Causal Future Prediction in a Minkowski Space-Time

• URL: http://arxiv.org/abs/2008.09154v2
• Date: Sun, 30 Aug 2020 17:08:17 GMT
• Title: Causal Future Prediction in a Minkowski Space-Time
• Authors: Athanasios Vlontzos, Henrique Bergallo Rocha, Daniel Rueckert, Bernhard Kainz
• Abstract summary: In the wild, a plausible succession of events is governed by the rules of causality which cannot easily be derived from a finite training set. We propose a novel theoretical framework to perform causal-temporal future prediction by embedding information on spacetime. We demonstrate successful applications in causal imagetemporal and future video frame prediction on a dataset of images.
• Score: 10.899379163846254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating future events is a difficult task. Unlike humans, machine learning approaches are not regularized by a natural understanding of physics. In the wild, a plausible succession of events is governed by the rules of causality, which cannot easily be derived from a finite training set. In this paper we propose a novel theoretical framework to perform causal future prediction by embedding spatiotemporal information on a Minkowski space-time. We utilize the concept of a light cone from special relativity to restrict and traverse the latent space of an arbitrary model. We demonstrate successful applications in causal image synthesis and future video frame prediction on a dataset of images. Our framework is architecture- and task-independent and comes with strong theoretical guarantees of causal capabilities.

Related papers

• Extralonger: Toward a Unified Perspective of Spatial-Temporal Factors for Extra-Long-Term Traffic Forecasting [69.4265346261936]
  We introduce Extralonger, which unifies temporal and spatial factors. It notably extends the prediction horizon to a week on real-world benchmarks. It sets new standards in long-term and extra-long-term scenarios.
  arXiv  Detail & Related papers  (2024-10-30T04:28:20Z)
• Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration [27.28184416632815]
  We argue that the recorded motion in training data could be an observation of possible future, rather than a predetermined result. A novel computationally efficient encoder-decoder model with uncertainty consideration is proposed.
  arXiv  Detail & Related papers  (2024-03-21T03:34:18Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Modeling the evolution of temporal knowledge graphs with uncertainty [34.54782960535138]
  We introduce a novel graph neural network architecture (WGP-NN) to jointly model the temporal evolution of the occurrence probability of events. We demonstrate the model's state-of-the-art performance on two real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-01-12T12:39:22Z)
• Wildfire Forecasting with Satellite Images and Deep Generative Model [0.0]
  We use a series of wildfire images as a video to anticipate how the fire would behave in the future. We introduce a novel temporal model whose dynamics are driven in a latent space. Results will be compared towards various benchmarking models.
  arXiv  Detail & Related papers  (2022-08-19T15:52:43Z)
• Predicting extreme events from data using deep machine learning: when and where [0.0]
  We develop a deep convolutional neural network (DCNN) based framework for model-free prediction of the occurrence of extreme events. We use synthetic data from the 2D complex Ginzburg-Landau equation and empirical wind speed data of the North Atlantic ocean to demonstrate and validate our machine-learning based prediction framework.
  arXiv  Detail & Related papers  (2022-03-31T16:28:01Z)
• Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction [63.62263239934777]
  We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. We propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction. Our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency.
  arXiv  Detail & Related papers  (2021-12-30T10:45:22Z)
• Are socially-aware trajectory prediction models really socially-aware? [75.36961426916639]
  We introduce a socially-attended attack to assess the social understanding of prediction models. An attack is a small yet carefully-crafted perturbations to fail predictors. We show that our attack can be employed to increase the social understanding of state-of-the-art models.
  arXiv  Detail & Related papers  (2021-08-24T17:59:09Z)
• Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction [55.4498466252522]
  We set a new standard of video prediction with orders of magnitude longer prediction time than existing approaches. Our method predicts future frames by first estimating a sequence of semantic structures and subsequently translating the structures to pixels by video-to-video translation. We evaluate our method on three challenging datasets involving car driving and human dancing, and demonstrate that it can generate complicated scene structures and motions over a very long time horizon.
  arXiv  Detail & Related papers  (2021-04-14T08:39:38Z)
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance [110.63037190641414]
  We propose to learn congestion patterns explicitly and devise a novel "Sense--Learn--Reason--Predict" framework. By decomposing the learning phases into two stages, a "student" can learn contextual cues from a "teacher" while generating collision-free trajectories. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset.
  arXiv  Detail & Related papers  (2021-03-26T02:42:33Z)
• Short- and long-term prediction of a chaotic flow: A physics-constrained reservoir computing approach [5.37133760455631]
  We propose a physics-constrained machine learning method-based on reservoir computing- to time-accurately predict extreme events and long-term velocity statistics in a model of turbulent shear flow. We show that the combination of the two approaches is able to accurately reproduce the velocity statistics and to predict the occurrence and amplitude of extreme events in a model of self-sustaining process in turbulence.
  arXiv  Detail & Related papers  (2021-02-15T12:29:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.