Blar i TKD - Fakultet for teknologi, kunst og design på dokumenttype "Chapter"

Viser treff 1-9 av 9

    • AI-Based Cropping of Soccer Videos for Different Social Media Representations 

      Houshmand Sarkhoosh, Mehdi; Dorcheh, Sayed Mohammad Majidi; Midoglu, Cise; Sabet, Saeed; Kupka, Tomas; Johansen, Dag; Riegler, Michael Alexander; Halvorsen, Pål (Chapter; Peer reviewed; Conference object; Journal article, 2024)
      The process of re-publishing soccer videos on social media often involves labor-intensive and tedious manual adjustments, particularly when altering aspect ratios while trying to maintain key visual elements. To address ...

    • Efficient Tracking of Statistical Properties of Data Streams with Rapid Changes 

      Hammer, Hugo Lewi; Yazidi, Anis (The 26th Mediterranean Conference on Control and Automation;, Chapter; Chapter; Peer reviewed, 2018-08-23)
      Many real-life dynamical systems change rapidly followed by almost stationary periods. In this paper, we consider streams of data with such rapidly changing behavior and investigate the problem of tracking their statistical ...

    • EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System 

      Chengjie, Lu; Quinghua, Xu; Yue, Tao; Shaukat, Ali; Schwitalla, Thomas; Nygård, Jan Franz (Chapter, 2023)
      The Cancer Registry of Norway (CRN) collects information on cancer patients by receiving cancer messages from different medical entities (e.g., medical labs, hospitals) in Norway. Such messages are validated by an automated ...

    • Form Feedback on the Web: A Comparison of Popup Alerts and In-Form Error Messages 

      Hofseth, Knut Åge; Haga, Lars Kristian; Sørlie, Vegard; Sandnes, Frode Eika (Innovation in Medicine and Healthcare Systems, and Multimedia; Proceedings of KES-InMed-19 and KES-IIMSS-19 Conferences, Journal article; Chapter; Peer reviewed, 2019)
      The literature on form feedback mostly focuses on in-form error messages, yet popup alert messages are still prevalent on the web. This study, therefore, set out to identify the differences between popup alerts and in-form ...

    • Hearing Early Modern Music Through the Contemporary 

      Øvrebø, Daniel Henry (Musped:Research;Nr. 4 2022, Chapter; Peer reviewed, 2022-02-23)
      This chapter focuses on how contemporary music practice interacts with early modern1 aesthetics. Two projects, in which Georg Philip Telemann’s solo fantasias are interspersed with contemporary techniques and repertoire, ...

    • Joint Energy-Efficient Cooperative Spectrum Sensing and Power Allocation in Cognitive Machine-to-Machine Communications 

      Pham, Hai Ngoc; Zhang, Yan; Skeie, Tor; Engelstad, Paal E.; Eliassen, Frank (Peer reviewed; Chapter, 2016)
      In battery-powered Cognitive Machine-to-Machine Communications (CM2M), the energy consumption, opportunis- tic data access capacity and interference to the licensed system need to be optimized simultaneously. ...

    • Kunsten i aksjonsforskning 

      Berg, Arild (Chapter; Peer reviewed, 2017)
      Action research can be a suitable approach for artists who want to contribute to systemic change. Although action research to some extent has been explored as an artistic approach internationally, there has been no case ...

    • Kvasir-VQA: A Text-Image Pair GI Tract Dataset 

      Gautam, Sushant; Storås, Andrea; Midoglu, Cise; Hicks, Steven; Thambawita, Vajira L B; Halvorsen, Pål; Riegler, Michael Alexander (Chapter; Peer reviewed; Conference object, 2024)
      We introduce Kvasir-VQA, an extended dataset derived from the HyperKvasir and Kvasir-Instrument datasets, augmented with questionand-answer annotations to facilitate advanced machine learning tasks in Gastrointestinal (GI) ...

    • TACDEC: Dataset of Tackle Events in Soccer Game Videos 

      Kassab, Evan Jåsund; Solberg, Håkon Maric; Gautam, Sushant; Sabet, Saeed Shafiee; Torjusen, Thomas; Riegler, Michael Alexander; Halvorsen, Pål; Midoglu, Cise (Chapter, 2024)
      This paper introduces TACDEC, a dataset of tackle events in soccer game videos. Recognizing the gap in existing open datasets that predominantly focus on official soccer events such as goals and cards, TACDEC targets a ...