Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder

• URL: http://arxiv.org/abs/2202.09315v2
• Date: Mon, 21 Feb 2022 13:55:45 GMT
• Title: Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder
• Authors: Xiaoyu Lin, Laurent Girin, Xavier Alameda-Pineda
• Abstract summary: We present an unsupervised probabilistic model and associated estimation algorithm for multi-object tracking (MOT) based on a dynamical variational autoencoder (DVAE) DVAE is a latent-variable deep generative model that can be seen as an extension of the variational autoencoder for the modeling of temporal sequences. It is included in DVAE-UMOT to model the objects' dynamics, after being pre-trained on an unlabeled synthetic dataset single-object trajectories.
• Score: 25.293475313066967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present an unsupervised probabilistic model and associated estimation algorithm for multi-object tracking (MOT) based on a dynamical variational autoencoder (DVAE), called DVAE-UMOT. The DVAE is a latent-variable deep generative model that can be seen as an extension of the variational autoencoder for the modeling of temporal sequences. It is included in DVAE-UMOT to model the objects' dynamics, after being pre-trained on an unlabeled synthetic dataset of single-object trajectories. Then the distributions and parameters of DVAE-UMOT are estimated on each multi-object sequence to track using the principles of variational inference: Definition of an approximate posterior distribution of the latent variables and maximization of the corresponding evidence lower bound of the data likehood function. DVAE-UMOT is shown experimentally to compete well with and even surpass the performance of two state-of-the-art probabilistic MOT models. Code and data are publicly available.

Related papers

• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
  We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
  arXiv  Detail & Related papers  (2024-10-10T17:18:30Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation [28.24190848937156]
  We propose a mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. We illustrate the versatility of the proposed MixDVAE model on two tasks: a computer vision task, and an audio processing task, namely single-channel audio source separation.
  arXiv  Detail & Related papers  (2023-12-07T09:36:31Z)
• IDM-Follower: A Model-Informed Deep Learning Method for Long-Sequence Car-Following Trajectory Prediction [24.94160059351764]
  Most car-following models are generative and only consider the inputs of the speed, position, and acceleration of the last time step. We implement a novel structure with two independent encoders and a self-attention decoder that could sequentially predict the following trajectories. Numerical experiments with multiple settings on simulation and NGSIM datasets show that the IDM-Follower can improve the prediction performance.
  arXiv  Detail & Related papers  (2022-10-20T02:24:27Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Discrete Auto-regressive Variational Attention Models for Text Modeling [53.38382932162732]
  Variational autoencoders (VAEs) have been widely applied for text modeling. They are troubled by two challenges: information underrepresentation and posterior collapse. We propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges.
  arXiv  Detail & Related papers  (2021-06-16T06:36:26Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Multivariate Temporal Autoencoder for Predictive Reconstruction of Deep Sequences [0.0]
  Time series sequence prediction and modelling has proven to be a challenging endeavor in real world datasets. Two key issues are the multi-dimensionality of data and the interaction of independent dimensions forming a latent output signal. This paper proposes a multi-branch deep neural network approach to tackling the aforementioned problems by modelling a latent state vector representation of data windows.
  arXiv  Detail & Related papers  (2020-10-07T21:25:35Z)
• Dynamical Variational Autoencoders: A Comprehensive Review [23.25573952809074]
  We introduce and discuss a general class of models, called dynamical variational autoencoders (DVAEs) We present in detail seven recently proposed DVAE models, with an aim to homogenize the notations and presentation lines. We have reimplemented those seven DVAE models and present the results of an experimental benchmark conducted on the speech analysis-resynthesis task.
  arXiv  Detail & Related papers  (2020-08-28T11:49:33Z)
• Relaxed-Responsibility Hierarchical Discrete VAEs [3.976291254896486]
  We introduce textitRelaxed-Responsibility Vector-Quantisation, a novel way to parameterise discrete latent variables. We achieve state-of-the-art bits-per-dim results for various standard datasets.
  arXiv  Detail & Related papers  (2020-07-14T19:10:05Z)
• Variational Hyper RNN for Sequence Modeling [69.0659591456772]
  We propose a novel probabilistic sequence model that excels at capturing high variability in time series data. Our method uses temporal latent variables to capture information about the underlying data pattern. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data.
  arXiv  Detail & Related papers  (2020-02-24T19:30:32Z)

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.