Sökning: "multi domain"

Visar resultat 1 - 5 av 219 uppsatser innehållade orden multi domain.

  1. 1. Image Quality Assessment Pipeline and Semi-Automated Annotation method for Synthetic Data

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Liam Le Tran; Edina Dedovic; [2023-10-24]
    Nyckelord :Facial Expression Recognition; FACS; Action Units; styleGAN2-ada; synthetic data; Image Quality Assessment; Multi-stage Pre-training; Pipeline Processing; Semi-automated Human Annotation;

    Sammanfattning : Predicting human emotions through facial expression, particularly in relation to medication field such as clinical trial settings, has garnered scientific interest in recent years due to significant understanding of the impact of treatment on emotions and social functioning. This thesis aims to improve performance of a FER model using large scale of synthetic data. LÄS MER

  3. 2. Natural Language Inference Transfer Learning in a Multi-Task Contract Dataset : In the Case of ContractNLI: a Document Information Extraction System

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Yiu Kei Tang; [2023]
    Nyckelord :;

    Sammanfattning : This thesis investigates the enhancement of legal contract Natural Language Inference (NLI) classification through supervised fine-tuning on general domain NLI, in the case of ContractNLI and Span NLI BERT (Koreeda and Manning, 2021), a multi-task document information extraction dataset and framework. Annotated datasets of a specific professional domain are scarce due to the high time and labour cost required to create them. LÄS MER

  4. 3. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders

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

    Författare :Kobe Moerman; [2023]
    Nyckelord :3D pose estimation; Joint landmarks; Variational autoencoder; Multi-task model; Loss discrimination; Latent-space modulation; Depth map; 3D-positionsuppskattning; Gemensamma landmärken; Variationell autoencoder; Multitask-modell; Förlustdiskriminering; Latent-space-modulering; Djupkarta;

    Sammanfattning : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. LÄS MER

  5. 4. Space-Division-Multiplexing Platform for a Delayed-Choice Experiment

    Master-uppsats, Linköpings universitet/Informationskodning

    Författare :Hilma Karlsson; [2023]
    Nyckelord :Wheeler s delayed choice; wave-particle delayed choice; Sagnac interferometer; Mach-Zehnder interferometer; complementarity relation; spatial modes; space-division-multiplexing; LP-modes; few-mode fibers; quantum communication; quantum optics;

    Sammanfattning : This master’s thesis explores a space-division-multiplexing (SDM) platform fora delayed-choice experiment. SDM is a multiplexing technique for optical datatransmission that employs spatial modes in a multi- or few-mode fiber to increasethe transmission capacity. The spatial modes can thus be used as separate channels. LÄS MER

  7. 5. Instance segmentation using 2.5D data

    Master-uppsats, Linköpings universitet/Institutionen för systemteknik

    Författare :Jonathan Öhrling; [2023]
    Nyckelord :instance segmentation; multi-modality; segmentation; multi-modality fusion; CNN; RGBD; ToF; Mask R-CNN; RTMDet; MMDetection; COCO; NYUDepth;

    Sammanfattning : Multi-modality fusion is an area of research that has shown promising results in the domain of 2D and 3D object detection. However, multi-modality fusion methods have largely not been utilized in the domain of instance segmentation. LÄS MER