Cognitive representations of spatial location [PDF]
Brain and Neuroscience Advances, 2018 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]
Computer graphics forum (Print), 2021 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
Learning Discriminative Representations for Skeleton Based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2023 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]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2022 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
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations [PDF]
International Conference on Machine Learning, 2023 Geo-tagged images are publicly available in large quantities, whereas labels such as object classes are rather scarce and expensive to collect. Meanwhile, contrastive learning has achieved tremendous success in various natural image and language tasks ...
Gengchen Mai +4 more
semanticscholar +1 more source
Foundations of spatial perception for robotics: Hierarchical representations and real-time systems [PDF]
Int. J. Robotics Res., 2023 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
Large-scale chemical language representations capture molecular structure and properties [PDF]
Nature Machine Intelligence, 2021 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
Neural representations of space in the hippocampus of a food-caching bird
Science, 2021 Conserved spatial memory mechanisms Food-caching birds are memory specialists that can remember thousands of hidden food items. Using electrophysiological recordings from freely behaving birds, Payne et al.
Hannah L. Payne, G. F. Lynch, D. Aronov
semanticscholar +1 more source
Dynamic synchronization between hippocampal representations and stepping
Nature, 2023 The hippocampus is a mammalian brain structure that expresses spatial representations^ 1 and is crucial for navigation^ 2 , 3 . Navigation, in turn, intricately depends on locomotion; however, current accounts suggest a dissociation between hippocampal ...
Abhilasha Joshi +8 more
semanticscholar +1 more source
Implicit Neural Spatial Representations for Time-dependent PDEs [PDF]
International Conference on Machine Learning, 2022 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
semanticscholar +1 more source