Sökning: "visual question answering"
Visar resultat 1 - 5 av 17 uppsatser innehållade orden visual question answering.
1. LE OCH VINKA POLITIKER! En kvantitativ innehållsanalys av svenska EUparlamentarikers självpresentation på Instagram
Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikationSammanfattning : The evolution of social media has changed the way people communicate, among other things the political communication. On social media political actors can communicate directly to their audience and circumvent the traditional media, and it is also platforms that have a more personal focus. LÄS MER
2. 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
3. COMPLEXITY & RANDOMNESS Exploring the Limits of Pattern Perception
Kandidat-uppsats, Institutionen för tillämpad informationsteknologiSammanfattning : Pattern perception is a core part of human cognition, however, our capacity to process patterns is limited. If a pattern is too complex to process, we no longer perceive it as a pattern but rather as noise, thus we hypothesize that there is a limit to human pattern perception that can be measured in terms of the complexity of the pattern. LÄS MER
4. KAN DU BJUDA PÅ ETT LEENDE?
Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikationSammanfattning : CAN YOU GIVE US A SMILE? The purpose of this study is to examine if the communication differs between journalists and female and male professional football players during live-interview situations. Since the 1900s sports journalism has grown into what we today consider a main subject in modern journalism (Dahlén, 2008:71-72). LÄS MER
5. There’s a Microwave in the Hallway
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Embodied Question Answering (EQA) is a task in which an agent situated in virtual environment navigates from its current position to an object (Navigation), and then answer a question about it (Visual Question Answering, VQA), for example “What color is the table in the table in the kitchen?” This project examines how an agent modelled as a deep neural network uses semantic information from its language model and visual information to answer questions in the second task. This is important since due to the regular nature of the task and the dataset it could be that the model is answering questions purely based on general semantic information from its language model (tables are frequently brown) and not relying on the visual scene, a phenomenon that is commonly known as hallucinating. LÄS MER