• Publications
  • Influence
The vernissage corpus: A conversational Human-Robot-Interaction dataset
TLDR
We introduce a new conversational Human-Robot-Interaction (HRI) dataset with a real-behaving robot inducing interactive behavior with and between humans. Expand
  • 29
  • 4
  • PDF
STARDATA: A StarCraft AI Research Dataset
TLDR
We use TorchCraft to extract and store the data, which standardizes the data format for both reading from replays and reading directly from the game. Expand
  • 25
  • 2
  • PDF
THE VERNISSAGE CORPUS: A MULTIMODAL HUMAN-ROBOT-INTERACTION DATASET
TLDR
We introduce a new multimodal interaction dataset with extensive annotations in a conversational Human-Robot-Interaction (HRI) scenario. Expand
  • 14
  • 2
  • PDF
Engagement-based Multi-party Dialog with a Humanoid Robot
TLDR
We present the integration of an engagement model in an existing dialog system based on interaction patterns. Expand
  • 36
  • 1
  • PDF
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
TLDR
We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games, and train well-performing models on a large dataset of human games of StarCraft: Brood War. Expand
  • 17
  • 1
  • PDF
Finding audio-visual events in informal social gatherings
TLDR
We address the problem of detecting and localizing objects that can be both seen and heard, e.g., people. Expand
  • 25
  • 1
  • PDF
The CAVA corpus: synchronised stereoscopic and binaural datasets with head movements
TLDR
This paper describes the acquisition and content of a new multi-modal database. Expand
  • 26
  • 1
  • PDF
Polygames: Improved Zero Learning
TLDR
We present Polygames, our framework for Zero learning, with its library of games and its checkpoints. Expand
  • 6
  • 1
  • PDF
Context aware addressee estimation for human robot interaction
TLDR
The paper investigates the problem of addressee recognition -to whom a speaker's utterance is intended- in a setting involving a humanoid robot interacting with multiple persons. Expand
  • 6
  • 1
Conjugate Mixture Models for Clustering Multimodal Data
TLDR
The problem of multimodal clustering arises whenever the data are gathered with several physically different sensors. Expand
  • 33
  • PDF