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 20 of 171 for “"Visual scene"”.
-
Active visual scene exploration
… one or several active cameras in the context of visual surveillance. This approach has two advantages. Firstly, any system dealing with real inputs must take into account noise in the measurements and the underlying system model. Secondly, the control of cameras in surveillance often has …
-
Efficient Structured Prediction for Visual Scene Understanding
This thesis focuses on three topics in visual scene understanding, sorted from low level to high level: unsupervised segmentation, collision-free space detection and holistic scene understanding. All of them are modeled within the framework of probabilistic graphical models. We tackle the problem …
-
DEEP VISUAL SCENE UNDERSTANDING: CLASSIFICATION, SEGMENTATION AND PREDICTION
Scene understanding including scene classification, scene parsing, prediction in the future scenes, etc., has attracted intense interests in both academia and industry. Traditional works are based on hand-crafted features followed by simple classifiers which have limited learning capabilities. In …
-
Visual Scene Understanding by Deep Fisher Discriminant Learning
… machine learning and computer vision, such as, scene understanding, natural language processing and machine translation. The substitution of feature hand-crafting with automatic feature learning, provides an excellent opportunity for gaining an in-depth understanding of large-scale data …
-
Visual scene recognition with biologically relevant generative models
This research focuses on developing visual object categorization methodologies that are based on machine learning techniques and biologically inspired generative models of visual scene recognition. Modelling the statistical variability in visual patterns, in the space of features extracted from …
-
Audio-Visual Scene Reconstruction of Geometry and Acoustic Fields
Reconstructing 3D scenes from sensor observations is an important problem in computer vision and embodied AI, with broad applications in augmented and virtual reality (AR/VR), robotics, telepresence, and immersive media. As real-world environments are spatially complex and rich in audio-visual …
-
Audio-Visual Scene Analysis With Application in Sports Video
"The last part of the thesis presents our work on ""single-channel audio source separation"" using generative probabilistic models. The approach can be potentially very useful as a pre-processing step for the key audio ""objects"" detection."
-
Audio-Visual Scene-Aware Dialog: A Step Towards Multimodal Conversational Agents
… agents, this dissertation introduces the Audio Visual Scene-Aware Dialog task. This task involves generating coherent responses to questions about a dynamic scene, leveraging video and audio inputs alongside the dialog history. To facilitate benchmarking of this task, the Audio Visual …
-
Neural framework for visual scene analysis with selective attention / by Eric Wai-Shing Chong.
… framework based on neural networks for visual scene analysis with attentional mechanisms.
-
Ανάπτυξη Οπτικών Προβολών Σκηνικών (Visual Scene Displays) για αποκατάσταση επικοινωνίας σε ασθενείς με αφασία
… study) της ανάπτυξης οπτικών προβολών σκηνικών (Visual Scene Displays) με στόχο την αποκατάσταση επικοινωνίας σε ασθενείς με αφασία. Οι οπτικές προβολές σκηνικών (VSD’s), έχουν αναπτυχθεί τα τελευταία χρόνια στο εξωτερικό και στα ελληνικά δεδομένα δεν υπάρχουν ακόμα μελέτες. Το χρονικό διάστημα …
-
Transferrable learning from synthetic data: novel texture synthesis using Domain Randomization for visual scene understanding
… in a simulator, such as the objects, their visual appearance, the lighting, and where they appear in the picture. This synthetic data can be used to train systems capable of performing well in reality. However, it is unclear how to best approach selecting Domain Randomization parameters such …
-
Typically developing preschooler's location of digital photos on speech generating devices using visual scene displays
… graphic symbols on the main page of a dynamic visual scene display (VSD) using embedded and non- embedded symbols. Method: Twenty participants were equally divided into two experimental conditions that included embedded or non-embedded VSDs. Participants were assigned to one of the two …
-
Learning of embedded and non-embedded visual scene display AAC technologies by typically developing 2-year-olds.
… that young children learn to locate symbols on visual scene displays (VSDs) more efficiently than on traditional grid displays (Drager, Light, Speltz & Jefferies, 2003). This study examined the effects of two different types of VSDs on three typically-developing two-year-olds’ abilities to …
-
A pilot study on the gait kinematics in children with autism during perturbations of visual scene and support surface
… the gait kinematics of children with ASD under a visually and proprioceptively challenging environments. We aimed to test whether children with ASD and TDC were similarly responsive to visual and treadmill perturbations (VP and TP). The second aim was to investigate how children with ASD and TDC …
-
A Comparison of Visual Scene and Traditional Grid Layouts of Augmentative and Alternative Communication Devices During Storybook Reading with Typically Developing Three-Year-Old Children
… there are two types of layouts that may be used, visual scene and traditional grid layouts. The purpose of this study was to compare these two types of layouts during storybook reading. Ten typically developing three-year-old children served as participants. The children were randomly separated …
-
Self-supervised Scene Representation Using Structured Representations for Surgical Applications
… image segmentation, novel view synthesis, and visual scene understanding, to name a few. Motivated by these advancements, we explore various learning schemes for comprehensive visual scene understanding of dynamic scenes. We assess the efficacy of our approach in the domain of laparoscopic …
-
Representations of Active Vision
… dissertation focuses on the interplay between visual processing and motor action during natural behaviors, which has previously been limited due to technological constraints in experimental paradigms. However, recent technological innovations have improved the data collection process, enabling …
Page 1 of 9