Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 13 of 13 for “"Visual correspondence"”.

  1. The compositional character of visual correspondence

    … the points in the two images is known as the correspondence problem. Stereo correspondence is a special case in which corresponding points lie on the same row in the two images; optical flow is the general case. In this thesis, we argue that correspondence is inextricably linked to other …

    maryland Repository record for The compositional character of visual correspondence (opens in a new tab)

  2. Synthetic training data for deep neural networks on visual correspondence tasks

    Im Maschinellen Sehen erzielen tendenziell diejenigen tiefen neuronalen Netzwerke die besten Resultate, welche nach dem Schema des überwachten Lernens trainiert wurden.<br>Hierbei enthält jeder Datenpunkt eines Trainingsdatensatzes eine Annotation mit einer korrekten Ausgabe, die zu reproduzieren …

    freiburg-diss Repository record for Synthetic training data for deep neural networks on visual correspondence tasks (opens in a new tab)

  3. Statistical Anomaly Discovery Through Visualization

    … often perform statistical analyses through visualization to develop such understanding. However, applicable insight can be difficult due to biases and anomalies in data. An often overlooked phenomenon is mix effects, in which subgroups of data exhibit patterns opposite to the data as a …

    oklahoma-thes Repository record for Statistical Anomaly Discovery Through Visualization (opens in a new tab)

  4. Me he tāheke te wai i aku kamo = Waterfalls of tears : an exhibition report presented in partial fulfilment of the requirements for the degree of Masters in Māori Visual Arts, Massey University, Palmerston North, New Zealand

    … wairuatanga and the metaphysical. Post-contact visual representation of Whanganui iwi, wai and whenua highlights the focus of the colonial lens to be commercially motivated whereas that of the indigenous lens to be grounded in kaupapa. The works of a range of contemporary artists who portray …

    massey Repository record for Me he tāheke te wai i aku kamo = Waterfalls of tears : an exhibition report presented in partial fulfilment of the requirements for the degree of Masters in Māori Visual Arts, Massey University, Palmerston North, New Zealand (opens in a new tab)

  5. Modifications of imaging spectroscopy methods for increases spatial and temporal consistency: a case study of change in leafy spurge distribution between 1999 and 2001 in Theodore Roosevelt National Park, North Dakota

    … from adjacent flight lines, as well as good visual correspondence, indicated that the mapping method produced consistent maps. Overall accuracy of area-wide spurge maps varied from 39% to 82%. Registration problems accounted for some of this variability. Some validation data and methods were …

    colostate Repository record for Modifications of imaging spectroscopy methods for increases spatial and temporal consistency: a case study of change in leafy spurge distribution between 1999 and 2001 in Theodore Roosevelt National Park, North Dakota (opens in a new tab)

  6. Incremental object matching with probabilistic methods

    … In matching the object in a test image, the visual correspondence of the points as well as their spatial layout is usually considered simultaneously. Typically the corresponding points of the object are manually pre-annotated in the training images which facilitates the learning process. In …

    aalto Repository record for Incremental object matching with probabilistic methods (opens in a new tab)

  7. Visually grounded language understanding and generation

    … Specifically, I cover these four tasks: visual question answering, neural image captioning, visual dialog and vision and language pretraining. In visual question answering, we collected a large scale visual question answering dataset and I study various baselines to benchmark these tasks. …

    gatech Repository record for Visually grounded language understanding and generation (opens in a new tab)

  8. Geometric Modeling of Bio-Inspired Topologically Interlocking Space-Filling Shapes

    … the design of interlocking shapes by finding a visual correspondence with weave symmetry. Then we do a structural analysis and compare the results of three such topologically interlocking assemblies we get using predefined Voronoi sites. The results show that the tiles have a well-defined stress …

    tamu Repository record for Geometric Modeling of Bio-Inspired Topologically Interlocking Space-Filling Shapes (opens in a new tab)

  9. Audio-visual deep learning

    … utilizing the natural co-occurrence of audio and visual information in videos to learn useful tasks.</p> <p>The thesis is structured around four main themes: (i) lip reading and Audio-Visual Speech Recognition (AVSR); (ii) audio-visual speech enhancement and separation; (iii) audio-visual sound …

    oxford Repository record for Audio-visual deep learning (opens in a new tab)

  10. Automating Manufacturing Surveillance Processes Using External Observers

    … operator safety and reduction in cycle-time, visual surveillance plays a critical role in providing real-time alerts of spatiotemporal parts irregularities. In this study, surveillance videos are obtained using external observers to conduct spatiotemporal object segmentation within: digital …

    waterloo Repository record for Automating Manufacturing Surveillance Processes Using External Observers (opens in a new tab)

  11. Media Space: an analysis of spatial practices in planar pictorial media.

    The thesis analyses the visual space displayed in pictures, film, television and digital interactive media. The argument is developed that depictions are informed by the objectives of the artefact as much as by any simple visual correspondence to the observed world. The simple concept of ‘realism’ …

    middlesex Download PDF for Media Space: an analysis of spatial practices in planar pictorial media. (opens in a new tab)

  12. Vision-based navigation and mapping for flight in GPS-denied environments

    Traditionally, the task of determining aircraft position and attitude for automatic control has been handled by the combination of an inertial measurement unit (IMU) with a Global Positioning System (GPS) receiver. In this configuration, accelerations and angular rates from the IMU can be …

    gatech Repository record for Vision-based navigation and mapping for flight in GPS-denied environments (opens in a new tab)