Search Results for author:
Found 46 papers, 11 papers with code
Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs.
TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization
We propose an optimal viewpoint selection strategy, that finds the most miniature set of viewpoints covering all the faces of a mesh.
LEO- and RIS-Empowered User Tracking: A Riemannian Manifold Approach
To address inherent challenges including nonlinear observation function, constrained UE state, and unknown observation statistics, we develop a Riemannian manifold-based unscented Kalman filter (UKF) method.
PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval
In the field of urban planning, general-purpose large language models often struggle to meet the specific needs of planners.
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.
Ranked #1 on
Recommendation Systems
on MovieLens 20M
(HR@10 (full corpus) metric)
GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA).
LEO Satellite and RIS: Two Keys to Seamless Indoor and Outdoor Localization
By leveraging the strong signal reception of the LEO satellite signals and capitalizing on the radio environment-reshaping capability of RISs, the integration of these two technologies presents a vision of a future where localization services transcend existing constraints.
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
This paper presents GIR, a 3D Gaussian Inverse Rendering method for relightable scene factorization.
Dynamic Fault Analysis in Substations Based on Knowledge Graphs
To address the challenge of identifying hidden danger in substations from unstructured text, a novel dynamic analysis method is proposed.
Tactile Active Inference Reinforcement Learning for Efficient Robotic Manipulation Skill Acquisition
In this study, we propose a novel method for skill learning in robotic manipulation called Tactile Active Inference Reinforcement Learning (Tactile-AIRL), aimed at achieving efficient training.
Beamforming Design and Performance Evaluation for RIS-aided Localization using LEO Satellite Signals
The growing availability of low-Earth orbit (LEO) satellites, coupled with the anticipated widespread deployment of reconfigurable intelligent surfaces (RISs), opens up promising prospects for new localization paradigms.
What are Public Concerns about ChatGPT? A Novel Self-Supervised Neural Topic Model Tells You
The recently released artificial intelligence conversational agent, ChatGPT, has gained significant attention in academia and real life.
Attitude Determination in Urban Canyons: A Synergy between GNSS and 5G Observations
The tight fusion of the GNSS and the 5G observations results in a unique hybrid integer- and orthonormality-constrained optimization problem.
HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation
In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models.
Revisiting Neural Retrieval on Accelerators
A key component of retrieval is to model (user, item) similarity, which is commonly represented as the dot product of two learned embeddings.
Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
Kernelized Stein discrepancy (KSD) is a score-based discrepancy widely used in goodness-of-fit tests.
MTrainS: Improving DLRM training efficiency using heterogeneous memories
In Deep Learning Recommendation Models (DLRM), sparse features capturing categorical inputs through embedding tables are the major contributors to model size and require high memory bandwidth.
5G-Aided RTK Positioning in GNSS-Deprived Environments
This paper considers the localization problem in a 5G-aided global navigation satellite system (GNSS) based on real-time kinematic (RTK) technique.
A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based Testing
We prove a convergence theorem for U-statistics of degree two, where the data dimension $d$ is allowed to scale with sample size $n$.
Learning the Network of Graphs for Graph Neural Networks
Our model solves the first issue by simultaneously learning multiple relation graphs of data samples as well as a relation network of graphs, and solves the second and the third issue by selecting important data features as well as important data sample relations.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Instantaneous GNSS Ambiguity Resolution and Attitude Determination via Riemannian Manifold Optimization
Given the characteristics of the employed nonlinear constraints, we formulate GNSS attitude determination as an optimization problem on a manifold.
Grassmann Stein Variational Gradient Descent
Stein variational gradient descent (SVGD) is a deterministic particle inference algorithm that provides an efficient alternative to Markov chain Monte Carlo.
Machine Learning in Heterogeneous Porous Materials
The "Workshop on Machine learning in heterogeneous porous materials" brought together international scientific communities of applied mathematics, porous media, and material sciences with experts in the areas of heterogeneous materials, machine learning (ML) and applied mathematics to identify how ML can advance materials research.
Constrained Wrapped Least Squares: A Tool for High Accuracy GNSS Attitude Determination
Attitude determination is a popular application of Global Navigation Satellite Systems (GNSS).
A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems
To address this problem, existing methods partition the overall DPDP into fixed-size sub-problems by caching online generated orders and solve each sub-problem, or on this basis to utilize the predicted future orders to optimize each sub-problem further.
Cross-Region Domain Adaptation for Class-level Alignment
To cope with this, we propose a method that applies adversarial training to align two feature distributions in the target domain.
Ranked #1 on
Domain Adaptation
on Synscapes-to-Cityscapes
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
To consider if and how well we can utilize such information stored in RAW-format images for image matching, we have created a new dataset named MID (matching in the dark).
3D High-Fidelity Mask Face Presentation Attack Detection Challenge
The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers.
Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection
To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask).
Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models
Deep learning recommendation models (DLRMs) are used across many business-critical services at Facebook and are the single largest AI application in terms of infrastructure demand in its data-centers.
TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models
TT-Rec achieves 117 times and 112 times model size compression, for Kaggle and Terabyte, respectively.
Pushing the Envelope of Thin Crack Detection
We experimentally show that this makes it possible to detect cracks from an image of one-third the resolution of images used for annotation with about the same accuracy.
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination
This paper presents a novel end-to-end framework for low-rank tensorized training of neural networks.
Bayesian Probabilistic Numerical Integration with Tree-Based Models
The advantages and disadvantages of this new methodology are highlighted on a set of benchmark tests including the Genz functions, and on a Bayesian survey design problem.
A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
We also propose a novel Poisson-blending Generative Adversarial Network (Poisson GAN) and an efficient object detection network (AquaNet) to address two common issues within related datasets: the class-imbalance problem and the problem of mass small object, respectively.
A Compared Study Between Some Subspace Based Algorithms
The technology of face recognition has made some progress in recent years.
2DR1-PCA and 2DL1-PCA: two variant 2DPCA algorithms based on none L2 norm
In this paper, two novel methods: 2DR1-PCA and 2DL1-PCA are proposed for face recognition.
Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network
The employment of convolutional neural networks has achieved unprecedented performance in the task of image restoration for a variety of degradation factors.
Learning Shape-Motion Representations from Geometric Algebra Spatio-Temporal Model for Skeleton-Based Action Recognition
Skeleton-based action recognition has been widely applied in intelligent video surveillance and human behavior analysis.
Ranked #88 on
Skeleton Based Action Recognition
on NTU RGB+D
Evaluating Artificial Systems for Pairwise Ranking Tasks Sensitive to Individual Differences
There is another type of tasks for which what to predict is human perception itself, in which there are often individual differences.
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
In this paper, we study design of deep neural networks for tasks of image restoration.
Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions
There are many different types of distortion which affect image quality.
Data Augmentation for Robust Keyword Spotting under Playback Interference
Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents.
Feature Quantization for Defending Against Distortion of Images
In this work, we address the problem of improving robustness of convolutional neural networks (CNNs) to image distortion.
Integrating Deep Features for Material Recognition
We propose a method for integration of features extracted using deep representations of Convolutional Neural Networks (CNNs) each of which is learned using a different image dataset of objects and materials for material recognition.
