Search Results for author:
Found 9 papers, 0 papers with code
A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos
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).
Combining Optimal Path Search With Task-Dependent Learning in a Neural Network
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.
Bootstrapping Concept Formation in Small Neural Networks
We argue that, first, Concepts are formed as closed representations, which are then consolidated by relating them to each other.
Human and Machine Action Prediction Independent of Object Information
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.
Semantic Image Search for Robotic Applications
Generalization in robotics is one of the most important problems.
Generation of Paths in a Maze using a Deep Network without Learning
Trajectory- or path-planning is a fundamental issue in a wide variety of applications.
One-shot path planning for multi-agent systems using fully convolutional neural network
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.
Action Prediction in Humans and Robots
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.
