Ethem F. Can

Predicting retweet count using visual cues

Social media platforms allow rapid information diffusion, and serve as a source of information to many of the users. Particularly, in Twitter information provided by tweets diffuses over the users through retweets. Hence, being able to predict the retweet count of a given tweet is important for understanding and controlling information diffusion on Twitter. Since the length of a tweet is limited to 140 characters, extracting relevant features to predict the retweet count is a challenging task. However, visual features of images linked in tweets may provide predictive features. In this study, we focus on predicting the expected retweet count of a tweet by using visual cues of an image linked in that tweet in addition to content and structure-based features.

A Hybrid Model for Automatic Image Annotation

In this work, we present a hybrid model (SVM-DMBRM) combining a generative and a discriminative model for the image annotation task. A support vector machine (SVM) is used as the discriminative model and a Discrete Multiple Bernoulli Relevance Model (DMBRM) is used as the generative model. The idea of combining both the models is to take advantage of the distinct capabilities of each model. The SVM tries to address the problem of poor annotation (images are not annotated with all relevant keywords), while the DMBRM model tries to address the problem of data imbalance (large variations in number of positive samples). Since DMBRM does not work well with high-dimensional data, a Latent Dirichlet Allocation (LDA) model is used to reduce the dimensionality of vector quantized features before using it. The hybrid models results are comparable to or better than the state-of-the-art results on three standard datasets: Corel-5k, ESP-Game and IAPRTC-12.

A line-based representation for matching words in historical manuscripts

In this study, we propose a new method for retrieving and recognizing words in historical documents. We represent word images with a set of line segments. Then we provide a criterion for word matching based on matching the lines. We carry out experiments on a benchmark dataset consisting of manuscripts by George Washington, as well as on Ottoman manuscripts.

Modeling Concept Dependencies for Event Detection

Event detection is a recent and challenging task. The aim is to retrieve the relevant videos given an event description. A set of training examples associated with the events are generally provided as well, since retrieving relevant videos from textual queries solely is not feasible. Early attempts of event detection are based on low-level features. High level features such as concepts for event detection have been introduced as an alternative to low-level features since high-level features provide semantically richer information. In this work, we focus on object-based concepts and exploit their dependencies using a Markov Random Field (MRF) based model for event detection. This enables us to model likelihood of concepts, either pairwise or individually, present in the videos. Here, we propose a method incorporating the strengths of concepts and MRF based model for event detection task. We evaluate our models on an Multimedia Event Detection (MED) dataset from NISTs 2011 TRECVID Multimedia, which consists of approximately 45,000 unconstrained videos. This type of work is beneficial from several respects. First, we focus on the task of concept-based event detection using a very large number of unconstrained Youtube videos. Second, we introduce the application of MRFs for the event detection purpose, which can further be enhanced incorporating other features or temporal information. At last but not means least, we exploit the occurrence and co-occurrence of object based concepts for event detection that enables us to reveal interactions of such concepts in the video level. Experimental results show that revealing these interactions provide promising event detection results.

Incorporating query-specific feedback into learning-to-rank models

Relevance feedback has been shown to improve retrieval for a broad range of retrieval models. It is the most common way of adapting a retrieval model for a specific query. In this work, we expand this common way by focusing on an approach that enables us to do query-specific modification of a retrieval model for learning-to-rank problems. Our approach is based on using feedback documents in two ways: 1) to improve the retrieval model directly and 2) to identify a subset of training queries that are more predictive than others. Experiments with the Gov2 collection show that this approach can obtain statistically significant improvements over two baselines; learning-to-rank (SVM-rank) with no feedback and learning-to-rank with standard relevance feedback.

Formulating Action Recognition as a Ranking Problem

Action recognition is one of the major challenges of computer vision. Several approaches have been proposed using different descriptors and multi-class models. In this paper, we focus on binary ranking models for the action recognition problem and address the action recognition as a ranking problem. A binary ranking model is trained for each action and used to recognize the test videos for that action. Binary ranking models are constructed using dense SIFT (DSIFT) descriptors and histogram of oriented gradients / histogram of optical flows (HOG/HOF) descriptors. We show that using ranking models, it is possible to obtain higher recognition accuracies from a baseline that is based on multi-class models on the very recent and challenging benchmark datasets, Human Motion Database (HMDB) and The Action Similarity Labeling (ASLAN).

Automatic Categorization of Ottoman Literary Texts by Poet and Time Period

Millions of manuscripts and printed texts are available in the Ottoman language. The automatic categorization of Ottoman texts would make these documents much more accessible in various applications ranging from historical investigations to literary analyses. In this work, we use transcribed version of Ottoman literary texts in the Latin alphabet and show that it is possible to develop effective Automatic Text Categorization techniques that can be applied to the Ottoman language. For this purpose, we use two fundamentally different machine learning methods: Naive Bayes and Support Vector Machines, and employ four style markers: most frequent words, token lengths, two-word collocations, and type lengths. In the experiments, we use the collected works (divans) of ten different poets: two poets from five different hundred-year periods ranging from the 15th to 19th century. The experimental results show that it is possible to obtain highly accurate classifications in terms of poet and time period. By using statistical analysis we are able to recommend which style marker and machine learning method are to be used in future studies.

A framework for manipulating and searching multiple retrieval types

Conventional retrieval systems view documents as a unit and look at different retrieval types within a document. We introduce Proteus, a frame-work for seamlessly navigating books as dynamic collections which are defined on the fly. Proteus allows us to search various retrieval types. Navigable types include pages, books, named persons, locations, and pictures in a collection of books taken from the Internet Archive. The demonstration shows the value of multi-type browsing in dynamic collections to peruse new data.

Redif Extraction in Handwritten Ottoman Literary Texts

Repeated patterns, rhymes and redifs, are among the fundamental building blocks of Ottoman Divan poetry. They provide integrity of a poem by connecting its parts and bring a melody to its voice. In Ottoman literature, poets wrote their works by making use of the rhymes and redifs of previous poems according to the nazire (creative imitation) tradition either to prove their expertise or to show respect towards old masters. Automatic recognition of redifs would provide important data mining opportunities in literary analyses of Ottoman poetry where the majority of it is in handwritten form. In this study, we propose a matching criterion and method, Red if Extraction using Contour Segments (RECS) using the proposed matching criterion, that detects redifs in handwritten Ottoman literary texts using only visual analysis. Our method provides a success rate of 0.682 in a test collection of 100 poems.

Translation Relationship Quantification: A Cluster-Based Approach and its Application to Shakespeare’s Sonnets

We introduce a method for quantifying translation relation-ship between source and target texts.In this method, we partition source and target texts into corresponding blocks and cluster them separately using word phrases extracted by a suffx tree approach. We quantify the translation relationship by examining the similarity between source and target clustering structures. In this comparison we aim to observe that their similarity is meaningful, i.e., it is significantly different from random. The method is based on the hypothesis that similarities and dis-similarities among the source blocks will not be lost in translation and reappear among target blocks. For testing we use Shakespeares sonnets and its translation in Turkish. The results show that our method suc-cessfully quantifies translation relationships.