Zobrazeno 1 - 10
of 466
pro vyhledávání: '"Kim, Won Hwa"'
Autor:
Ding, Jiaqi, Dan, Tingting, Wei, Ziquan, Cho, Hyuna, Laurienti, Paul J., Kim, Won Hwa, Wu, Guorong
An unprecedented amount of existing functional Magnetic Resonance Imaging (fMRI) data provides a new opportunity to understand the relationship between functional fluctuation and human cognition/behavior using a data-driven approach. To that end, tre
Externí odkaz:
http://arxiv.org/abs/2409.11377
In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated with training segmentation models. Mask-JEPA combines a Joint Embeddin
Externí odkaz:
http://arxiv.org/abs/2407.10733
A Marked Temporal Point Process (MTPP) is a stochastic process whose realization is a set of event-time data. MTPP is often used to understand complex dynamics of asynchronous temporal events such as money transaction, social media, healthcare, etc.
Externí odkaz:
http://arxiv.org/abs/2406.06149
The human brain is a complex inter-wired system that emerges spontaneous functional fluctuations. In spite of tremendous success in the experimental neuroscience field, a system-level understanding of how brain anatomy supports various neural activit
Externí odkaz:
http://arxiv.org/abs/2405.16357
Domain shift occurs when training (source) and test (target) data diverge in their distribution. Source-Free Domain Adaptation (SFDA) addresses this domain shift problem, aiming to adopt a trained model on the source domain to the target domain in a
Externí odkaz:
http://arxiv.org/abs/2401.14587
Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers increases. The is
Externí odkaz:
http://arxiv.org/abs/2401.11840
Autor:
Dan, Tingting, Ding, Jiaqi, Wei, Ziquan, Kovalsky, Shahar Z, Kim, Minjeong, Kim, Won Hwa, Wu, Guorong
Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. However, the locality assumption of GNNs, which limits information exchange to neighboring nodes, hampers their ability to capture long-range depende
Externí odkaz:
http://arxiv.org/abs/2307.00222
Scene graph generation aims to construct a semantic graph structure from an image such that its nodes and edges respectively represent objects and their relationships. One of the major challenges for the task lies in the presence of distracting objec
Externí odkaz:
http://arxiv.org/abs/2304.03495
Publikováno v:
In Medical Image Analysis July 2024 95
Autor:
Ma, Xin, Kim, Won Hwa
Clustering algorithms have significantly improved along with Deep Neural Networks which provide effective representation of data. Existing methods are built upon deep autoencoder and self-training process that leverages the distribution of cluster as
Externí odkaz:
http://arxiv.org/abs/2106.05430