Search Results for author:
Found 62 papers, 28 papers with code
LightFC-X: Lightweight Convolutional Tracker for RGB-X Tracking
To alleviate this problem, we propose LightFC-X, a family of lightweight convolutional RGB-X trackers that explores a unified convolutional architecture for lightweight multimodal tracking.
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models.
EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance
However, these approaches often produce biased distributions of important tokens due to the influence of accumulated attention scores or positional encoding.
Convergence analysis of wide shallow neural operators within the framework of Neural Tangent Kernel
Neural operators are aiming at approximating operators mapping between Banach spaces of functions, achieving much success in the field of scientific computing.
UniDrive: Towards Universal Driving Perception Across Camera Configurations
We further propose a virtual configuration optimization method by minimizing the expected projection error between original cameras and virtual cameras.
Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations
MaTAV is with the advantages of aligning unimodal features to ensure consistency across different modalities and handling long input sequences to better capture contextual multimodal information.
A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting
Continuous blood pressure (BP) monitoring is essential for timely diagnosis and intervention in critical care settings.
Component Fourier Neural Operator for Singularly Perturbed Differential Equations
Solving Singularly Perturbed Differential Equations (SPDEs) poses computational challenges arising from the rapid transitions in their solutions within thin regions.
Knowledge-data fusion oriented traffic state estimation: A stochastic physics-informed deep learning approach
Physics-informed deep learning (PIDL)-based models have recently garnered remarkable success in traffic state estimation (TSE).
Inversion-DeepONet: A Novel DeepONet-Based Network with Encoder-Decoder for Full Waveform Inversion
The success of DL-FWI relies significantly on the quantity and diversity of the datasets.
U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training
As for the detrimental effect of underwater color cast noise, recent underwater object detectors make network architecture or training complex, which also hinders their application and deployment on underwater vehicle platforms.
Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
In this work, we provide the convergence analysis of natural gradient descent (NGD) in training two-layer PINNs, demonstrating that the learning rate can be $\mathcal{O}(1)$, and at this rate, the convergence rate is independent of the Gram matrix.
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs.
Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
In this paper, we provide convergence analysis for the IGD in training over-parameterized two-layer PINNs.
Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning
Additionally, a multi-scale Transformer denoising module is constructed to leverage multi-scale convolution blocks and cross-attention-based diffusion Transformer blocks for conditional guidance to generate subject-adaptive SR EEG.
Large Language Models for Cuffless Blood Pressure Measurement From Wearable Biosignals
This paper pioneers the exploration of LLMs for cuffless BP measurement, providing a potential solution to enhance the accuracy of cuffless BP measurement.
From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking
Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy.
RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Tracker
The spatial cross-attention is used to overcome the problem of spatial misalignment of between RGB and sonar images.
Causality-inspired Latent Feature Augmentation for Single Domain Generalization
Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains.
Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges.
Improving Generalization of Deep Neural Networks by Optimum Shifting
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima.
Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion
The former does not fully exploit the potential of using only RGB and TIR information of the template or search region for channel and spatial feature fusion, and the latter lacks direct interaction between the template and search area, which limits the model's ability to fully exploit the original semantic information of both modalities.
Ranked #10 on
Rgb-T Tracking
on RGBT210
Is Your LiDAR Placement Optimized for 3D Scene Understanding?
However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately.
MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property
In this paper, we contribute a new benchmark, the first Multilingual-oriented quiZ on Intellectual Property (MoZIP), for the evaluation of LLMs in the IP domain.
Customizable Perturbation Synthesis for Robust SLAM Benchmarking
To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations.
Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems
This paper presents Graph-of-Thought (GoT), a new model for workflow automation that enhances the flexibility and efficiency of Large Language Models (LLMs) in complex task execution.
Efficient Discrete Physics-informed Neural Networks for Addressing Evolutionary Partial Differential Equations
Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning.
ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
Multimodal semantic segmentation is developing rapidly, but the modality of RGB-Polarization remains underexplored.
Ranked #1 on
Semantic Segmentation
on UPLight
TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction
In TTMFN, we present a two-stream multimodal co-attention transformer module to take full advantage of the complex relationships between different modalities and the potential connections within the modalities.
Valuation Duration of the Stock Market
In contrast, at the height of the global financial crisis, more than 2. 2% of market value is from dividends in the next year, implying a duration of 46 years.
Lightweight Full-Convolutional Siamese Tracker
Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms.
UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection
In this paper, we propose a plug-and-play Underwater joint image enhancement Module (UnitModule) that provides the input image preferred by the detector.
OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting
Extensive experiments on real-world benchmark datasets for downstream time series anomaly detection and forecasting tasks demonstrate that OneShotSTL is from 10 to over 1, 000 times faster than the state-of-the-art methods, while still providing comparable or even better accuracy.
DAA: A Delta Age AdaIN operation for age estimation via binary code transformer
Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation.
Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks
Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems, but they are still trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features.
Interactive Log Parsing via Light-weight User Feedback
Template mining is one of the foundational tasks to support log analysis, which supports the diagnosis and troubleshooting of large scale Web applications.
VQNet 2.0: A New Generation Machine Learning Framework that Unifies Classical and Quantum
Therefore, based on VQNet 1. 0, we further propose VQNet 2. 0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization.
Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles
The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions.
Investigation of Network Architecture for Multimodal Head-and-Neck Tumor Segmentation
Inspired by the recent success of Transformers for Natural Language Processing and vision Transformer for Computer Vision, many researchers in the medical imaging community have flocked to Transformer-based networks for various main stream medical tasks such as classification, segmentation, and estimation.
Generative artificial intelligence-enabled dynamic detection of nicotine-related circuits
And models of functional addiction circuits developed from functional imaging are an effective tool for discovering and verifying addiction circuits.
Physics-guided Data Augmentation for Learning the Solution Operator of Linear Differential Equations
Neural networks, especially the recent proposed neural operator models, are increasingly being used to find the solution operator of differential equations.
Bi-LSTM Price Prediction based on Attention Mechanism
In this paper, we propose a bidirectional LSTM neural network based on an attention mechanism, which is based on two popular assets, gold and bitcoin.
VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations
Although physics-informed neural networks(PINNs) have progressed a lot in many real applications recently, there remains problems to be further studied, such as achieving more accurate results, taking less training time, and quantifying the uncertainty of the predicted results.
Contextual Transformer for Offline Meta Reinforcement Learning
Firstly, we propose prompt tuning for offline RL, where a context vector sequence is concatenated with the input to guide the conditional policy generation.
Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising
In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs.
LPC-AD: Fast and Accurate Multivariate Time Series Anomaly Detection via Latent Predictive Coding
LPC-AD is motivated by the ever-increasing needs for fast and accurate MTS anomaly detection methods to support fast troubleshooting in cloud computing, micro-service systems, etc.
A Noise-level-aware Framework for PET Image Denoising
Our hypothesis is that by explicitly providing the local relative noise level of the input image to a deep convolutional neural network (DCNN), the DCNN can outperform itself trained on image appearance only.
Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond.
TransMorph: Transformer for unsupervised medical image registration
Recently Vision Transformer architectures have been proposed to address the shortcomings of ConvNets and have produced state-of-the-art performances in many medical imaging applications.
Ranked #1 on
Medical Image Registration
on OASIS
Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networks
The results demonstrated that the proposed method provides fast and robust lesion and bone segmentation for QBSPECT/CT.
ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration
However, the performances of ConvNets are still limited by lacking the understanding of long-range spatial relations in an image.
Ranked #4 on
Medical Image Registration
on OASIS
A Multi-task Joint Framework for Real-time Person Search
To solve these problems, we propose a Multi-task Joint Framework for real-time person search (MJF), which optimizes the person detection, feature extraction and identity comparison respectively.
Discriminatively Constrained Semi-supervised Multi-view Nonnegative Matrix Factorization with Graph Regularization
In recent years, semi-supervised multi-view nonnegative matrix factorization (MVNMF) algorithms have achieved promising performances for multi-view clustering.
Quality-aware semi-supervised learning for CMR segmentation
SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce.
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing.
Ranked #7 on
Passage Retrieval
on Natural Questions
Boundary-aware Context Neural Network for Medical Image Segmentation
In this paper, we formulate a boundary-aware context neural network (BA-Net) for 2D medical image segmentation to capture richer context and preserve fine spatial information.
Cascaded Context Enhancement Network for Automatic Skin Lesion Segmentation
In this paper, we formulate a cascaded context enhancement neural network for automatic skin lesion segmentation.
Triplet Online Instance Matching Loss for Person Re-identification
Triplet loss processes batch construction in a complicated and fussy way and converges slowly.
Acoustic Scene Classification Using Bilinear Pooling on Time-liked and Frequency-liked Convolution Neural Network
Although works have been done in using HPSS as input representation for CNN model in ASC task, this paper further investigate the possibility on leveraging the separated harmonic component and percussive component by curating 2 CNNs which tries to understand harmonic audio and percussive audio in their natural form, one specialized in extracting deep features in time biased domain and another specialized in extracting deep features in frequency biased domain, respectively.
Generating Anthropomorphic Phantoms Using Fully Unsupervised Deformable Image Registration with Convolutional Neural Networks
In this work, we present a novel image registration method for creating highly anatomically detailed anthropomorphic phantoms from a single digital phantom.
Modeling arterial pulse waves in healthy aging: a database for in silico evaluation of hemodynamics and pulse wave indexes
The database, containing PWs from 4, 374 virtual subjects, was verified by comparing the simulated PWs and derived indexes with corresponding in vivo data.
