Mapping Language to Vision in a Real-World Robotic Scenario

  title={Mapping Language to Vision in a Real-World Robotic Scenario},
  author={K. {\vS}tep{\'a}nov{\'a} and F. Klein and A. Cangelosi and Michal Vavrecka},
  journal={IEEE Transactions on Cognitive and Developmental Systems},
  • K. Štepánová, F. Klein, +1 author Michal Vavrecka
  • Published 2018
  • Computer Science
  • IEEE Transactions on Cognitive and Developmental Systems
  • Language has evolved over centuries and was gradually enriched and improved. The question, how people find assignment between meanings and referents, remains unanswered. There are many of computational models based on the statistical co-occurrence of meaning-reference pairs. Unfortunately, these mapping strategies show poor performance in an environment with a higher number of objects or noise. Therefore, we propose a more robust noise-resistant algorithm. We tested the performance of this… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Learning visually grounded words and syntax for a scene description task
    • 220
    • Open Access
    Deep Visual-Semantic Alignments for Generating Image Descriptions
    • 1,512
    • Open Access
    Long-term recurrent convolutional networks for visual recognition and description
    • 3,182
    • Open Access
    A computational study of cross-situational techniques for learning word-to-meaning mappings
    • 513
    • Open Access
    From robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories1
    • 126
    • Open Access
    Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes
    • 189
    • Highly Influential
    • Open Access
    The iCub humanoid robot: an open platform for research in embodied cognition
    • 503
    • Open Access
    The grounding of higher order concepts in action and language: A cognitive robotics model
    • 46
    YARP: Yet Another Robot Platform
    • 563
    • Open Access