English
Related papers

Related papers: Deep Variational Luenberger-type Observer for Stoc…

200 papers

Self-supervised video representation methods typically focus on the representation of temporal attributes in videos. However, the role of stationary versus non-stationary attributes is less explored: Stationary features, which remain…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Nadine Behrmann , Mohsen Fayyaz , Juergen Gall , Mehdi Noroozi

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Matteo Tiezzi , Simone Marullo , Lapo Faggi , Enrico Meloni , Alessandro Betti , Stefano Melacci

Visual representation is crucial for a visual tracking method's performances. Conventionally, visual representations adopted in visual tracking rely on hand-crafted computer vision descriptors. These descriptors were developed generically…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Jason Kuen , Kian Ming Lim , Chin Poo Lee

We describe a new spatio-temporal video autoencoder, based on a classic spatial image autoencoder and a novel nested temporal autoencoder. The temporal encoder is represented by a differentiable visual memory composed of convolutional long…

Machine Learning · Computer Science 2016-09-02 Viorica Patraucean , Ankur Handa , Roberto Cipolla

Video anomaly detection is a challenging task because most anomalies are scarce and non-deterministic. Many approaches investigate the reconstruction difference between normal and abnormal patterns, but neglect that anomalies do not…

Computer Vision and Pattern Recognition · Computer Science 2022-06-28 Guodong Shen , Yuqi Ouyang , Victor Sanchez

Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but also because it is commonly considered as an unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Yuqi Ouyang , Victor Sanchez

The paper deals with the observer design problem for a wide class of triangular time-varying nonlinear systems, with unobservable linearization. Sufficient conditions are derived for the existence of a Luenberger-type observer, when it is a…

Optimization and Control · Mathematics 2012-04-17 D. Boskos , J. Tsinias

In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future state which are predictable from those which are inherently…

Artificial Intelligence · Computer Science 2017-12-04 Mikael Henaff , Junbo Zhao , Yann LeCun

This work proposes a Stochastic Variational Deep Kernel Learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses…

Machine Learning · Computer Science 2023-06-28 Nicolò Botteghi , Mengwu Guo , Christoph Brune

Designing Luenberger observers for nonlinear systems involves the challenging task of transforming the state to an alternate coordinate system, possibly of higher dimensions, where the system is asymptotically stable and linear up to output…

Optimization and Control · Mathematics 2023-04-06 Muhammad Umar B. Niazi , John Cao , Xudong Sun , Amritam Das , Karl Henrik Johansson

A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on. However, interpretability for deep video…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Joonatan Mänttäri , Sofia Broomé , John Folkesson , Hedvig Kjellström

This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory…

Computer Vision and Pattern Recognition · Computer Science 2020-03-18 Giulia Slavic , Damian Campo , Mohamad Baydoun , Pablo Marin , David Martin , Lucio Marcenaro , Carlo Regazzoni

Given a visual history, multiple future outcomes for a video scene are equally probable, in other words, the distribution of future outcomes has multiple modes. Multimodality is notoriously hard to handle by standard regressors or…

Computer Vision and Pattern Recognition · Computer Science 2017-05-08 Katerina Fragkiadaki , Jonathan Huang , Alex Alemi , Sudheendra Vijayanarasimhan , Susanna Ricco , Rahul Sukthankar

Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…

Computer Vision and Pattern Recognition · Computer Science 2020-03-20 Osamu Shouno

Identifying systems with high-dimensional inputs and outputs, such as systems measured by video streams, is a challenging problem with numerous applications in robotics, autonomous vehicles and medical imaging. In this paper, we propose a…

Systems and Control · Electrical Eng. & Systems 2021-05-11 Gerben Izaak Beintema , Roland Toth , Maarten Schoukens

We introduce a new version of deep state-space models (DSSMs) that combines a recurrent neural network with a state-space framework to forecast time series data. The model estimates the observed series as functions of latent variables that…

Machine Learning · Statistics 2022-05-20 Haoxuan Wu , David S. Matteson , Martin T. Wells

Extracting the true dynamical variables of a system from high-dimensional video is challenging due to distracting visual factors such as background motion, occlusions, and texture changes. We propose LyTimeT, a two-phase framework for…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Kuai Yu , Crystal Su , Xiang Liu , Judah Goldfeder , Mingyuan Shao , Hod Lipson

Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective…

Robotics · Computer Science 2022-07-12 Oliver Limoyo , Bryan Chan , Filip Marić , Brandon Wagstaff , Rupam Mahmood , Jonathan Kelly

This paper presents a novel Luenberger-style observer for robot manipulators with position measurements. Under the assumption that the state evolutions that are to be observed have bounded velocities, it is shown that the origin of the…

Optimization and Control · Mathematics 2007-05-23 Fabio Celani

Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging. In this work, we treat the domain parameters of dynamical…

Machine Learning · Computer Science 2023-06-02 Stathi Fotiadis , Mario Lino , Shunlong Hu , Stef Garasto , Chris D Cantwell , Anil Anthony Bharath