Sökning: "vision"
Visar resultat 16 - 20 av 5175 uppsatser innehållade ordet vision.
16. Att vara eller icke vara jämställd. Vad är det för fråga? : Göteborg Film Festival ur ett feministiskt jämställdhetsperspektiv
Kandidat-uppsats, Linnéuniversitetet/Institutionen för film och litteratur (IFL)Sammanfattning : This BA thesis studies Göteborg Film Festival from a feminist theoretical perspective. It examines how the festival responds to recent efforts of working towards gender equality in the film industry. LÄS MER
17. Night Vision Goggle Simulation in a Mixed Reality Flight Simulator with Seamless Integrated Real World
Magister-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakultetenSammanfattning : Night vision goggles (NVGs) are optical devices used to enhance human vision at low light conditions such as nighttime. The image seen through the goggles is brightened but with the consequence of introduced visual limitations and illusions. LÄS MER
18. Visualization and analysis of object states using diffusion models and PyTorch
Kandidat-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : Artificial Intelligence (AI) is an extremely rapidly growing field in modern technology. As the applications of AI expand, the ability to accurately analyze and predict the condition of various objects through various models has profound implications across numerous industries. LÄS MER
19. Where to Fuse
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : This thesis investigates fusion techniques in multimodal transformer models, focusing on enhancing the capabilities of large language models in understanding not just text, but also other modalities like images, audio, and sensor data. The study compares late fusion (concatenating modality tokens after separate encoding) and early fusion (concatenating before encoding) techniques, examining their respective advantages and disadvantages. LÄS MER
20. Self-Supervised Learning for Tabular Data: Analysing VIME and introducing Mix Encoder
Kandidat-uppsats, Lunds universitet/Fysiska institutionenSammanfattning : We introduce Mix Encoder, a novel self-supervised learning framework for deep tabular data models based on Mixup [1]. Mix Encoder uses linear interpolations of samples with associated pretext tasks to form useful pre-trained representations. LÄS MER
