no code implementations • 13 Nov 2023 • Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi, Minija Tamosiunaite, Florentin Wörgötter
Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video.
no code implementations • 1 Oct 2023 • Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi, Minija Tamosiunaite, Florentin Wörgötter
To achieve this, we encode, first, the spatio-temporal inter dependencies between objects and actions with scene graphs and we combine this, in a second step, with a novel 3-level architecture creating a hierarchical attention mechanism using Graph Attention Networks (GATs).
no code implementations • 26 Jan 2022 • Tomas Kulvicius, Minija Tamosiunaite, Florentin Wörgötter
The neural network has the same algorithmic complexity as Bellman-Ford and, in addition, we can show that network learning mechanisms (such as Hebbian learning) can adapt the weights in the network augmenting the resulting paths according to some task at hand.
no code implementations • 26 Oct 2021 • Minija Tamosiunaite, Tomas Kulvicius, Florentin Wörgötter
We argue that, first, Concepts are formed as closed representations, which are then consolidated by relating them to each other.
no code implementations • 22 Apr 2020 • Fatemeh Ziaeetabar, Jennifer Pomp, Stefan Pfeiffer, Nadiya El-Sourani, Ricarda I. Schubotz, Minija Tamosiunaite, Florentin Wörgötter
In spite of these constraints, our results show the subjects were able to predict actions in, on average, less than 64% of the action's duration.
no code implementations • 2 Apr 2020 • Tomas Kulvicius, Irene Markelic, Minija Tamosiunaite, Florentin Wörgötter
Generalization in robotics is one of the most important problems.
no code implementations • 1 Apr 2020 • Tomas Kulvicius, Sebastian Herzog, Minija Tamosiunaite, Florentin Wörgötter
Trajectory- or path-planning is a fundamental issue in a wide variety of applications.
no code implementations • 1 Apr 2020 • Tomas Kulvicius, Sebastian Herzog, Timo Lüddecke, Minija Tamosiunaite, Florentin Wörgötter
In contrast to that, we propose a novel method by utilising fully convolutional neural network, which allows generation of complete paths, even for more than one agent, in one-shot, i. e., with a single prediction step.
no code implementations • 3 Jul 2019 • Florentin Wörgötter, Fatemeh Ziaeetabar, Stefan Pfeiffer, Osman Kaya, Tomas Kulvicius, Minija Tamosiunaite
To achieve prediction, actions can be encoded by a series of events, where every event corresponds to a change in a (static or dynamic) relation between some of the objects in a scene.