Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2024
Cross-modal learning for optical flow estimation with events
AbstractBenefiting from the low latency and high dynamic range, event cameras have recently been adopted for Optical Flow (OF) prediction under harsh environments with high-speed motion or extreme lighting conditions. However, the emitted events only ...
Highlights- Alleviating the imperfection of events by utilizing the spatiotemporal attention-based module.
- Fully exploiting the cross-modal characteristics between frames and events.
- Designing long-term motion information for global temporal ...
- ArticleAugust 2024
Unsupervised Domain Adaptation Method for Medical Image Segmentation Using Fourier Feature Decoupling and Multi-scale Feature Fusion
Advanced Intelligent Computing Technology and ApplicationsPages 53–64https://doi.org/10.1007/978-981-97-5600-1_5AbstractUnsupervised Domain Adaptation (UDA) is an effective technique for utilizing labeled data from a source domain alongside unlabeled data from a target domain, aiming to mitigate the impact of domain shift on model performance. Feature decoupling-...
- ArticleAugust 2024
Unsupervised Domain Adaptation in Medical Image Segmentation via Fourier Feature Decoupling and Multi-teacher Distillation
Advanced Intelligent Computing Technology and ApplicationsPages 98–110https://doi.org/10.1007/978-981-97-5597-4_9AbstractUnsupervised domain adaptation (UDA) has recently garnered widespread attention in the field of medical image segmentation by transferring knowledge from labeled source datasets to enhance model segmentation performance on unlabeled target domain ...
- ArticleAugust 2024
Hierarchical Cascaded Multi-Axis Window Self-Attention and Layer Feature Fusion for Brain Glioma Segmentation
Advanced Intelligent Computing Technology and ApplicationsPages 233–245https://doi.org/10.1007/978-981-97-5597-4_20AbstractAutomatic segmentation of brain glioma from magnetic resonance imaging (MRI) using deep learning methods is very important for clinical diagnosis and follow-up treatments. The size, shape and location of glioma vary greatly among different ...
- ArticleAugust 2024
CAT-DG: A Cross-Attention-Based Domain Generalization Model for Medical Image Segmentation
Advanced Intelligent Computing Technology and ApplicationsPages 169–180https://doi.org/10.1007/978-981-97-5597-4_15AbstractIn medical image segmentation tasks, the performance of the trained segmentation model in the unseen domain is affected by the domain shifting problem. Therefore, improving the model’s generalization is crucial for the practical application of ...
-
- research-articleJuly 2024
Rényi–Sobolev Inequalities and Connections to Spectral Graph Theory
IEEE Transactions on Information Theory (ITHR), Volume 70, Issue 10Pages 6809–6822https://doi.org/10.1109/TIT.2024.3435414In this paper, we generalize the log-Sobolev inequalities to Rényi–Sobolev inequalities by replacing the entropy with the two-parameter entropy, which is a generalized version of entropy and closely related to Rényi divergences. We ...
- research-articleMay 2024
Exact Exponents for Concentration and Isoperimetry in Product Polish Spaces
IEEE Transactions on Information Theory (ITHR), Volume 70, Issue 8Pages 5427–5452https://doi.org/10.1109/TIT.2024.3408043In this paper, we derive variational formulas for the asymptotic exponents (i.e., convergence rates) of the concentration and isoperimetric functions in the product Polish probability space under certain mild assumptions. These formulas are expressed in ...
- extended-abstractMay 2024
MA-MIX: Value Function Decomposition for Cooperative Multiagent Reinforcement Learning Based on Multi-Head Attention Mechanism
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2402–2404Multi-Agent Deep Reinforcement Learning (MADRL) is a research field that combines deep learning and multi-agent reinforcement learning. In complex tasks, a single agent often finds it difficult to complete the task independently, thus requiring ...
- research-articleApril 2024
End-to-end dynamic residual focal transformer network for multimodal medical image fusion
Neural Computing and Applications (NCAA), Volume 36, Issue 19Pages 11579–11601https://doi.org/10.1007/s00521-024-09729-4AbstractMultimodal medical image fusion aims to improve the clinical practicability of medical images by integrating complementary information from multiple medical images. However, in traditional fusion methods, the fusion rules based on prior knowledge ...
- review-articleAugust 2024
High-precision offline mapping and localization system based on ground texture with binary descriptors
Expert Systems with Applications: An International Journal (EXWA), Volume 240, Issue Chttps://doi.org/10.1016/j.eswa.2023.122650AbstractAccurate and robust localization is one of the most basic functional modules of mobile robots. A recent promising approach is to employ a camera that captures ground textures to achieve high-precision localization. However, low robustness and ...
- research-articleApril 2024
“Seeing” ENF From Neuromorphic Events: Modeling and Robust Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 46, Issue 10Pages 6809–6825https://doi.org/10.1109/TPAMI.2024.3386813Most artificial lights exhibit subtle fluctuations in intensity and frequency in response to the influence of the grid's alternating current, providing the potential to estimate the Electric Network Frequency (ENF) from conventional frame-based ...
- research-articleJuly 2024
YOLO_SRv2: An evolved version of YOLO_SR
Engineering Applications of Artificial Intelligence (EAAI), Volume 130, Issue Chttps://doi.org/10.1016/j.engappai.2023.107657AbstractRecently, object detection based on deep neural network has become the mainstream research direction of sweeping robots since different obstacles may produce completely contradictory sweeping decisions. However, due to the limited computational ...
- research-articleMarch 2024
MAC Optimization Protocol for Cooperative UAV Based on Dual Perception of Energy Consumption and Channel Gain
IEEE Transactions on Mobile Computing (ITMV), Volume 23, Issue 10Pages 9851–9862https://doi.org/10.1109/TMC.2024.3372253FANET (Fly-Adhoc-Network) does not rely on pre-built infrastructure, and can form a temporary network through wireless links anytime and anywhere, which has been widely used in emergency communication and disaster relief. In order to solve the problem of ...
- research-articleJanuary 2024
Graphs of Joint Types, Noninteractive Simulation, and Stronger Hypercontractivity
IEEE Transactions on Information Theory (ITHR), Volume 70, Issue 4Pages 2287–2308https://doi.org/10.1109/TIT.2024.3357859In this paper, we study the type graph, namely, a bipartite graph induced by a joint type. We investigate the maximum edge density of induced bipartite subgraphs of this graph having a number of vertices on each side on an exponential scale in the length <...
- research-articleJuly 2024
Parameter Estimation of a Single Chirp in the Presence of Wiener Phase Noise With Unknown Variance
IEEE Transactions on Signal Processing (TSP), Volume 72Pages 3171–3186https://doi.org/10.1109/TSP.2024.3421374This study addresses the problem of estimating the parameters of a single chirp signal affected by Wiener phase noise with an unknown variance and observed in an additive white Gaussian noise (AWGN) environment. We derive the time-domain joint maximum ...
- research-articleApril 2024
Learning from vertically distributed data across multiple sites: An efficient privacy-preserving algorithm for Cox proportional hazards model with variable selection
Journal of Biomedical Informatics (JOBI), Volume 149, Issue Chttps://doi.org/10.1016/j.jbi.2023.104581Graphical abstractDisplay Omitted
Abstract ObjectiveTo develop a lossless distributed algorithm for regularized Cox proportional hazards model with variable selection to support federated learning for vertically distributed data.
MethodsWe propose a novel distributed algorithm for ...
- research-articleApril 2024
Video Frame Interpolation With Stereo Event and Intensity Cameras
IEEE Transactions on Multimedia (TOM), Volume 26Pages 9187–9202https://doi.org/10.1109/TMM.2024.3387690The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information. However, such a setup commonly encounters cross-...
- research-articleFebruary 2024
Neuromorphic Synergy for Video Binarization
IEEE Transactions on Image Processing (TIP), Volume 33Pages 1403–1418https://doi.org/10.1109/TIP.2024.3364529Bimodal objects, such as the checkerboard pattern used in camera calibration, markers for object tracking, and text on road signs, to name a few, are prevalent in our daily lives and serve as a visual form to embed information that can be easily ...
- research-articleJanuary 2024
Motion Deblur by Learning Residual From Events
IEEE Transactions on Multimedia (TOM), Volume 26Pages 6632–6647https://doi.org/10.1109/TMM.2024.3355630Conventional cameras face challenges when capturing motion information during the exposure due to their physical design, rendering the motion deblurring task ill-posed. To this end, we propose a Two-stage Residual-based Motion Deblurring (TRMD) framework ...
- research-articleFebruary 2024
Few-shot learning via weighted prototypes from graph structure
Pattern Recognition Letters (PTRL), Volume 176, Issue CPages 230–235https://doi.org/10.1016/j.patrec.2023.11.017AbstractFew-shot learning is attracting extensive research because of its ability to classify only a few co-trainable samples. Current few-shot learning approaches focus on learning class prototypes representation to solve problems by a simple averaging ...
Highlights- Introduced a novel approach for few-shot image classification.
- Innovatively transformed the process of assessing sample importance into graph label propagation.
- Achieved performance improvements on few-shot benchmark datasets.