Sökning: "video encoder"

Visar resultat 1 - 5 av 46 uppsatser innehållade orden video encoder.

  1. 1. Visual Attention Guided Adaptive Quantization for x265 using Deep Learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Mikaela Gärde; [2023]
    Nyckelord :video encoding; deep learning; visual attention; adaptive quantization; videokodning; djupinlärning; visuellt fokus; adaptiv kvantisering;

    Sammanfattning : The video on demand streaming is raising drastically in popularity, bringing new challenges to the video coding field. There is a need for new video coding techniques that improve performance and reduce the bitrates. LÄS MER

  3. 2. Regularizing Vision-Transformers Using Gumbel-Softmax Distributions on Echocardiography Data

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Alfred Nilsson; [2023]
    Nyckelord :Deep Learning; Vision-Transformers; Echocardiography; Feature Selection; Gumbel-Softmax; Concrete Autoencoders; Regression; Djupinlärning; Vision-Transformers; Ekokardiografi; Feature Selection; GumbelSoftmax; Concrete Autoencoders; Regression;

    Sammanfattning : This thesis introduces an novel approach to model regularization in Vision Transformers (ViTs), a category of deep learning models. It employs stochastic embedded feature selection within the context of echocardiography video analysis, specifically focusing on the EchoNet-Dynamic dataset. LÄS MER

  4. 3. AI Second that Emotion - Using Natural Language Processing to Study the Impact of Non-Stereotyped Video Advertising on Consumers’ Emotions & Online Consumer Engagement

    Master-uppsats, Göteborgs universitet/Graduate School

    Författare :Amanda Hassel; Linnea Jonsson; Johan Strömfeldt; [2022-08-04]
    Nyckelord :Stereotype; Video Advertisement; Emotions; Online Consumer Engagement; Natural Language Processing NLP ; Artificial Intelligence AI ; Machine Learning; Bidirectional Encoder Representation from Transformers BERT ; Transformer Models;

    Sammanfattning : This paper aims to provide a deeper understanding of the emotional and online engagement behavioral responses to non-stereotyped gender role depictions in video advertisements. The consumer response to two video ads that portray non-stereotyped gender roles by the well-known brands Gillette and Always was analyzed. LÄS MER

  5. 4. Making Video Streaming More Efficient Using Per-Shot Encoding

    Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Douglas Gådin; Fanny Hermanson; Anton Marhold; Joel Sikström; Johan Winman; [2022]
    Nyckelord :per-shot encoding; video streaming; encoding; transcoding; per-shot kodning; videoströmmning; videokodning; transkodering;

    Sammanfattning : The demand for streaming high-quality video increases each year and the energy used by consumers is estimated to increase by 23% from 2020 to 2030. The largest contributor to this is increased data transmission. LÄS MER

  7. 5. Pedestrian Multiple Object Tracking  Using Deep Learning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Uvais Karni Mohideen Meera Sha; [2021]
    Nyckelord :;

    Sammanfattning : In this thesis, the aim is to examine the viability of Deep Neural  Network (DNN) based Multi-Object Tracking approaches for tracking  pedestrians. The tracking results are used for Autonomous Driver Assistance System (ADAS). The process of tracking multiple agents  across video is termed as Multiple Object Tracking (MOT). LÄS MER