'e ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric.
Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase
However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views.
Robust photon-efficient imaging using a pixel-wise residual shrinkage network
Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios.
Deep Domain Adversarial Adaptation for Photon-efficient Imaging
Photon-efficient imaging with the single-photon light detection and ranging (LiDAR) captures the three-dimensional (3D) structure of a scene by only a few detected signal photons per pixel.
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.
Lightweight Object-level Topological Semantic Mapping and Long-term Global Localization based on Graph Matching
In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness.
A Survey of Visual Sensory Anomaly Detection
In this survey, we are the first one to provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.
Guide Local Feature Matching by Overlap Estimation
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important.
Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance.
Ranked #39 on
Anomaly Detection
on MVTec AD
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
Towards Efficient and Scalable Sharpness-Aware Minimization
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers.
Region-Aware Face Swapping
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction.
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images.
Ranked #9 on
Optical Flow Estimation
on KITTI 2015 (train)
Stability and Generalization of Differentially Private Minimax Problems
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
Sharper Utility Bounds for Differentially Private Models
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
Understanding the Generalization Performance of Spectral Clustering Algorithms
The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance.
Ridgeless Regression with Random Features
Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.
UniInst: Unique Representation for End-to-End Instance Segmentation
Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e. g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions.
Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.
Enhancing Sequential Recommendation with Graph Contrastive Learning
Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.
Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.
Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.
Bootstrap Latent Representations for Multi-modal Recommendation
Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e. g., user-user or item-item relation graph) to augment the learned representations of users and/or items.
Learning Quality-aware Dynamic Memory for Video Object Segmentation
However, they mainly focus on better matching between the current frame and the memory frames without explicitly paying attention to the quality of the memory.
Ranked #11 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
(using extra training data)
E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context
However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance.
Ranked #4 on
Video Reconstruction
on UVG
Adaptive Assignment for Geometry Aware Local Feature Matching
The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance.
Layer-refined Graph Convolutional Networks for Recommendation
Specifically, these models usually aggregate all layer embeddings for node updating and achieve their best recommendation performance within a few layers because of over-smoothing.
DA$^2$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping
In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects.
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
ATPL: Mutually enhanced adversarial training and pseudo labeling for unsupervised domain adaptation
Accordingly, ATPL will use the pseudo-labeled information to improve the adversarial training process, which can guarantee the feature transferability by generating adversarial data to fill in the domain gap.
Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective
However, there still lack efforts to evaluate the robustness of such CF systems in deployment.
Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging.
Scatter Points in Space: 3D Detection from Multi-view Monocular Images
3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision.
Exemplar-Based Image Colorization with A Learning Framework
This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image.
Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.
Localizing Anatomical Landmarks in Ocular Images using Zoom-In Attentive Networks
Therefore, localization has its unique challenges different from segmentation or detection.
Mask-Guided Image Person Removal with Data Synthesis
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains.
Generative Model Watermarking Based on Human Visual System
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.
Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals
Edge caching plays an increasingly important role in boosting user content retrieval performance while reducing redundant network traffic.
Inductive Graph Transformer for Delivery Time Estimation
Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences.
Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images
Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed.
