Browsing by Author "Qureshi, Faisal"

Now showing items 1-13 of 13

    • Achieving real-time video summarization on commodity hardware 

      Taylor, Wesley (2018-04-01)
      We present a system for automatic video summarization which is able to operate in real-time on commodity hardware. This is achieved by performing segmentation to divide a video into a series of small video clips, which are ...

    • Computational and laboratory investigations of a model of blood droplet flight for forensic applications 

      Murray, Raquel (2012-09-01)
      We present a three-dimensional, forward model of blood droplets in ight. The proposed model is based on a set of ordinary di erential equations (ODEs) incorporating viscous drag and gravitational forces. We validate the ...

    • Error estimation for single-image human body mesh reconstruction 

      Jafarian, Hamoon (2023-05-01)
      Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has ...

    • Investigation into smoothed particle hydrodynamics for non-newtonian droplet modelling 

      Lobo, Gavin (2011-08-01)
      Droplet splatter dynamics is an important study in the field of forensics since a crime event can produce many blood stains. Understanding the origins of the blood stains from pure observations is very difficult because ...

    • An investigation into the use of ConvNext within IICS/IIDS framework for person Re-ID 

      Dehghani, Roya (2023-05-01)
      In this thesis, we explore the integration of ConvNeXt, a CNN-based network inspired by vision transformers, into the Intra and Inter Camera Similarity (IICS) and Intra and Inter Domain Similarity (IIDS) frameworks for ...

    • Joint spatial and layer attention for convolutional networks 

      Joseph, Tony (2019-05-01)
      In this work, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., “what” feature abstraction to attend to) and different spatial locations of the ...

    • A modular approach to image matting 

      Talpur, Mir Afgan H. (2022-11-01)
      Image matting is the art of creating an accurate alpha matte for the purpose of foreground separation in an image or video. Although there have been many methods which only require an input image, the best-performing image ...

    • Multi-character prediction using attention 

      Baeenh, Mohmmed (2020-01-01)
      We propose a computational attention approach to localize and classify characters in a sequence in a given image. Our approach combines spatial soft-attention with attention regularization and learns “where-to-look” to ...

    • Predicting multi-person dynamics 

      Karia, Chirag (2023-12-01)
      Humans unconsciously model the dynamics of the world around them; for example, we predict the movement of surrounding traffic and pedestrians while driving, or forecast player positions in a game of soccer. Our work builds ...

    • Ray tracing large distributed datasets using ray caches 

      Little, Christopher (2012-03-09)
      Many large scale simulations now produce datasets that are signi cantly larger than can typically be stored in memory on a visualization system. Visualization algorithms then become ine ective and stall since the data must ...

    • Robust curved road boundary identification using hierarchical clustering. 

      Parvin, Nurjahan (2013-11-01)
      We develop a new method for automatic curved road boundary detection in images captured by traffic cameras. The proposed method combines data driven (edge segments) and model based (2nd degree polynomial models for road ...

    • Topic models for image localization 

      Wang, Zheng (2013-08-01)
      We present a new scheme for partitioning geo-tagged reference image database in an effort to speed up query image localization while maintaining acceptable localization accuracy. Our method learns a topic model over the ...

    • Towards parallax-based unencumbered displays 

      Shanks, Ryan A. (2015-01-01)
      We present an analysis of content adaptive parallax barriers used for multi-layer unencumbered displays. We explain the techniques involved in detail from the input light field to the output masks and how to display them. ...