Search for dissertations about: "Josephine Sullivan"

Found 5 swedish dissertations containing the words Josephine Sullivan.

2. 1. Structured Representations for Explainable Deep Learning

   Author : Federico Baldassarre; Hossein Azizpour; Josephine Sullivan; Kevin Smith; Hamed Pirsiavash; KTH; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Explainable AI; Deep Learning; Self-supervised Learning; Transformers; Graph Networks; Computer Vision; Explainable AI; Deep Learning; Self-supervised Learning; Transformers; Graph Networks; Computer Vision; Datalogi; Computer Science;

   Abstract : Deep learning has revolutionized scientific research and is being used to take decisions in increasingly complex scenarios. With growing power comes a growing demand for transparency and interpretability. The field of Explainable AI aims to provide explanations for the predictions of AI systems. READ MORE

4. 2. Shape-based Representations and Boosting for Visual Object Class Detection : Models and methods for representaion and detection in single and multiple views

   Author : Oscar Danielsson; Stefan Carlsson; Josephine Sullivan; Bernt Schiele; KTH; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES;

   Abstract : Detection of generic visual object classes (i.e. cars, dogs, mugs or people) in images is a task that humans are able to solve with remarkable ease. Unfortunately this has proven a very challenging task for computer vision. READ MORE

5. 3. Convolutional Network Representation for Visual Recognition

   Author : Ali Sharif Razavian; Atsuto Maki; Stefan Carlsson; Josephine Sullivan; Josef Sivic; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Convolutional Network; Visual Recognition; Transfer Learning; Computer Science; Datalogi;

   Abstract : Image representation is a key component in visual recognition systems. In visual recognition problem, the solution or the model should be able to learn and infer the quality of certain visual semantics in the image. READ MORE

6. 4. Deep Learning for Active Fire Detection Using Multi-Source Satellite Image Time Series

   Author : Yu Zhao; Yifang Ban; Andrea Nascetti; Josephine Sullivan; Cartalis Constantinos; KTH; []
   Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Wildfire; Remote Sensing; Active Fire Detection; GOES-R ABI; Suomi-NPP VIIRS; Image Segmentation; Deep Learning; Gated Recurrent Units GRU ; Transformer.; Vilda Bränder; Fjärranalys; Aktiv Branddetektering; GOES- R ABI; Suomi-NPP VIIRS; Bildsegmentering; Djupinlärning; Gated Recurrent Units GRU ; Transformer; Geoinformatik; Geoinformatics;

   Abstract : In recent years, climate change and human activities have caused increas- ing numbers of wildfires. Earth observation data with various spatial and temporal resolutions have shown great potential in detecting and monitoring wildfires. READ MORE

7. 5. Human Face Identification and Face Attribute Prediction : From Gabor Filtering to Deep Learning

   Author : Yang Zhong; Haibo Li; Josephine Sullivan; Juyang (John) Weng; KTH; []
   Keywords : Media Technology; Medieteknik;

   Abstract : After decades of research, it is exciting to see that face recognition technology has entered a most flourishing era. Driven by the latest development in data science and especially technical evolutions in computer vision and pattern recognition, face recognition has achieved significant progress over the last three years. READ MORE