Researcher:
Sezgin, Tevfik Metin

Profile Picture
ORCID

Job Title

Faculty Member

First Name

Tevfik Metin

Last Name

Sezgin

Name

Name Variants

Sezgin, Tevfik Metin

Email Address

Birth Date

Filters

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.c67f56ef-f09e-4da3-b252-be71881f9a9f

Search Results

Now showing 1 - 10 of 82
  • Placeholder
    PublicationMetadata only
    Audio-facial laughter detection in naturalistic dyadic conversations
    (Ieee-Inst Electrical Electronics Engineers Inc, 2017) N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Yemez, Yücel; Sezgin, Tevfik Metin; Erzin, Engin; PhD Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 107907; 18632; 34503
    We address the problem of continuous laughter detection over audio-facial input streams obtained from naturalistic dyadic conversations. We first present meticulous annotation of laughters, cross-talks and environmental noise in an audio-facial database with explicit 3D facial mocap data. Using this annotated database, we rigorously investigate the utility of facial information, head movement and audio features for laughter detection. We identify a set of discriminative features using mutual information-based criteria, and show how they can be used with classifiers based on support vector machines (SVMs) and time delay neural networks (TDNNs). Informed by the analysis of the individual modalities, we propose a multimodal fusion setup for laughter detection using different classifier-feature combinations. We also effectively incorporate bagging into our classification pipeline to address the class imbalance problem caused by the scarcity of positive laughter instances. Our results indicate that a combination of TDNNs and SVMs lead to superior detection performance, and bagging effectively addresses data imbalance. Our experiments show that our multimodal approach supported by bagging compares favorably to the state of the art in presence of detrimental factors such as cross-talk, environmental noise, and data imbalance.
  • Placeholder
    PublicationMetadata only
    Affect burst detection using multi-modal cues
    (IEEE, 2015) Department of Computer Engineering; Department of Computer Engineering; N/A; Department of Computer Engineering; N/A; Sezgin, Tevfik Metin; Yemez, Yücel; Türker, Bekir Berker; Erzin, Engin; Marzban, Shabbir; Faculty Member; Faculty Member; PhD Student; Faculty Member; Master Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; Graduate School of Sciences and Engineering; 18632; 107907; N/A; 34503; N/A
    Recently, affect bursts have gained significant importance in the field of emotion recognition since they can serve as prior in recognising underlying affect bursts. In this paper we propose a data driven approach for detecting affect bursts using multimodal streams of input such as audio and facial landmark points. The proposed Gaussian Mixture Model based method learns each modality independently followed by combining the probabilistic outputs to form a decision. This gives us an edge over feature fusion based methods as it allows us to handle events when one of the modalities is too noisy or not available. We demonstrate robustness of the proposed approach on 'Interactive emotional dyadic motion capture database' (IEMOCAP) which contains realistic and natural dyadic conversations. This database is annotated by three annotators to segment and label affect bursts to be used for training and testing purposes. We also present performance comparison between SVM based methods and GMM based methods for the same configuration of experiments.
  • Placeholder
    PublicationMetadata only
    Role allocation through haptics in physical human-robot interaction
    (Institute of Electrical and Electronics Engineers (IEEE), 2013) N/A; N/A; Department of Computer Engineering; Department of Mechanical Engineering; Küçükyılmaz, Ayşe; Sezgin, Tevfik Metin; Başdoğan, Çağatay; PhD Student; Faculty Member; Faculty Member; Department of Computer Engineering; Department of Mechanical Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 18632; 125489
    This paper presents a summary of our efforts to enable dynamic role allocation between humans and robots in physical collaboration tasks. A major goal in physical human-robot interaction research is to develop tacit and natural communication between partners. In previous work, we suggested that the communication between a human and a robot would benefit from a decision making process in which the robot can dynamically adjust its control level during the task based on the intentions of the human. In order to do this, we define leader and follower roles for the partners, and using a role exchange mechanism, we enable the partners to negotiate solely through force information to exchange roles. We show that when compared to an “equal control” condition, the role exchange mechanism improves task performance and the joint efficiency of the partners.
  • Placeholder
    PublicationMetadata only
    Sketch recognition with few examples
    (Pergamon-Elsevier Science Ltd, 2017) N/A; Department of Computer Engineering; Yeşilbek, Kemal Tuğrul; Sezgin, Tevfik Metin; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 18632
    Sketch recognition is the task of converting hand-drawn digital ink into symbolic computer representations. Since the early days of sketch recognition, the bulk of the work in the field focused on building accurate recognition algorithms for specific domains, and well defined data sets. Recognition methods explored so far have been developed and evaluated using standard machine learning pipelines and have consequently been built over many simplifying assumptions. For example, existing frameworks assume the presence of a fixed set of symbol classes, and the availability of plenty of annotated examples. However, in practice, these assumptions do not hold. In reality, the designer of a sketch recognition system starts with no labeled data at all, and faces the burden of data annotation. In this work, we propose to alleviate the burden of annotation by building systems that can learn from very few labeled examples, and large amounts of unlabeled data. Our systems perform self-learning by automatically extending a very small set of labeled examples with new examples extracted from unlabeled sketches. The end result is a sufficiently large set of labeled training data, which can subsequently be used to train classifiers. We present four self-learning methods with varying levels of implementation difficulty and runtime complexities. One of these methods leverages contextual co-occurrence patterns to build verifiably more diverse set of training instances. Rigorous experiments with large sets of data demonstrate that this novel approach based on exploiting contextual information leads to significant leaps in recognition performance. As a side contribution, we also demonstrate the utility of bagging for sketch recognition in imbalanced data sets with few positive examples and many outliers.
  • Placeholder
    PublicationMetadata only
    Visualization literacy at elementary school
    (Assoc Computing Machinery, 2017) Alper, Başak; Riche, Nathalie Henry; Chevalier, Fanny; Boy, Jeremy; Department of Computer Engineering; Sezgin, Tevfik Metin; Faculty Member; Department of Computer Engineering; College of Engineering; 18632
    This work advances our understanding of children's visualization literacy, and aims to improve it with a novel approach for teaching visualization at elementary schools. We first contribute an analysis of data graphics and activities employed in grade K to 4 educational materials, and the results of a survey conducted with 16 elementary school teachers. We find that visualization education could benefit from integrating pedagogical strategies for teaching abstract concepts with established interactive visualization techniques. Building on these insights, we develop and study design principles for novel interactive teaching material aimed at increasing children's visualization literacy. We specifically contribute Cest la Vis, an online platform for teachers and students to respectively teach and learn about pictographs and bar charts, and report on our initial observations of its use in grades K and 2.
  • Placeholder
    PublicationMetadata only
    Special section on the 2011 joint symposium on computational aesthetics (CAe), non-photorealistic animation and rendering (NPAR), and sketch-based interfaces and modeling (SBIM)
    (Pergamon-Elsevier Science Ltd, 2012) Isenberg, Tobias; Asente, Paul; Collomosse, John; Department of Computer Engineering; Sezgin, Tevfik Metin; Faculty Member; Department of Computer Engineering; College of Engineering; 18632
    N/A
  • Placeholder
    PublicationMetadata only
    Generation of 3D human models and animations using simple sketches
    (Canadian Information Processing Society, 2020) Sahillioğlu, Y.; N/A; Department of Computer Engineering; Akman, Alican; Sezgin, Tevfik Metin; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 18632
    Generating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to the existing human modeling techniques, our method requires neither a statistical body shape model nor a rigged 3D character model. We exploit Variational Autoencoders to develop a novel framework capable of transitioning from a simple 2D stick figure sketch, to a corresponding 3D human model. Our network learns the mapping between the input sketch and the output 3D model. Furthermore, our model learns the embedding space around these models. We demonstrate that our network can generate not only 3D models, but also 3D animations through interpolation and extrapolation in the learned embedding space. Extensive experiments show that our model learns to generate reasonable 3D models and animations. © 2020 Canadian Information Processing Society. All rights reserved.
  • Placeholder
    PublicationMetadata only
    Gaze-based predictive user interfaces: visualizing user intentions in the presence of uncertainty
    (Academic Press Ltd- Elsevier Science Ltd, 2018) N/A; N/A; Department of Computer Engineering; Karaman, Çağla Çiğ; Sezgin, Tevfik Metin; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 18632
    Human eyes exhibit different characteristic patterns during different virtual interaction tasks such as moving a window, scrolling a piece of text, or maximizing an image. Human-computer, studies literature contains examples of intelligent systems that can predict user's task-related intentions and goals based on eye gaze behavior. However, these systems are generally evaluated in terms of prediction accuracy, and on previously collected offline interaction data. Little attention has been paid to creating real-time interactive systems using eye gaze and evaluating them in online use. We have five main contributions that address this gap from a variety of aspects. First, we present the first line of work that uses real-time feedback generated by a gaze-based probabilistic task prediction model to build an adaptive real-time visualization system: Our system is able to dynamically provide adaptive interventions that are informed by real-time user behavior data. Second, we propose two novel adaptive visualization approaches that take into account the presence of uncertainty in the outputs of prediction models. Third, we offer a personalization method to suggest which approach will be more suitable for each user in terms of system performance (measured in terms of prediction accuracy). Personalization boosts system performance and provides users with the more optimal visualization approach (measured in terms of usability and perceived task load). Fourth, by means of a thorough usability study, we quantify the effects of the proposed visualization approaches and prediction errors on natural user behavior and the performance of the underlying prediction systems. Finally, this paper also demonstrates that our previously-published gaze-based task prediction system, which was assessed as successful in an offline test scenario, can also be successfully utilized in realistic online usage scenarios.
  • Placeholder
    PublicationMetadata only
    Sketch recognition in interspersed drawings using time-based graphical models
    (Pergamon-Elsevier Science Ltd, 2008) Department of Computer Engineering; Sezgin, Tevfik Metin; Faculty Member; Department of Computer Engineering; College of Engineering; 18632
    Sketching is a natural mode of interaction used in a variety of settings. With the increasing availability of pen-based computers, sketch recognition has gained attention as an enabling technology for natural pen-based interfaces. Previous work in sketch recognition has shown that in certain domains the stroke orderings used when drawing objects contain temporal patterns that can aid recognition. So far, systems that use temporal information for recognition have assumed that objects are drawn one at a time. This paper shows how this assumption can be relaxed to permit temporal interspersing of strokes from different objects. We describe a statistical framework based on dynamic Bayesian networks that explicitly models the fact that objects can be drawn interspersed. We present recognition results for hand-drawn electronic circuit diagrams, showing that handling interspersed drawing provides a significant increase in accuracy.
  • Placeholder
    PublicationMetadata only
    Data-driven vibrotactile rendering of digital buttons on touchscreens
    (Academic Press Ltd- Elsevier Science Ltd, 2020) N/A; N/A; Department of Computer Engineering; Department of Mechanical Engineering; Sadia, Büshra; Emgin, Senem Ezgi; Sezgin, Tevfik Metin; Başdoğan, Çağatay; PhD Student; PhD Student; Faculty Member; Faculty Member; Department of Computer Engineering; Department of Mechanical Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; 18632; 125489
    Interaction with physical buttons is an essential part of our daily routine. We use buttons daily to turn lights on, to call an elevator, to ring a doorbell, or even to turn on our mobile devices. Buttons have distinct response characteristics and are easily activated by touch. However, there is limited tactile feedback available for their digital counterparts displayed on touchscreens. Although mobile phones incorporate low-cost vibration motors to enhance touch-based interactions, it is not possible to generate complex tactile effects on touchscreens. It is also difficult to relate the limited vibrotactile feedback generated by these motors to different types of physical buttons. In this study, we focus on creating vibrotactile feedback on a touchscreen that simulates the feeling of physical buttons using piezo actuators attached to it. We first recorded and analyzed the force, acceleration, and voltage data from twelve participants interacting with three different physical buttons: latch, toggle, and push buttons. Then, a button-specific vibrotactile stimulus was generated for each button based on the recorded data. Finally, we conducted a three-alternative forced choice (3AFC) experiment with twenty participants to explore whether the resultant stimulus is distinct and realistic. In our experiment, participants were able to match the three digital buttons with their physical counterparts with a success rate of 83%. In addition, we harvested seven adjective pairs from the participants expressing their perceptual feeling of pressing the physical buttons. All twenty participants rated the degree of their subjective feelings associated with each adjective for all the physical and digital buttons investigated in this study. Our statistical analysis showed that there exist at least three adjective pairs for which participants have rated two out of three digital buttons similar to their physical counterparts.