Implicit Neural Spatial Representations for Time-dependent PDEs [PDF]
Implicit Neural Spatial Representation (INSR) has emerged as an effective representation of spatially-dependent vector fields. This work explores solving time-dependent PDEs with INSR.
Honglin Chen +4 more
openalex +3 more sources
Cognitive representations of spatial location [PDF]
Spatial memory has fascinated psychologists ever since the discipline began, but a series of findings beginning in the middle of last century propelled its study into the domain of neuroscience and helped bring about the cognitive revolution in psychology.
K. Jeffery
openaire +4 more sources
Compressive Neural Representations of Volumetric Scalar Fields [PDF]
We present an approach for compressing volumetric scalar fields using implicit neural representations. Our approach represents a scalar field as a learned function, wherein a neural network maps a point in the domain to an output scalar value. By setting
Yuzhe Lu, K. Jiang, J. Levine, M. Berger
semanticscholar +1 more source
Spatial representability of neuronal activity [PDF]
Abstract A common approach to interpreting spiking activity is based on identifying the firing fields—regions in physical or configuration spaces that elicit responses of neurons. Common examples include hippocampal place cells that fire at preferred locations in the navigated environment, head direction cells that fire at preferred ...
D. Akhtiamov, A. G. Cohn, Y. Dabaghian
openaire +6 more sources
Learning Discriminative Representations for Skeleton Based Action Recognition [PDF]
Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton representations
Huanyu Zhou, Qingjie Liu, Yunhong Wang
semanticscholar +1 more source
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation [PDF]
Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution operation.
Moein Heidari +6 more
semanticscholar +1 more source
Foundations of spatial perception for robotics: Hierarchical representations and real-time systems [PDF]
3D spatial perception is the problem of building and maintaining an actionable and persistent representation of the environment in real-time using sensor data and prior knowledge. Despite the fast-paced progress in robot perception, most existing methods
Nathan Hughes +6 more
semanticscholar +1 more source
Island connections: Icelandic spatiality in the wake of worldly linkages [PDF]
The notions and materiality of connections, through electronic networks as well as modes of mobility, play an ever-increasing role in how we define, understand, engage and experience the world we live in and the islands we live on.
David Bjarnason
doaj +2 more sources
Large-scale chemical language representations capture molecular structure and properties [PDF]
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design.
Jerret Ross +5 more
semanticscholar +1 more source
Spatial representation of coherence. [PDF]
Four experiments examined spatial correlates of the experience of coherence, that is, the extent to which propositions "fit together." Experiment 1 demonstrates for Heiderian triads (i.e., sets of liking/disliking relations between 3 fictitious persons) that name pairs from balanced triads, such as 2 friends commonly disliking a third person (high ...
Ulrich von Hecker +2 more
openaire +4 more sources

