Sökning: "Action recognition"

Visar resultat 1 - 5 av 91 avhandlingar innehållade orden Action recognition.

  1. 1. Recognition of Prior Learning in Health Care : From a Caring Ideology and Power, to Communicative Action and Recognition

    Författare :Fredrik Sandberg; Per Andersson; Andreas Fejes; Kjell Rubenson; Linköpings universitet; []
    Nyckelord :SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; RPL; health care; health care assistant; critical social theory; communicative action; recognition; adult education; adult learning; Jürgen Habermas; Axel Honneth; Validering; omvårdnad; vårdbiträde; kritisk samhällsteori; kommunikativt handlande; erkännande; vuxnas lärande; Jürgen Habermas; Axel Honneth;

    Sammanfattning : During the last decades Recognition of Prior Learning (RPL) has become a more frequently used method to recognise adult’s prior learning. This thesis analyses a process of RPL in health care, where health care assistants are assessed against subjects in the upper-secondary health care program. LÄS MER

  2. 2. Action Recognition for Robot Learning

    Författare :Alessandro Pieropan; Kjellström Hedvig; Markus Vinkze; KTH; []

    Sammanfattning : This thesis builds on the observation that robots cannot be programmed to handle any possible situation in the world. Like humans, they need mechanisms to deal with previously unseen situations and unknown objects. One of the skills humans rely on to deal with the unknown is the ability to learn by observing others. LÄS MER

  3. 3. Mind in Action: Action Representation and the Perception of Biological Motion

    Författare :Paul Hemeren; Kognitionsvetenskap; []
    Nyckelord :HUMANIORA; HUMANITIES; HUMANIORA; HUMANITIES; perception; action; concept; Cognition; categorization; embodiment; prototype; biological motion; semantics; language; configural processing; basic level; graded structure; typicality; action; Civics; Samhällsvetenskap; Humanities and Social sciences; Humaniora-samhällsvetenskap;

    Sammanfattning : The ability to understand and communicate about the actions of others is a fundamental aspect of our daily activity. How can we talk about what others are doing? What qualities do different actions have such that they cause us to see them as being different or similar? What is the connection between what we see and the development of concepts and words or expressions for the things that we see? To what extent can two different people see and talk about the same things? Is there a common basis for our perception, and is there then a common basis for the concepts we form and the way in which the concepts become lexicalized in language? The broad purpose of this thesis is to relate aspects of perception, categorization and language to action recognition and conceptualization. LÄS MER

  4. 4. Computational models for intent recognition in robotic systems

    Författare :Michele Persiani; Thomas Hellström; Sven Magg; Umeå universitet; []
    Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Intent Recognition; Robotics; Plan Recognition; Speech; Affordances; Computer Science; datalogi;

    Sammanfattning : The ability to infer and mediate intentions has been recognized as a crucial task in recent robotics research, where it is agreed that robots are required to be equipped with intentional mechanisms in order to participate in collaborative tasks with humans.Reasoning about - or rather, perceiving - intentions enables robots to infer what other agents are doing, to communicate what are their plans, or to take proactive decisions. LÄS MER

  5. 5. Action in Mind : A Neural Network Approach to Action Recognition and Segmentation

    Författare :Zahra Gharaee; Kognitiv modellering; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Action recognition; motion perception; cognitive robotics; hierarchical models; self-organizing neural networks; growing grids; attention;

    Sammanfattning : Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry.This thesis presents a novel computational approach for human action recognition through different implementations of multi-layer architectures based on artificial neural networks. LÄS MER