Duygulu, P.[Pinar]
* 1998: Heuristic Algorithm for Hierarchical Representation of Form Documents, A
* 2001: Clustering Art
* 2002: hierarchical representation of form documents for identification and retrieval, A
* 2002: Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
* 2003: effects of segmentation and feature choice in a translation model of object recognition, The
* 2003: Object-based image labeling through learning by example and multi-level segmentation
* 2004: GCap: Graph-based Automatic Image Captioning
* 2004: What's News, What's Not? Associating News Videos with Words
* 2005: Person Search Made Easy
* 2005: Systematic Evaluation of Machine Translation Methods for Image and Video Annotation
* 2006: Finding People Frequently Appearing in News
* 2006: Graph Based Approach for Naming Faces in News Photos, A
* 2006: Recognizing Objects and Scenes in News Videos
* 2006: Retrieval of Ottoman documents
* 2006: Translating Images to Words for Recognizing Objects in Large Image and Video Collections
* 2007: Human Action Recognition Using Distribution of Oriented Rectangular Patches
* 2007: Matching Ottoman Words: An image retrieval approach to historical document indexing
* 2008: Human action recognition with line and flow histograms
* 2008: Pose sentences: A new representation for action recognition using sequence of pose words
* 2008: Re-ranking of web image search results using a graph algorithm
* 2008: Recognizing actions from still images
* 2009: 3D human pose search using oriented cylinders
* 2009: Histogram of oriented rectangles: A new pose descriptor for human action recognition
* 2010: Interesting faces: A graph-based approach for finding people in news
* 2010: Recognizing Human Actions Using Key Poses
* 2010: Redif Extraction in Handwritten Ottoman Literary Texts
* 2011: line-based representation for matching words in historical manuscripts, A
* 2011: Multimedia translation for linking visual data to semantics in videos
* 2011: new pose-based representation for recognizing actions from multiple cameras, A
* 2012: Hybrid for Line Segmentation in Handwritten Documents, A
* 2013: line based pose representation for human action recognition, A
* 2014: ConceptMap: Mining Noisy Web Data for Concept Learning
* 2014: Snippet Based Trajectory Statistics Histograms for Assistive Technologies
* 2014: What Is Usual in Unusual Videos? Trajectory Snippet Histograms for Discovering Unusualness
* 2015: Classifying fonts and calligraphy styles using complex wavelet transform
* 2015: FAME: Face Association through Model Evolution
* 2016: Sentioscope: A Soccer Player Tracking System Using Model Field Particles
* 2020: GANILLA: Generative adversarial networks for image to illustration translation
* 2020: I-ME: iterative model evolution for learning from weakly labeled images and videos
* 2021: Adversarial Segmentation Loss for Sketch Colorization
* 2021: Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos
* 2022: How robust are discriminatively trained zero-shot learning models?
* 2023: HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness
Includes: Duygulu, P.[Pinar] Duygulu, P. Duygulu, P.[Pınar]
43 for Duygulu, P.