Related papers: AI-driven spatio-temporal engine for finding gravi…

The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an…

Multiply imaged, gravitationally lensed supernovae are rare but powerful tools for providing independent measurements on cosmological parameters. Supernova (SN) 2025wny ("SN Winny") is the first gravitationally-lensed Type I superluminous…

Motion Planning, as a fundamental technology of automatic navigation for the autonomous vehicle, is still an open challenging issue in the real-life traffic situation and is mostly applied by the model-based approaches. However, due to the…

Over the past decade advancements in the understanding of several astrophysical phenomena have allowed us to infer a concordance cosmological model that successfully accounts for most of the observations of our universe. This has opened up…

We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i.e. series of observations sharing temporal and spatial dependencies. The model learns these…

In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams. Existing approaches typically utilize external…

Collaborative perception in Internet of Vehicles (IoV) aggregates multi-vehicle observations for broader scene coverage and improved decision-making. However, fusion quality degrades under spatiotemporal heterogeneity from unsynchronized…

Gravitational lensing offers unique insights into cosmology by bending light around massive objects. Strong gravitational lensing, in particular, produces magnified and often multiple images of distant sources, crucial for precise…

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs,…

Strong gravitational lensing time-delay measurements, together with the distance sum rule (DSR), offer a model-independent approach to probe the geometry and expansion of the universe without relying on a fiducial cosmological model. In…

Many earth observation programs such as Landsat, Sentinel, SPOT, and Pleiades produce huge volume of medium to high resolution multi-spectral images every day that can be organized in time series. In this work, we exploit both temporal and…

Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution. However, due to the sparsity of abnormal video clips in real life, collecting annotated data for supervised learning is…

We investigate the use of approximate Bayesian neural networks (BNNs) in modeling hundreds of time-delay gravitational lenses for Hubble constant ($H_0$) determination. Our BNN was trained on synthetic HST-quality images of strongly lensed…

In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space. So far, the development and application of GANs…

Convolutional neural networks have enabled accurate image super-resolution in real-time. However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures. In…

We present an inductive spatio-temporal learning framework rooted in inductive logic programming. With an emphasis on visuo-spatial language, logic, and cognition, the framework supports learning with relational spatio-temporal features…

Deep generative models have demonstrated their effectiveness in learning latent representation and modeling complex dependencies of time series. In this paper, we present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE)…

In this paper we develop a new unsupervised machine learning technique comprised of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian mixture model (BGM). We apply this…

Gravitationally lensed sources may have unresolved or blended multiple images, and for time varying sources the lightcurves from individual images can overlap. We use convolutional neural nets to both classify the lightcurves as due to…

Artificial Intelligence (AI) models deployed in production frequently face challenges in maintaining their performance in non-stationary environments. This issue is particularly noticeable in medical settings, where temporal dataset shifts…