Search Results for author:
Found 86 papers, 18 papers with code
Collaborative Memory Network for Recommendation Systems
We propose Collaborative Memory Networks (CMN), a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based structure in a nonlinear fashion.
Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds
In this paper, we propose a novel method to learn consistency-aware unsigned distance functions directly from raw point clouds.
Variational Deep Semantic Hashing for Text Documents
Especially, deep generative models naturally combine the expressiveness of probabilistic generative models with the high capacity of deep neural networks, which is very suitable for text modeling.
Ranked #1 on
Supervised Text Retrieval
on Reuters-21578
Non-Rigid Point Set Registration Networks
In contrast, the proposed point registration neural network (PR-Net) actively learns the registration pattern as a parametric function from a training dataset, consequently predict the desired geometric transformation to align a pair of point sets.
Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver.
Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration
In contrast to previous efforts (e. g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process.
HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.
Ranked #2 on
Surface Normals Estimation
on PCPNet
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds
To address this problem, we present a novel and efficient self-supervised point cloud representation learning framework, named 3D Occlusion Auto-Encoder (3D-OAE), to facilitate the detailed supervision inherited in local regions and global shapes.
Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation
In this way, the categorization of each point is conditioned on its local semantic pattern.
FairCLIP: Harnessing Fairness in Vision-Language Learning
Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions.
Dual Attention Guided Gaze Target Detection in the Wild
In the third stage, we use the generated dual attention as guidance to perform two sub-tasks: (1) identifying whether the gaze target is inside or out of the image; (2) locating the target if inside.
Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration
To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment.
SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds
In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.
SHREC 2022: Protein-ligand binding site recognition
This paper presents the methods that have participated in the SHREC 2022 contest on protein-ligand binding site recognition.
NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.
Neural Gradient Learning and Optimization for Oriented Point Normal Estimation
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.
Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services
Finally, we apply ESLE to seek new service ports for NTT DOCOMO's bike share services operated in Japan.
MOEA/D with Angle-based Constrained Dominance Principle for Constrained Multi-objective Optimization Problems
The experimental results manifest that MOEA/D-ACDP is significantly better than the other four CMOEAs on these test instances and the real-world case, which indicates that ACDP is more effective for solving CMOPs.
ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
Arbitrary-oriented text detection in the wild is a very challenging task, due to the aspect ratio, scale, orientation, and illumination variations.
3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
In this paper, powered with a novel design of adversarial networks (3D-A-Nets), we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address the challenging issues of efficient and effective 3D volumetric data processing.
Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning
Recent advancements in deep learning opened new opportunities for learning a high-quality 3D model from a single 2D image given sufficient training on large-scale data sets.
An Improved Epsilon Constraint-handling Method in MOEA/D for CMOPs with Large Infeasible Regions
In order to evaluate the performance of MOEA/D-IEpsilon, a new set of CMOPs with two and three objectives is designed, having large infeasible regions (relative to the feasible regions), and they are called LIR-CMOPs.
Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval
Due to the large cross-modality discrepancy between 2D sketches and 3D shapes, retrieving 3D shapes by sketches is a significantly challenging task.
DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval
Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning.
3D Deep Shape Descriptor
Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category.
Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence
Different from these real-valued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence.
Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval
For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation.
Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter
This paper focuses on robotic picking tasks in cluttered scenario.
Structure-Attentioned Memory Network for Monocular Depth Estimation
To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.
Ranked #48 on
Monocular Depth Estimation
on KITTI Eigen split
Learning Object-specific Distance from a Monocular Image
Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving.
Self-Supervised Learning of Depth and Ego-motion with Differentiable Bundle Adjustment
Learning to predict scene depth and camera motion from RGB inputs only is a challenging task.
Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification
Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.
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.
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.
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.
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.
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.
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.
Meta Deformation Network: Meta Functionals for Shape Correspondence
We present a new technique named "Meta Deformation Network" for 3D shape matching via deformation, in which a deep neural network maps a reference shape onto the parameters of a second neural network whose task is to give the correspondence between a learned template and query shape via deformation.
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.
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.
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.
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.
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.
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.
Design and Performance Analysis of a New STBC-MIMO LoRa System
The result demonstrates that the diversity order of the system in the imperfect CSI scenario with fixed channel estimate error variance is zero.
Correction to the photometric magnitudes of the Gaia Early Data Release 3
In this letter, we have carried out an independent validation of the Gaia EDR3 photometry using about 10, 000 Landolt standard stars from Clem & Landolt (2013).
Solar and Stellar Astrophysics Astrophysics of Galaxies
A New Frequency-Bin-Index LoRa System for High-Data-Rate Transmission: Design and Performance Analysis
To further improve the system flexibility, we formulate a generalized modulation scheme and propose scheme II by treating the SFB groups as an additional type of transmission entity.
G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.
Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.
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.
ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation
Lane segmentation is a challenging issue in autonomous driving system designing because lane marks show weak textural consistency due to occlusion or extreme illumination but strong geometric continuity in traffic images, from which general convolution neural networks (CNNs) are not capable of learning semantic objects.
3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers.
3D Unsupervised Region-Aware Registration Transformer
This paper concerns the research problem of point cloud registration to find the rigid transformation to optimally align the source point set with the target one.
Meta-Learning 3D Shape Segmentation Functions
We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions.
3D Meta-Registration: Meta-learning 3D Point Cloud Registration Functions
Learning robust 3D point cloud registration functions with deep neural networks has emerged as a powerful paradigm in recent years, offering promising performance in producing spatial geometric transformations for each pair of 3D point clouds.
Contrastive Learning of 3D Shape Descriptor with Dynamic Adversarial Views
In addition, CoLAV introduces a novel mechanism for the dynamic generation of shape-instance-dependent adversarial views as positive pairs to adversarially train robust contrastive learning models towards the learning of more informative 3D shape representation.
Adaptive Wavelet Transformer Network for 3D Shape Representation Learning
We present a novel method for 3D shape representation learning using multi-scale wavelet decomposition.
3D Meta-Segmentation Neural Network
Based on the learned information of task distribution, our meta part segmentation learner is able to dynamically update the part segmentation learner with optimal parameters which enable our part segmentation learner to rapidly adapt and have great generalization ability on new part segmentation tasks.
Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network
However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.
Network-Aware 5G Edge Computing for Object Detection: Augmenting Wearables to "See" More, Farther and Faster
The vision evaluation is combined with a detailed full-stack wireless network simulation to determine the distribution of throughputs and delays with real navigation paths and ray-tracing from new high-resolution 3D models in an urban environment.
WebFormer: The Web-page Transformer for Structure Information Extraction
Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price.
A Multi-task Learning Framework for Product Ranking with BERT
The proposed model utilizes domain-specific BERT with fine-tuning to bridge the vocabulary gap and employs multi-task learning to optimize multiple objectives simultaneously, which yields a general end-to-end learning framework for product search.
Space Layout of Low-entropy Hydration Shells Guides Protein Binding
According to an analysis of determined protein complex structures, shape matching between the largest low-entropy hydration shell region of a protein and that of its partner at the binding sites is revealed as a regular pattern.
Deep Partial Multiplex Network Embedding
Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks.
DIANES: A DEI Audit Toolkit for News Sources
Professional news media organizations have always touted the importance that they give to multiple perspectives.
Multi-organ Segmentation Network with Adversarial Performance Validator
The proposed network organically converts the 2D-coarse result to 3D high-quality segmentation masks in a coarse-to-fine manner, allowing joint optimization to improve segmentation accuracy.
The low-entropy hydration shell at the binding site of spike RBD determines the contagiousness of SARS-CoV-2 variants
The low-entropy level of hydration shells at the binding site of a spike protein is found to be an important indicator of the contagiousness of the coronavirus.
Reconfigurable Intelligent Surface-aided $M$-ary FM-DCSK System: a New Design for Noncoherent Chaos-based Communication
In this paper, we propose two reconfigurable intelligent surface-aided $M$-ary frequency-modulated differential chaos shift keying (RIS-$M$-FM-DCSK) schemes.
Perceptual Quality Assessment of Omnidirectional Images
The original and distorted omnidirectional images, subjective quality ratings, and the head and eye movement data together constitute the OIQA database.
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Detect and Approach: Close-Range Navigation Support for People with Blindness and Low Vision
These functions enable the system to suggest an initial navigation path, continuously update the path as the user moves, and offer timely recommendation about the correction of the user's path.
Dynamic Write-Voltage Design and Read-Voltage Optimization for MLC NAND Flash Memory
To mitigate the impact of noise and interference on multi-level-cell (MLC) flash memory with the use of low-density parity-check (LDPC) codes, we propose a dynamic write-voltage design scheme considering the asymmetric property of raw bit error rate (RBER), which can obtain the optimal write voltage by minimizing a cost function.
Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance
We further assess the impact of the distance of an object to the camera on the detection accuracy and show that higher spatial resolution enables a greater detection range.
LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes
To capture geometry details, current mainstream methods divide 3D shapes into local regions and then learn each one with a local latent code via a decoder, where the decoder shares the geometric similarities among different local regions.
Revisiting Fine-Tuning Strategies for Self-supervised Medical Imaging Analysis
In this paper, we present the first comprehensive study that discovers effective fine-tuning strategies for self-supervised learning in medical imaging.
FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scaling
To address this research gap, we conduct the first comprehensive study on the fairness of 3D medical imaging models across multiple protected attributes.
VisPercep: A Vision-Language Approach to Enhance Visual Perception for People with Blindness and Low Vision
By combining the prompt and input image, a large vision-language model (i. e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt.
MemoryCompanion: A Smart Healthcare Solution to Empower Efficient Alzheimer's Care Via Unleashing Generative AI
With the rise of Large Language Models (LLMs), notably characterized by GPT frameworks, there emerges a catalyst for novel healthcare applications.
How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?
In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently shown impressive performance.
Mathematical Foundation and Corrections for Full Range Head Pose Estimation
This paper presents (1) code and algorithms for inferring coordinate system from provided source code, code for Euler angle application order and extracting precise rotation matrices and the Euler angles, (2) code and algorithms for converting poses from one rotation system to another, (3) novel formulae for 2D augmentations of the rotation matrices, and (4) derivations and code for the correct drawing routines for rotation matrices and poses.
Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers
The integration of Large Language Models (LLMs) in information retrieval has raised a critical reevaluation of fairness in the text-ranking models.
Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models
Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs.
Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation
To address this issue, we formulate the cross-receiver RFFI as a model adaptation problem, which adapts the trained model to unlabeled signals from a new receiver.
