|
|
Football Event Recognition for Spatiotemporal Data of Gaming Objects
Čížek, Tomáš ; Bartík, Vladimír (referee) ; Rychlý, Marek (advisor)
This diploma thesis deals with automatic soccer event detection . Its goal is to introduce reader to this issue , discuss possible ways of solution of this task and then implement event detection . This work aims at event recognition using spatio - temporal data of gaming objects . Introduced way of dealing with event detection lies in its converting to sequence labeling task . Then such task is solved using LSTM recurrent neural networks . Lastly , result of sequence labeling is interpreted as detected events . Library for event detection has been created as the output of this work . This library allow user to experiment with different variants how to formulate event detection as sequence labeling task .
|
|
|
Signal propagation in neural networks
Blaštík, Filip ; Šanda, Pavel (advisor) ; Bureš, Zbyněk (referee)
A proper account of signal propagation in neuronal networks is the key to developing a genuine understanding of information processing accomplished by the brain. The data can often be in the form of the complex activity of neuronal assemblies and their spiking patterns. Under particular circumstances, neuronal assemblies produce a coordinated synchronized activity with the profile of travelling waves. These have been shown to represent the information processing of, e.g., perceptual sensitivity. We decided to model the phenomenon of the travelling wave by using a spiking neural network model of 1mm2 of primate's early visual cortices. The modelled neural column was employed to generate synchronized activity. By interconnecting said columns, we were able to model the travelling wave. In order to describe its dynamics, we developed several event-detection algorithms to identify such a travelling wave from simulated neural columns. We discovered that methods based on the detection of local dynamics in moving windows rendered most adequately the intuitive idea of the travelling wave. After establishing our event-detection approach, we shifted the focus to causal inference. Signal propagation is commonly inferred by abstract theoretical concepts like the Granger causality or transfer entropy. In this work, we...
|
|
| |
|
| |
|
|
Football Event Recognition for Spatiotemporal Data of Gaming Objects
Čížek, Tomáš ; Bartík, Vladimír (referee) ; Rychlý, Marek (advisor)
This diploma thesis deals with automatic soccer event detection . Its goal is to introduce reader to this issue , discuss possible ways of solution of this task and then implement event detection . This work aims at event recognition using spatio - temporal data of gaming objects . Introduced way of dealing with event detection lies in its converting to sequence labeling task . Then such task is solved using LSTM recurrent neural networks . Lastly , result of sequence labeling is interpreted as detected events . Library for event detection has been created as the output of this work . This library allow user to experiment with different variants how to formulate event detection as sequence labeling task .
|
|
|
Semantics in Multimedia: Event detection and cross-media feature extraction
Nemrava, Jan ; Svátek, Vojtěch (advisor) ; Berka, Petr (referee) ; Smrž, Pavel (referee)
This dissertation thesis describes the area of multimedia semantics which is a research area that brings together research streams that until recently run separately. The aim of the work is to provide an insight to all areas from this wide discipline and give an outlook on current problems especially to the semantic gab phenomena. Number of findings and outcomes in this work comes from international project K-Space, in which the author took part for three years. The extensive theoretical introduction into problematic is followed by a list state-of-the-art application from this area and overview of KIZI activities and involvements in the European project. The contribution of the work is a research on textual resources complementary to video and experiments with automatic detection of sporting events based on pre-classified examples and trained model. The practical contribution is also a demo web application that shows all the resources together and allows non-linear browsing of events.
|
guest ::
