1 code implementation • 3 Mar 2022 • Stephane Vujasinovic, Sebastian Bullinger, Stefan Becker, Norbert Scherer-Negenborn, Michael Arens, Rainer Stiefelhagen
While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Video Object Segmentation (CiVOS) framework to simplify the required user workload as much as possible.
1 code implementation • 22 May 2023 • Stéphane Vujasinović, Sebastian Bullinger, Stefan Becker, Norbert Scherer-Negenborn, Michael Arens, Rainer Stiefelhagen
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos.
Semantic Segmentation Semi-Supervised Video Object Segmentation +1
no code implementations • 19 May 2018 • Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens
In recent years, there is a shift from modeling the tracking problem based on Bayesian formulation towards using deep neural networks.
no code implementations • 16 Apr 2018 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens
Recurrent neural networks are able to learn complex long-term relationships from sequential data and output a pdf over the state space.
no code implementations • 5 Feb 2019 • Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens
The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation.
no code implementations • 27 Mar 2020 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens
The analysis and quantification of sequence complexity is an open problem frequently encountered when defining trajectory prediction benchmarks.
no code implementations • 28 May 2020 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens
Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models.
no code implementations • 6 Aug 2020 • Stéphane Vujasinović, Stefan Becker, Timo Breuer, Sebastian Bullinger, Norbert Scherer-Negenborn, Michael Arens
The 3D reconstruction of the scene is computed with an image-based Structure-from-Motion (SfM) component that enables us to leverage a state estimator in the corresponding 3D scene during tracking.
no code implementations • 22 Mar 2021 • Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris
For providing a full temporal filtering cycle, a basic RNN is extended to take observations and the associated belief about its accuracy into account for updating the current state.
no code implementations • 30 Jun 2021 • Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris
By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs.
no code implementations • 1 Jul 2021 • Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris
To demonstrate the applicability of the synthetic trajectory data, we show that an RNN-based prediction model solely trained on the generated data can outperform classic reference models on a real-world UAV tracking dataset.
no code implementations • 3 May 2022 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens, Jürgen Beyerer
Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information.
no code implementations • 19 Jun 2023 • Jens Bayer, Stefan Becker, David Münch, Michael Arens
The patches of these so-called evasion attacks are computational expensive to produce and require full access to the attacked detector.
no code implementations • 16 Nov 2023 • Stefan Becker, Jens Bayer, Ronny Hug, Wolfgang Hübner, Michael Arens
Data pooling offers various advantages, such as increasing the sample size, improving generalization, reducing sampling bias, and addressing data sparsity and quality, but it is not straightforward and may even be counterproductive.
no code implementations • 5 Apr 2024 • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens
An appropriate data basis grants one of the most important aspects for training and evaluating probabilistic trajectory prediction models based on neural networks.