Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Birinci-Şahıs Videolarda Aktivite Tanıma İçin Sıralamalı Takviyeli Çoklu Çekirdek Öğrenmesi
Date
2018-05-05
Author
Özkan, Fatih
Sürer, Elif
Temizel, Alptekin
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
102
views
0
downloads
Cite This
In this paper, we investigate fusion of different types of classifiers for activity recognition on first-person videos in a data-driven approach. The algorithm first uses the classifiers, which are composed of kernel and descriptor combinations, through well-known AdaBoost trials. After all trials, classifiers are ordered and assigned ranks with respect to their performances in each trial separately. These classifiers compose a candidate list according to their performance ranks. Classifiers in the candidate list are employed together on the training set again. Classifiers in most successful candidate lists are combined as final classifiers. Our experiments show improvements in recognition comparison to traditional methods.
Subject Keywords
Activity recognition
,
Multiple kernel learning
,
Boosting
URI
https://hdl.handle.net/11511/31248
DOI
https://doi.org/10.1109/siu.2018.8404221
Conference Name
26th IEEE Signal Processing and Communications Applications Conference (SIU)
Collections
Graduate School of Informatics, Conference / Seminar
Suggestions
OpenMETU
Core
Quantifying and mitigating class imbalance in long-tailed visual recognition
Baltacı, Zeynep Sonat; Kalkan, Sinan; Akbaş, Emre; Department of Computer Engineering (2022-7)
Objects are distributed unevenly in real world, which manifests itself as a long-tailed distribution in realistic visual recognition datasets. Deep learning based approaches trained on such imbalanced datasets using conventional gradient-based training strategies exhibit unfair recognition performances towards classes that are under-represented in the dataset. This so-called class imbalance has been studied in the literature by measuring imbalance via either class frequency or class hardness, and using thos...
Discretized categorization of high level traffic activities in tunnels using attribute grammars
Büyüközcü, Demirhan; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2012)
This work focuses on a cognitive science inspired solution to an event detection problem in a video domain. The thesis raises the question whether video sequences that are taken in highway tunnels can be used to create meaningful data in terms of symbolic representation, and whether these symbolic representations can be used as sequences to be parsed by attribute grammars into abnormal and normal events. The main motivation of the research was to develop a novel algorithm that parses sequences of primitive ...
Human activity classification using spatio-temporal feature relations
Akpınar, Kutalmış; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2012)
This thesis compares the state of the art methods and proposes solutions for human activity classification from video data. Human activity classification is finding the meaning of human activities, which are captured by the video. Classification of human activity is needed in order to improve surveillance video analysis and summarization, video data mining and robot intelligence. This thesis focuses on the classification of low level human activities which are used as an important information source to dete...
Almost periodic solutions of recurrently structured impulsive neural networks
Top, Gülbahar; Akhmet, Marat; Department of Mathematics (2022-3-28)
This thesis aims to conduct detailed and precise neural networks research with impulses at nonprescribed moments in terms of periodic and almost periodic solutions. Most of the actions in nature modeled by neural networks involve repetitions. Hence periodic and almost periodic motions become crucial. So in this thesis, the existence, uniqueness, and stability of the periodic and almost periodic motion are served for the neural networks with prescribed and nonprescribed impacts. This impulsive system is a n...
Utilizing video colorization as a self-supervised auxiliary task for object tracking
Fırat, Engin; Akbaş, Emre; Department of Computer Engineering (2021-2-08)
In this thesis work, we studied combining an object tracker, which uses siamese networks, with another model that is trained by using the self-supervised learning paradigm. We define grayscale video colorization as a pretext task for self-supervised learning and we select the similarity based object tracking as a downstream task. Both the siamese network based object tracker and the colorization network model use the similarity between subsequent video frames. The spatio-temporal coherence between the frame...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
F. Özkan, E. Sürer, and A. Temizel, “Birinci-Şahıs Videolarda Aktivite Tanıma İçin Sıralamalı Takviyeli Çoklu Çekirdek Öğrenmesi,” presented at the 26th IEEE Signal Processing and Communications Applications Conference (SIU), Izmir, TURKEY, 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/31248.