Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Nazli Ikizler-Cinbis"'
Autor:
Ramin Abbaszadi, Nazli Ikizler-Cinbis
Publikováno v:
IEEE Access, Vol 10, Pp 30436-30444 (2022)
In video surveillance, visual person attributes such as gender, backpack, type of clothing are crucial for person search or re-identification. For detecting and retrieving these attributes with high accuracy, the availability of high-quality videos i
Externí odkaz:
https://doaj.org/article/fb654dc24352476e9c40b53b4c816860
Autor:
Aytac Cavent, Nazli Ikizler‐Cinbis
Publikováno v:
IET Computer Vision, Vol 12, Iss 6, Pp 844-854 (2018)
This study presents a novel representation based on hierarchical histogram of local feature sequences for human interaction recognition. The authors’ method basically combines the power of discriminative sequence mining and histogram representation
Externí odkaz:
https://doaj.org/article/d670f3d0016a445fbeea02e5973adddc
Autor:
Mert Kilickaya, Burak Kerim Akkus, Ruket Cakici, Aykut Erdem, Erkut Erdem, Nazli Ikizler‐Cinbis
Publikováno v:
IET Computer Vision, Vol 11, Iss 6, Pp 398-406 (2017)
In the past few years, automatically generating descriptions for images has attracted a lot of attention in computer vision and natural language processing research. Among the existing approaches, data‐driven methods have been proven to be highly e
Externí odkaz:
https://doaj.org/article/d6956dcf808e4f44b78a6d469c051ca2
Autor:
Cemil Zalluhoglu, Nazli Ikizler-Cinbis
Publikováno v:
Signal, Image and Video Processing. 16:865-872
In this study, we utilize attention mechanisms to leverage the spatio-temporal information available in videos for the action recognition and collective activity recognition tasks. In this context, we explore 2D and 3D attention mechanisms and invest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6de77f1cd54b9d5e28ce56f8eba02ac9
https://doi.org/10.1007/s11760-021-02028-8
https://doi.org/10.1007/s11760-021-02028-8
Publikováno v:
Pattern Recognition Letters. 146:70-76
Collecting textual descriptions is an especially costly task for dense video captioning, since each event in the video needs to be annotated separately and a long descriptive paragraph needs to be provided. In this paper, we investigate a way to miti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cbb53b1f0ca3454aa71e554386cf18d
https://doi.org/10.1016/j.patrec.2021.02.009
https://doi.org/10.1016/j.patrec.2021.02.009
Publikováno v:
Annu Int Conf IEEE Eng Med Biol Soc
In our comprehensive experiments and evaluations, we show that it is possible to generate multiple contrast (even all synthetically) and use synthetically generated images to train an image segmentation engine. We showed promising segmentation result
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::123652e3da4879af7f108be26808f8b9
https://doi.org/10.1109/embc48229.2022.9871119
https://doi.org/10.1109/embc48229.2022.9871119
Autor:
Gokhan Yaliniz, Nazli Ikizler-Cinbis
Publikováno v:
Multimedia Tools and Applications. 80:17827-17847
Sigmoid and hyperbolic activation functions in long short-term memory (LSTM) and gated recurrent unit (GRU) based models used in recent studies on video summarization, may cause gradient decay over layers. Moreover, interpreting and developing networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34e78e474968692882c16b5c88b93a69
https://doi.org/10.1007/s11042-020-10293-x
https://doi.org/10.1007/s11042-020-10293-x
This paper tackles the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign classes to recognize the instances of unseen sign classes. In this context, readily available textual sign
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab2d9e3a45091bcf528907c1f7550d6a
http://arxiv.org/abs/2201.05914
http://arxiv.org/abs/2201.05914
Autor:
Nazli Ikizler-Cinbis, Cemil Zalluhoglu
Publikováno v:
Journal of Visual Communication and Image Representation. 60:170-179
Collective activity recognition, which analyses the behavior of groups of people in videos, is an important goal of video surveillance systems. In this paper, we focus on collective activity recognition problem and propose a new multi-stream convolut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91ae4beb1ecfa48a9c2bd274b3c3f99b
https://doi.org/10.1016/j.jvcir.2019.02.016
https://doi.org/10.1016/j.jvcir.2019.02.016
Recognizing human interactions in still images is quite a challenging task since compared to videos, there is only a glimpse of interaction in a single image. This work investigates the role of human poses in recognizing human–human interactions in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9af4838f10096bef65914eb0abb7f1e4
https://aperta.ulakbim.gov.tr/record/236236
https://aperta.ulakbim.gov.tr/record/236236