M. Li

C. Xiao, W. An, Y. Zhang et al.

Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-intensive manual labels to tackle SVMOD, which needs high annotation costs and contains tremendous computational redundancy due to the severe imbalance between foreground and background regions. In this paper, we propose a highly efficient unsupervised framework for SVMOD. Specifically, we propose a generic unsupervised framework for SVMOD, in which pseudo labels generated by a traditional method can evolve with the training process to promote detection performance. Furthermore, we propose a highly efficient and effective sparse convolutional anchor-free detection network by sampling the dense multi-frame image form into a sparse spatio-temporal point cloud representation and skipping the redundant computation on background regions. Coping these two designs, we can achieve both high efficiency (label and computation efficiency) and effectiveness. Extensive experiments demonstrate that our method can not only process 98.8 frames per second on 1024x1024 images but also achieve state-of-the-art performance. The relabeled dataset and code are available at https://github.com/ChaoXiao12/Moving-object-detection-in-satellite-videos-HiEUM.

A. González-Mitjans, D. Paz-Linares, A. Areces-Gonzalez et al.

This paper introduces methods and a novel toolbox that efficiently integrates any high-dimensional Neural Mass Models (NMMs) specified by two essential components. The first is the set of nonlinear Random Differential Equations of the dynamics of each neural mass. The second is the highly sparse three-dimensional Connectome Tensor (CT) that encodes the strength of the connections and the delays of information transfer along the axons of each connection. Semi-analytical integration of the RDE is done with the Local Linearization scheme for each neural mass model, which is the only scheme guaranteeing dynamical fidelity to the original continuous-time nonlinear dynamic. It also seamlessly allows modeling distributed delays CT with any level of complexity or realism, as shown by the Moore-Penrose diagram of the algorithm. This ease of implementation includes models with distributed-delay CTs. We achieve high computational efficiency by using a tensor representation of the model that leverages semi-analytic expressions to integrate the Random Differential Equations (RDEs) underlying the NMM. We discretized the state equation with Local Linearization via an algebraic formulation. This approach increases numerical integration speed and efficiency, a crucial aspect of large-scale NMM simulations. To illustrate the usefulness of the toolbox, we simulate both a single Zetterberg-Jansen-Rit (ZJR) cortical column and an interconnected population of such columns. These examples illustrate the consequence of modifying the CT in these models, especially by introducing distributed delays. We provide an open-source Matlab live script for the toolbox.

M. Li, H. Bai, L. Tan et al.

Measuring sentence semantic similarity using pre-trained language models such as BERT generally yields unsatisfactory zero-shot performance, and one main reason is ineffective token aggregation methods such as mean pooling. In this paper, we demonstrate under a Bayesian framework that distance between primitive statistics such as the mean of word embeddings are fundamentally flawed for capturing sentence-level semantic similarity. To remedy this issue, we propose to learn a categorical variational autoencoder (VAE) based on off-the-shelf pre-trained language models. We theoretically prove that measuring the distance between the latent categorical mixtures, namely Latte-Mix, can better reflect the true sentence semantic similarity. In addition, our Bayesian framework provides explanations for why models finetuned on labelled sentence pairs have better zero-shot performance. We also empirically demonstrate that these finetuned models could be further improved by Latte-Mix. Our method not only yields the state-of-the-art zero-shot performance on semantic similarity datasets such as STS, but also enjoy the benefits of fast training and having small memory footprints.