Sökning: "Hedvig Kjellström"

Visar resultat 1 - 5 av 8 avhandlingar innehållade orden Hedvig Kjellström.

1. 1. Learning Spatiotemporal Features in Low-Data and Fine-Grained Action Recognition with an Application to Equine Pain Behavior

   Författare :Sofia Broomé; Hedvig Kjellström; Efstratios Gavves; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Equine pain; computer vision for animals; deep learning; deep video models; spatiotemporal features; video understanding; action recognition; frame dependency; video data; end-to-end learning; temporal modeling; Datalogi; Computer Science;

   Sammanfattning : Recognition of pain in animals is important because pain compromises animal welfare and can be a manifestation of disease. This is a difficult task for veterinarians and caretakers, partly because horses, being prey animals, display subtle pain behavior, and because they cannot verbalize their pain. LÄS MER

3. 2. Robots That Understand Natural Language Instructions and Resolve Ambiguities

   Författare :Fethiye Irmak Dogan; Iolanda Leite; Hedvig Kjellström; Hossein Azizpour; David Traum; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Datalogi; Computer Science;

   Sammanfattning : Verbal communication is a key challenge in human-robot interaction. For effective verbal interaction, understanding natural language instructions and clarifying ambiguous user requests are crucial for robots. In real-world environments, the instructions can be ambiguous for many reasons. LÄS MER

4. 3. Fine-Grained and Continual Visual Recognition for Assisting Visually Impaired People

   Författare :Marcus Klasson; Hedvig Kjellström; Cheng Zhang; Davide Bacciu; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Fine-Grained Image Recognition; Continual Learning; Visually Impaired People; Image Classification; Replay Scheduling; Datalogi; Computer Science;

   Sammanfattning : In recent years, computer vision-based assistive technologies have enabled visually impaired people to use automatic visual recognition on their mobile phones. These systems should be capable of recognizing objects on fine-grained levels to provide the user with accurate predictions. LÄS MER

5. 4. Developing and evaluating co-speech gesture-synthesis models for embodied conversational agents

   Författare :Taras Kucherenko; Hedvig Kjellström; Gustav Eje Henter; Iolanda Leite; Jonas Beskow; Stefan Kopp; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Human-agent interaction; gesture generation; social robotics; conversational agents; non-verbal behavior; deep learning; machine learning; Computer Science; Datalogi;

   Sammanfattning :  A  large part of our communication is non-verbal:   humans use non-verbal behaviors to express various aspects of our state or intent.  Embodied artificial agents, such as virtual avatars or robots, should also use non-verbal behavior for efficient and pleasant interaction. LÄS MER

7. 5. Action Recognition for Robot Learning

   Författare :Alessandro Pieropan; Kjellström Hedvig; Markus Vinkze; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computer Science; Datalogi;

   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