Sökning: "Captions"

Visar resultat 1 - 5 av 36 uppsatser innehållade ordet Captions.

1. 1. En bild säger mer än 1000 ord Könsrepresentationen under Olympiska spelen på förstasidorna i Aftonbladet & Sportbladet 1936–2020

   Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikation; Göteborgs universitet/Institutionen för journalistik, medier och kommunikation

   Författare :Sara Romano; Anja Magnusson; [2023-03-10]
   Nyckelord :genus; idrott; Olympiska spelen; Aftonbladet; Sportbladet; sportjournalistik; gender; athletics; the Olympic games; Aftonbladet; Sportbladet; sport journalism;

   Sammanfattning : Abstract A picture says more than 1000 words Sara Romano and Anja Magnusson Bachelor thesis in Journalism HT 2022 The purpose of this essay is to analyze how often female and male athletes are presented in images, captions and headlines on the front pages in the Swedish magazines Aftonbladet and Sportbladet every twelve years in the summer Olympic games from 1936. The intention of the essay is to establish how female and male athletes are described in Aftonbladet and Sportbladet in relation to nation, achievements, the perspective which the photographs are taken from and the activity of the athletes. LÄS MER

3. 2. Examining the effects of text support and noise during video meetings on listening effort and comprehension.

   Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Fredrik Fernlund; [2023]
   Nyckelord :Listening Effort; Cognitive Science; Noise; Subtitles; Text Supplementation; Video Meetings; Zoom; Remote Work; Comprehension; Comprehension in noise; Listening effort in noise; Captions; Closed Captions;

   Sammanfattning : Many companies implemented remote work procedures during the pandemic and for many organizations video meetings have since remained a staple. Remote working has enabled employees to be more flexible with their schedules and technical solutions such as live captioning has been identified as potentially enabling deaf/hard-of-hearing employees during meetings. LÄS MER

4. 3. Can Generative AI Replace Human Communication Professionals? A qualitative study comparing social media content generated by Artificial Intelligence and humans

   Kandidat-uppsats, Lunds universitet/Institutionen för strategisk kommunikation

   Författare :Deline Fredriksson; Matilda Eriksson; [2023]
   Nyckelord :Generative AI; AI visualisation tools; Artificial Intelligence; ChatGPT; DALL·E; Social Media; Content Creation; Digital Marketing; AI-generated content; Social Sciences;

   Sammanfattning : Generative AI is a novel phenomenon, now within the hands of the public. The utilisation of AI has already started replacing human employees in many industries and previous research shows that generative AI have great abilities in creative and communicative contexts. LÄS MER

5. 4. Text to Music Audio Generation using Latent Diffusion Model : A re-engineering of AudioLDM Model

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

   Författare :Ernan Wang; [2023]
   Nyckelord :Text to Music Audio Generation; Latent Diffusion; AudioLDM; Sampling Methods; Denoising Diffusion Probabilistic Model DDPM ; Denoising Diffusion Implicit Model DDIM ; Text till musik Ljudgenerering; Latent Diffusion; AudioLDM; Samplingsmetoder; DDPM; DDIM;

   Sammanfattning : In the emerging field of audio generation using diffusion models, this project pioneers the adaptation of the AudioLDM model framework, initially designed for text-to-daily sounds generation, towards text-to-music audio generation. This shift addresses a gap in the current scope of audio diffusion models, predominantly focused on everyday sounds. LÄS MER

7. 5. Efficient Utilization of Video Embeddings from Video-Language Models

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Felix Lindgren; [2023]
   Nyckelord :VLM; CLIP; transformers; machine learning; video retrieval; activitynet; efficient training; aggregation;

   Sammanfattning : In the digital age where video content is abundant, this thesis investigates the efficient adaptation of an existing video-language model (VLM) to new data. The research leverages CLIP, a robust language-vision model, for various video-related tasks including video retrieval. LÄS MER