Ibrahim Batuhan Akkaya
Ibrahim Batuhan Akkaya has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Bahram Zonooz
Advanced Research Lab, NavInfo Europe
1 shared publication - Cagri Toraman
Computer Engineering Department Middle East Technical University
1 shared publication Elahe Arani
1 shared publication- Eyup Halit Yilmaz
ASELSAN AS
1 shared publication - Furkan Şahinuç
Aselsan Research Center, Ankara, Turkey
1 shared publication Senthilkumar S. Kathiresan
1 shared publication
Latest Publications
- 21 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 153
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation
- 21 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 153
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation
- 31 March 2022
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 12 (1) , 1-16
Understanding social engagements: A comparative analysis of user and text features in Twitter
Information is spread as individuals engage with other users in the underlying social network. Analysis of social engagements can therefore provide insights to understand the motivation behind how and why users engage with others in different activities. In this study, we aim to understand the driving factors behind four engagement types in Twitter, namely like, reply, retweet, and quote. We extensively analyze a diverse set of features that reflect user behaviors, as well as tweet attributes and semantics by natural language processing, including a deep learning language model, BERT. The performance of these features is assessed in a supervised task of engagement prediction by learning social engagements from over 14 million multilingual tweets. In the light of our experimental results, we find that users would engage with tweets based on text semantics and contents regardless of tweet author, yet popular and trusted authors could be important for reply and quote. Users who actively liked and retweeted in the past are likely to maintain this type of behavior in the future, while this trend is not seen in more complex types of engagements, reply, and quote. Moreover, users do not necessarily follow the behavior of other users with whom they have previously engaged. We further discuss the social insights obtained from the experimental results to understand better user behavior and social engagements in online social networks.
- 31 March 2022
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 12 (1) , 1-16
Understanding social engagements: A comparative analysis of user and text features in Twitter
Information is spread as individuals engage with other users in the underlying social network. Analysis of social engagements can therefore provide insights to understand the motivation behind how and why users engage with others in different activities. In this study, we aim to understand the driving factors behind four engagement types in Twitter, namely like, reply, retweet, and quote. We extensively analyze a diverse set of features that reflect user behaviors, as well as tweet attributes and semantics by natural language processing, including a deep learning language model, BERT. The performance of these features is assessed in a supervised task of engagement prediction by learning social engagements from over 14 million multilingual tweets. In the light of our experimental results, we find that users would engage with tweets based on text semantics and contents regardless of tweet author, yet popular and trusted authors could be important for reply and quote. Users who actively liked and retweeted in the past are likely to maintain this type of behavior in the future, while this trend is not seen in more complex types of engagements, reply, and quote. Moreover, users do not necessarily follow the behavior of other users with whom they have previously engaged. We further discuss the social insights obtained from the experimental results to understand better user behavior and social engagements in online social networks.
- Open Access
- 1 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1586-1590
GAIT: Gradient Adjusted Unsupervised Image-To-Image Translation
Image-to-image translation (IIT) has made much progress recently with the development of adversarial learning. In most of the recent work, an adversarial loss is utilized to match the distributions of the translated and target image sets. However, this may create artifacts if two domains have different marginal distributions, for example, in uniform areas. In this work, we propose an unsupervised IIT method that preserves the uniform regions after the translation. The gradient adjustment loss, which is the L2 norm between the Sobel response of the target image and the adjusted Sobel response of the source images, is utilized. The proposed method is validated on the jellyfish-to-Haeckel dataset, which is prepared to demonstrate the mentioned problem, which contains images with different background distributions. We demonstrate that our method obtained a performance gain compared to the baseline method qualitatively and quantitatively, showing the effectiveness of the proposed method.
- 1 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1586-1590
Open AccessGAIT: Gradient Adjusted Unsupervised Image-To-Image Translation
Image-to-image translation (IIT) has made much progress recently with the development of adversarial learning. In most of the recent work, an adversarial loss is utilized to match the distributions of the translated and target image sets. However, this may create artifacts if two domains have different marginal distributions, for example, in uniform areas. In this work, we propose an unsupervised IIT method that preserves the uniform regions after the translation. The gradient adjustment loss, which is the L2 norm between the Sobel response of the target image and the adjusted Sobel response of the source images, is utilized. The proposed method is validated on the jellyfish-to-Haeckel dataset, which is prepared to demonstrate the mentioned problem, which contains images with different background distributions. We demonstrate that our method obtained a performance gain compared to the baseline method qualitatively and quantitatively, showing the effectiveness of the proposed method.