Search Results for author:
Found 32 papers, 10 papers with code
M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
Specifically, to eliminate the temporal inconsistency between EEG and speech modalities, the modal alignment module that uses a contrastive learning strategy is applied to align the temporal features of both modalities.
SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction
Recent advancements in high-definition \emph{HD} map construction have demonstrated the effectiveness of dense representations, which heavily rely on computationally intensive bird's-eye view \emph{BEV} features.
Learning-based Homothetic Tube MPC
In this paper, we study homothetic tube model predictive control (MPC) of discrete-time linear systems subject to bounded additive disturbance and mixed constraints on the state and input.
Global Rice Multi-Class Segmentation Dataset (RiceSEG): A Comprehensive and Diverse High-Resolution RGB-Annotated Images for the Development and Benchmarking of Rice Segmentation Algorithms
Developing computer vision-based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production.
Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach
Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients.
Inverse Flow and Consistency Models
While recent advances in generative models like diffusion models, conditional flow matching, and consistency models achieved impressive results by casting generation as denoising problems, they cannot be directly used for inverse generation without access to clean data.
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length.
DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis
Due to the irregular and disordered data structure in 3D point clouds, prior works have focused on designing more sophisticated local representation methods to capture these complex local patterns.
GlaLSTM: A Concurrent LSTM Stream Framework for Glaucoma Detection via Biomarker Mining
Glaucoma is a complex group of eye diseases marked by optic nerve damage, commonly linked to elevated intraocular pressure and biomarkers like retinal nerve fiber layer thickness.
Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement
3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance.
Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports
The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging.
Efficient Surgical Tool Recognition via HMM-Stabilized Deep Learning
Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications.
Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentation
This novel framework offers improved performance with fewer parameters and holds significant potential for accurate segmentation of lesion regions in various medical tasks, making it clinically valuable.
Observer-Based Environment Robust Control Barrier Functions for Safety-critical Control with Dynamic Obstacles
This paper proposes a safety-critical controller for dynamic and uncertain environments, leveraging a robust environment control barrier function (ECBF) to enhance the robustness against the measurement and prediction uncertainties associated with moving obstacles.
Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer in which the tumor-vascular involvement greatly affects the resectability and, thus, overall survival of patients.
Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning
Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM).
Dirichlet Diffusion Score Model for Biological Sequence Generation
Finally, we applied this approach to develop the first human promoter DNA sequence design model and showed that designed sequences share similar properties with natural promoter sequences.
Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions
In this study, a novel hybrid framework combining the controlled physics-informed data generation approach with a deep learning-based prediction model for prognostics is proposed.
Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework
While the fundamental framework of point cloud semantic segmentation has been largely overlooked, with most existing approaches rely on the U-Net architecture by default.
CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice, while most medical AI systems are built to focus on single organs with a narrow list of a few diseases.
Interaction-Aware Motion Planning for Autonomous Vehicles with Multi-Modal Obstacle Uncertainty Predictions
This paper proposes an interaction and safety-aware motion-planning method for an autonomous vehicle in uncertain multi-vehicle traffic environments.
Combating Uncertainty and Class Imbalance in Facial Expression Recognition
Experiments show that our method surpasses most basic methods in terms of accuracy on facial expression data sets (e. g., AffectNet, RAF-DB), and it also solves the problem of class imbalance well.
Facial Expression Recognition
Facial Expression Recognition (FER)
An Adjustable Farthest Point Sampling Method for Approximately-sorted Point Cloud Data
Sampling is an essential part of raw point cloud data processing such as in the popular PointNet++ scheme.
Novelty Detection via Contrastive Learning with Negative Data Augmentation
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
Contrastive Learning for Compact Single Image Dehazing
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Ranked #5 on
Image Dehazing
on RS-Haze
Strain effects on monolayer MoSi2N4: ideal strength and failure mechanism
Interestingly, the critical strain and failure mechanism of zigzag direction in MoSi2N4 are almost the same as those of armchair direction in MoS2, while the critical strain and failure mechanism of armchair direction for MoSi2N4 are similar to the ones of zigzag direction for MoS2.
Mesoscale and Nanoscale Physics
Trace anomaly contribution to hydrogen atom mass
We compute trace anomaly contribution to hydrogen atom mass, which turns out to be related to the part of the Lamb shift.
High Energy Physics - Phenomenology
New opportunities at the photon energy frontier
Ultra-peripheral collisions (UPCs) involving heavy ions and protons are the energy frontier for photon-mediated interactions.
High Energy Physics - Phenomenology High Energy Physics - Experiment Nuclear Experiment
Multistage Model for Robust Face Alignment Using Deep Neural Networks
First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment.
Perceptual Visual Interactive Learning
Supervised learning methods are widely used in machine learning.
Image reconstruction from limited range projections using orthogonal moments
A set of orthonormal polynomials is proposed for image reconstruction from projection data.
Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction
Here we present a new supervised generative stochastic network (GSN) based method to predict local secondary structure with deep hierarchical representations.
