Pinar Duygulu

108 papers A* 4A 4B 10Misc 1Journal 37Unranked 51
YearRankTypeTitle / Venue / Authors
2025 J jnl
NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation.
CoRR
Serkan Ozturk, Samet Hicsonmez, Pinar Duygulu
2025 J jnl
WAIT: Feature warping for animation to illustration video translation using GANs.
Neurocomputing
Samet Hicsonmez, Nermin Samet, Fidan Samet, Oguz Bakir, Emre Akbas, Pinar Duygulu
2024 — conf
Automatic Data Augmentation for Cooking Videos.
SIU
Yunus Emre Özköse, Pinar Duygulu
2023 — conf
Alignment of Image-Text and Video-Text Datasets.
SIU
Yunus Emre Özköse, Zeynep Gökce, Pinar Duygulu
2023 A* conf
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness.
ICCV
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2023 J jnl
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness.
CoRR
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2023 J jnl
Improving Sketch Colorization using Adversarial Segmentation Consistency.
CoRR
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2023 J jnl
Learning actionness from action/background discrimination.
Signal Image Video Process.
Ozge Yalcinkaya Simsek, Olga Russakovsky, Pinar Duygulu
2023 J jnl
Multi-task learning for gland segmentation.
Signal Image Video Process.
Iman Rezazadeh, Pinar Duygulu
2023 J jnl
WAIT: Feature Warping for Animation to Illustration video Translation using GANs.
CoRR
Samet Hicsonmez, Nermin Samet, Fidan Samet, Oguz Bakir, Emre Akbas, Pinar Duygulu
2022 J jnl
How Robust are Discriminatively Trained Zero-Shot Learning Models?
CoRR
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2022 J jnl
How robust are discriminatively trained zero-shot learning models?
Image Vis. Comput.
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2021 B conf
Adversarial Segmentation Loss For Sketch Colorization.
ICIP
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2021 J jnl
Adversarial Segmentation Loss for Sketch Colorization.
CoRR
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2021 A conf
Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos.
WACV
Yunus Can Bilge, Mehmet Kerim Yücel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis, Pinar Duygulu
2020 — conf
A Deep Dive into Adversarial Robustness in Zero-Shot Learning.
ECCV Workshops (1)
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2020 J jnl
A Deep Dive into Adversarial Robustness in Zero-Shot Learning.
CoRR
Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu
2020 J jnl
GANILLA: Generative Adversarial Networks for Image to Illustration Translation.
CoRR
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2020 J jnl
GANILLA: Generative adversarial networks for image to illustration translation.
Image Vis. Comput.
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2020 J jnl
I-ME: iterative model evolution for learning from weakly labeled images and videos.
Mach. Vis. Appl.
Ozge Yalcinkaya, Eren Golge, Pinar Duygulu
2020 J jnl
Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos.
CoRR
Yunus Can Bilge, Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis, Pinar Duygulu
2019 — conf
Learning Semantic Concepts from Weakly Labeled Data.
SIU
Samet Hiçsönmez, Iman Rezazadeh, Damla Unal, Didem Yaniktepe, Pinar Duygulu
2018 — conf
Who draw this? Caricaturist recognition using convolutional neural networks.
SIU
Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
2018 J jnl
Wildest Faces: Face Detection and Recognition in Violent Settings.
CoRR
Mehmet Kerim Yucel, Yunus Can Bilge, Oguzhan Oguz, Nazli Ikizler-Cinbis, Pinar Duygulu, Ramazan Gokberk Cinbis
2017 — conf
Action recognition with prototypes.
SIU
Ozge Yalcinkaya, Pinar Duygulu
2017 — conf
Could we create a training set for image captioning using automatic translation?
SIU
Nermin Samet, Samet Hicsonmez, Pinar Duygulu, Emre Akbas
2017 B conf
DRAW: Deep Networks for Recognizing Styles of Artists Who Illustrate Children's Books.
ICMR
Samet Hicsonmez, Nermin Samet, Fadime Sener, Pinar Duygulu
2017 J jnl
DRAW: Deep networks for Recognizing styles of Artists Who illustrate children's books.
CoRR
Samet Hicsonmez, Nermin Samet, Fadime Sener, Pinar Duygulu
2016 J jnl
Cross-document word matching for segmentation and retrieval of Ottoman divans.
Pattern Anal. Appl.
Pinar Duygulu, Damla Arifoglu, Mehmet Kalpakli
2016 — conf
Rock-paper-scissors game against computer.
SIU
Nihat Tekeli, Burçin Buket Ogul, Pinar Duygulu
2016 J jnl
Sentioscope: A Soccer Player Tracking System Using Model Field Particles.
IEEE Trans. Circuits Syst. Video Technol.
Sermetcan Baysal, Pinar Duygulu
2016 J jnl
Smart computing for large scale visual data sensing and processing.
Neurocomputing
Lei Zhang, Pinar Duygulu, Wangmeng Zuo, Shiguang Shan, Alexander G. Hauptmann
2016 — conf
Turkish sign language recognition application using Motion History Image.
SIU
Ozge Yalcinkaya, Anil Atvar, Pinar Duygulu
2015 J jnl
Classifying fonts and calligraphy styles using complex wavelet transform.
Signal Image Video Process.
Alican Bozkurt, Pinar Duygulu, A. Enis Çetin
2015 A conf
ConceptFusion: A Flexible Scene Classification Framework.
ECIR
Mustafa Ilker Sarac, Ahmet Iscen, Eren Golge, Pinar Duygulu
2015 — conf
FAME: Face Association through Model Evolution.
CVPR Workshops
Eren Golge, Pinar Duygulu
2015 J jnl
Matching Islamic patterns in Kufic images.
Pattern Anal. Appl.
Damla Arifoglu, Emre Sahin, Hande Adiguzel, Pinar Duygulu, Mehmet Kalpakli
2014 — conf
Bilkent-RETINA at Retrieving Diverse Social Images Task of MediaEval 2014.
MediaEval
Mustafa Ilker Sarac, Pinar Duygulu
2014 J jnl
Classifying Fonts and Calligraphy Styles Using Complex Wavelet Transform.
CoRR
Alican Bozkurt, Pinar Duygulu, A. Enis Çetin
2014 — conf
ConceptMap: Mining Noisy Web Data for Concept Learning.
ECCV (7)
Eren Golge, Pinar Duygulu
2014 J jnl
ConceptVision: A Flexible Scene Classification Framework.
CoRR
Ahmet Iscen, Eren Golge, Pinar Duygulu
2014 J jnl
FAME: Face Association through Model Evolution.
CoRR
Eren Golge, Pinar Duygulu
2014 — conf
Snippet Based Trajectory Statistics Histograms for Assistive Technologies.
ECCV Workshops (4)
Ahmet Iscen, Yijie Wang, Pinar Duygulu, Alexander G. Hauptmann
2014 — conf
What Is Usual in Unusual Videos? Trajectory Snippet Histograms for Discovering Unusualness.
CVPR Workshops
Ahmet Iscen, Anil Armagan, Pinar Duygulu
2014 J jnl
What is usual in unusual videos? Trajectory snippet histograms for discovering unusualness.
CoRR
Ahmet Iscen, Anil Armagan, Pinar Duygulu
2013 J jnl
A line based pose representation for human action recognition.
Signal Process. Image Commun.
Sermetcan Baysal, Pinar Duygulu
2013 — conf
Action recognition in a high-dimensional feature space.
SIU
Hande Adiguzel, Hayrettin Erdem, Hakan Ferhatosmanoglu, Pinar Duygulu
2013 — conf
Knives are picked before slices are cut: recognition through activity sequence analysis.
CEA@ACM Multimedia
Ahmet Iscen, Pinar Duygulu
2013 — conf
Labeling of Faces in Personal Photo Albums.
SIU
Emre Sener, Utku Can Yucel, Sercan Aksoy, Ibrahim Buyukgebiz, Burak Uzun, Pinar Duygulu
2013 — conf
MUCKE Participation at Retrieving Diverse Social Images Task of MediaEval 2013.
MediaEval
Anil Armagan, Adrian Popescu, Pinar Duygulu
2013 — conf
Recognizing human actions from noisy videos via multiple instance learning.
SIU
Fadime Sener, Nermin Samet, Pinar Duygulu, Nazli Ikizler-Cinbis
2013 J jnl
Rectifying Self Organizing Maps for Automatic Concept Learning from Web Images.
CoRR
Eren Golge, Pinar Duygulu
2013 — conf
Scene classification with random forests and object and color distributions.
SIU
Ahmet Iscen, Eren Golge, Anil Armagan, Pinar Duygulu
2012 B conf
A Hybrid for Line Segmentation in Handwritten Documents.
ICFHR
Hande Adiguzel, Emre Sahin, Pinar Duygulu
2012 — conf
A discussion on homography between stationary multi-camera systems and the soccer field model.
SIU
Sermetcan Baysal, Pinar Duygulu, Ceren Kayalar
2012 — conf
Affordance prediction of hand tools using interactive perception.
SIU
Yigit Çaliskan, Pinar Duygulu, Erol Sahin
2012 — conf
OTAP ottoman archives internet interface.
SIU
Emre Sahin, Hande Adiguzel, Pinar Duygulu, Mehmet Kalpakli
2011 J jnl
A line-based representation for matching words in historical manuscripts.
Pattern Recognit. Lett.
Ethem Fatih Can, Pinar Duygulu
2011 J jnl
A new pose-based representation for recognizing actions from multiple cameras.
Comput. Vis. Image Underst.
Selen Pehlivan, Pinar Duygulu
2011 — conf
Automatic Categorization of Ottoman Literary Texts by Poet and Time Period.
ISCIS
Ethem Fatih Can, Fazli Can, Pinar Duygulu, Mehmet Kalpakli
2011 J jnl
Multimedia translation for linking visual data to semantics in videos.
Mach. Vis. Appl.
Pinar Duygulu, Muhammet Bastan
2010 J jnl
Automatic tag expansion using visual similarity for photo sharing websites.
Multim. Tools Appl.
Sare Gul Sevil, Onur Kucuktunc, Pinar Duygulu, Fazli Can
2010 J jnl
Interesting faces: A graph-based approach for finding people in news.
Pattern Recognit.
Derya Ozkan, Pinar Duygulu
2010 B conf
Recognizing Human Actions Using Key Poses.
ICPR
Sermetcan Baysal, Mehmet Can Kurt, Pinar Duygulu
2010 B conf
Redif Extraction in Handwritten Ottoman Literary Texts.
ICPR
Ethem Fatih Can, Pinar Duygulu, Fazli Can, Mehmet Kalpakli
2009 — conf
3D human pose search using oriented cylinders.
ICCV Workshops
Selen Pehlivan, Pinar Duygulu
2009 J jnl
Histogram of oriented rectangles: A new pose descriptor for human action recognition.
Image Vis. Comput.
Nazli Ikizler, Pinar Duygulu
2009 — conf
Recognizing faces in news photographs on the web.
ISCIS
Hilal Zitouni, Muhammed Fatih Bulut, Pinar Duygulu
2008 — ch.
Combining Textual and Visual Information for Semantic Labeling of Images and Videos.
Machine Learning Techniques for Multimedia
Pinar Duygulu, Muhammet Bastan, Derya Ozkan
2008 B conf
Human action recognition with line and flow histograms.
ICPR
Nazli Ikizler, Ramazan Gokberk Cinbis, Pinar Duygulu
2008 B conf
Pose sentences: A new representation for action recognition using sequence of pose words.
ICPR
Kardelen Hatun, Pinar Duygulu
2008 B conf
Re-ranking of web image search results using a graph algorithm.
ICPR
Hilal Zitouni, Sare Gul Sevil, Derya Ozkan, Pinar Duygulu
2008 B conf
Recognizing actions from still images.
ICPR
Nazli Ikizler, Ramazan Gokberk Cinbis, Selen Pehlivan, Pinar Duygulu
2008 — conf
Tag Suggestr: Automatic Photo Tag Expansion Using Visual Information for Photo Sharing Websites.
SAMT
Onur Kucuktunc, Sare Gul Sevil, A. Burak Tosun, Hilal Zitouni, Pinar Duygulu, Fazli Can
2007 — conf
Bilkent University at TRECVID 2007.
TRECVID
Sercan Aksoy, Pinar Duygulu, Cem Aksoy, E. Aydin, D. Günaydin, K. Hadimh, L. Koç, Y. Olgun, Cihan Orhan, G. Yakin
2007 — conf
Human Action Recognition Using Distribution of Oriented Rectangular Patches.
Workshop on Human Motion
Nazli Ikizler, Pinar Duygulu
2007 — conf
Matching ottoman words: an image retrieval approach to historical document indexing.
CIVR
Esra Ataer, Pinar Duygulu
2007 — conf
Searching for repeated video sequences.
Multimedia Information Retrieval
Tolga Can, Pinar Duygulu
2006 — conf
A Graph Based Approach for Naming Faces in News Photos.
CVPR (2)
Derya Ozkan, Pinar Duygulu
2006 — conf
Finding People Frequently Appearing in News.
CIVR
Derya Ozkan, Pinar Duygulu
2006 — conf
Recognizing Objects and Scenes in News Videos.
CIVR
Muhammet Bastan, Pinar Duygulu
2006 — conf
Retrieval of Ottoman documents.
Multimedia Information Retrieval
Esra Ataer, Pinar Duygulu
2006 — conf
Translating Images to Words for Recognizing Objects in Large Image and Video Collections.
Toward Category-Level Object Recognition
Pinar Duygulu, Muhammet Bastan, David A. Forsyth
2005 — conf
Bilkent University at TRECVID 2005.
TRECVID
Sercan Aksoy, A. Avci, Erman Balcik, Ö. Cavus, Pinar Duygulu, Z. Karaman, P. Kavak, Cihan Kaynak, E. Küçükayvaz, Huseyin Cagdas Öcalan, P. Yildiz
2005 A* conf
Joint visual-text modeling for automatic retrieval of multimedia documents.
ACM Multimedia
Giridharan Iyengar, Pinar Duygulu, Shaolei Feng, Pavel Ircing, Sanjeev Khudanpur, Dietrich Klakow, M. R. Krause, Raghavan Manmatha, Harriet J. Nock, D. Petkova, Brock Pytlik, Paola Virga
2005 — conf
Person Search Made Easy.
CIVR
Nazli Ikizler, Pinar Duygulu
2005 — conf
Systematic Evaluation of Machine Translation Methods for Image and Video Annotation.
CIVR
Paola Virga, Pinar Duygulu
2004 A conf
Automatic image captioning.
ICME
Jia-Yu Pan, Hyung-Jeong Yang, Pinar Duygulu, Christos Faloutsos
2004 A* conf
Automatic multimedia cross-modal correlation discovery.
KDD
Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu
2004 — conf
Bilkent University at TRECVID 2004.
TRECVID
Sercan Aksoy, K. Bircan, S. Çiraci, Pinar Duygulu, E. Karaca, S. Kasirga, Tarkan Sevilmis, M. Sener
2004 A conf
Comparison and combination of two novel commercial detection methods.
ICME
Pinar Duygulu, Ming-yu Chen, Alexander G. Hauptmann
2004 — conf
GCap: Graph-Based Automatic Image Captioning.
MDDE
Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu
2004 — conf
GCap: Graph-based Automatic Image Captioning.
CVPR Workshops
Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu
2004 A* conf
Towards auto-documentary: tracking the evolution of news stories.
ACM Multimedia
Pinar Duygulu, Jia-Yu Pan, David A. Forsyth
2004 — conf
What's News, What's Not? Associating News Videos with Words.
CIVR
Pinar Duygulu, Alexander G. Hauptmann
2003 — conf
Comparison of Feature Sets Using Multimedia Translation.
ISCIS
Pinar Duygulu, Özge Can Özcanli, Norman Papernick
2003 — conf
Informedia at TRECVID 2003 : Analyzing and Searching Broadcast News Video.
TRECVID
Alexander G. Hauptmann, Robert V. Baron, Ming-yu Chen, Michael G. Christel, Pinar Duygulu, C. Huang, Rong Jin, Wei-Hao Lin, Tobun D. Ng, Neema Moraveji, Norman Papernick, Cees G. M. Snoek, G. Tzanetakis, Jie Yang, Rong Yan, Howard D. Wactlar
2003 J jnl
Matching Words and Pictures.
J. Mach. Learn. Res.
Kobus Barnard, Pinar Duygulu, David A. Forsyth, Nando de Freitas, David M. Blei, Michael I. Jordan
2003 J jnl
Object-based image labeling through learning by example and multi-level segmentation.
Pattern Recognit.
Yaowu Xu, Pinar Duygulu, Eli Saber, A. Murat Tekalp, Fatos T. Yarman-Vural
2003 — conf
The Effects of Segmentation and Feature Choice in a Translation Model of Object Recognition.
CVPR (2)
Kobus Barnard, Pinar Duygulu, Raghavendra Guru, Prasad Gabbur, David A. Forsyth
2002 J jnl
A hierarchical representation of form documents for identification and retrieval.
Int. J. Document Anal. Recognit.
Pinar Duygulu, Volkan Atalay
2002 — conf
Modeling the statistics of image features and associated text.
Document Recognition and Retrieval
Kobus Barnard, Pinar Duygulu, David A. Forsyth
2002 — conf
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary.
ECCV (4)
Pinar Duygulu, Kobus Barnard, João F. G. de Freitas, David A. Forsyth
2001 — conf
Clustering Art.
CVPR (2)
Kobus Barnard, Pinar Duygulu, David A. Forsyth
2001 — conf
Multilevel image segmentation and object representation for content-based image retrieval.
Storage and Retrieval for Media Databases
Pinar Duygulu, Fatos T. Yarman-Vural
2000 — conf
Hierarchical representation of form documents for identification and retrieval.
Document Recognition and Retrieval
Pinar Duygulu, Volkan Atalay
2000 Misc conf
Object based image retrieval based on multi-level segmentation.
ICASSP
Yaowu Xu, Pinar Duygulu, Eli Saber, A. Murat Tekalp, Fatos T. Yarman-Vural
1998 B conf
A heuristic algorithm for hierarchical representation of form documents.
ICPR
Pinar Duygulu, Volkan Atalay, Ebru Dincel