Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
263 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Metadata only Multi-scale deformable alignment and content-adaptive inference for flexible-rate bi-directional video compression(IEEE Computer Society, 2023) Department of Electrical and Electronics Engineering; Yılmaz, Mustafa Akın; UlaÅ, ĆkkeÅ UÄur; Tekalp, Ahmet Murat; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of EngineeringThe lack of ability to adapt the motion compensation model to video content is an important limitation of current end-to-end learned video compression models. This paper advances the state-of-the-art by proposing an adaptive motion-compensation model for end-to-end rate-distortion optimized hierarchical bi-directional video compression. In particular, we propose two novelties: i) a multi-scale deformable alignment scheme at the feature level combined with multi-scale conditional coding, ii) motion-content adaptive inference. In addition, we employ a gain unit, which enables a single model to operate at multiple rate-distortion operating points. We also exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding1.Publication Metadata only Artificial intelligence and medical decision-making: Wind of change for medical malpractice liability and insurance?(Edward Elgar Publishing Ltd., 2023) N/A; Ćelebi, ĆzgĆ¼n; BuÄra, AyÅegĆ¼l; Law SchoolIn the field of health care, computing systems' extensive capabilities and ongoing improvements as to their autonomy raise the question of whether the patient's expectations from healthcare professionals and the corresponding rules regarding assessment of medical liability will and shall remain the same. This chapter attempts to analyse the impact of cognitive computing systems - regarded neither as a human-dependent medical device nor as an autonomous and trustworthy agent - upon medical malpractice and the development of an adequate insurance system. In particular, the chapter deals with the difficulties relating to the detection of the root cause of the misdiagnosis, the impact of the use of cognitive computer systems upon the standard of care expected from health practitioners, the interactions of the systems with the requirements regarding the patient's informed consent and the role of medical liability insurance upon patient safety and compensation. Ā© Edward Elgar Publishing 2023.Publication Metadata only Snoopie: a multi-GPU communication profiler and visualizer(Assoc Computing Machinery, 2024) Department of Computer Engineering; Issa, Mohammad Kefah Taha; Sasongko, Muhammad Aditya; Turimbetov, Ä°lyas; Baydamirli, Javid; SaÄbili, DoÄan; Erten, Didem Unat; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringWith data movement becoming one of the most expensive bottlenecks in computing, the need for profiling tools to analyze communication becomes crucial for effectively scaling multi-GPU applications. While existing profiling tools including first-party software by GPU vendors are robust and excel at capturing compute operations within a single GPU, support for monitoring GPU-GPU data transfers and calls issued by communication libraries is currently inadequate. To fill these gaps, we introduce Snoopie, an instrumentation-based multi-GPU communication profiling tool built on NVBit, capable of tracking peer-to-peer transfers and GPU-centric communication library calls. To increase programmer productivity, Snoopie can attribute data movement to the source code line and the data objects involved. It comes with multiple visualization modes at varying granularities, from a coarse view of the data movement in the system as a whole to specific instructions and addresses. Our case studies demonstrate Snoopie's effectiveness in monitoring data movement, locating performance bugs in applications, and understanding concrete data transfers abstracted beneath communication libraries. The tool is publicly available at https://github.com/ParCoreLab/snoopie.Publication Metadata only Learning markerless robot-depth camera calibration and end-effector pose estimation(Ml Research Press, 2023) Department of Computer Engineering; Sefercik, BuÄra Can; AkgĆ¼n, BarıÅ; Department of Computer Engineering; KoƧ Ćniversitesi Ä°Å Bankası Yapay Zeka Uygulama ve AraÅtırma Merkezi (KUIS AI)/ KoƧ University Ä°Å Bank Artificial Intelligence Center (KUIS AI); College of Engineering; Graduate School of Sciences and EngineeringTraditional approaches to extrinsic calibration use fiducial markers and learning-based approaches rely heavily on simulation data. In this work, we present a learning-based markerless extrinsic calibration system that uses a depth camera and does not rely on simulation data. We learn models for end-effector (EE) segmentation, single-frame rotation prediction and keypoint detection, from automatically generated real-world data. We use a transformation trick to get EE pose estimates from rotation predictions and a matching algorithm to get EE pose estimates from keypoint predictions. We further utilize the iterative closest point algorithm, multiple-frames, filtering and outlier detection to increase calibration robustness. Our evaluations with training data from multiple camera poses and test data from previously unseen poses give sub-centimeter and sub-deciradian average calibration and pose estimation errors. We also show that a carefully selected single training pose gives comparable results. Ā© 2023 Proceedings of Machine Learning Research. All rights reserved.Publication Metadata only Multimodal fusion for effective recommendations on a user-anonymous price comparison platform(Institute of Electrical and Electronics Engineers Inc., 2024) Kantarcı, Merve GĆ¼l; Department of Industrial Engineering; Gƶnen, Mehmet; Department of Industrial Engineering; College of EngineeringThis study proposes a novel recommendation framework designed for a digital price comparison platform. The challenges arise from the absence of user login and gold labels in item variations, which make effective recommendations tricky. The proposed framework integrates three distinct modalities: product titles using a multilingual BERT model, product images through the CLIP model, and click data via a novel Word2Vec model named Prod2Vec. Three fusion methods were tested to obtain a single unified representation for a given product: early, intermediate, and late fusion. Offline evaluations showcased a significant performance boost when leveraging all three modalities and employing intermediate fusion. The proposed framework achieved an impressive 92% Adjusted Rand Index clustering score at the category level. Fusion with two modalities also proved to be competitively effective, yielding scores between 87% and 88%. The framework was shown to be scalable by maintaining good performance even when we increased the number of categories up to 50. For online evaluations, we selected three representative categories and deployed the best-selected fusion method on the platform through A/B testing against a click-text encoding baseline. Our framework resulted in a significant improvement by increasing the Click-Through Rate from 1.43% to 3.17% across all categories. These findings underscore the efficacy of the proposed framework in enhancing user engagement and interaction with the platform. Ā© 2024 IEEE.Publication Metadata only Graph domain adaptation with localized graph signal representations(Elsevier GMBH, 2024) Pilavci, Yusuf Yigit; Guneyi, Eylem Tugce; Vural, Elif; Cengiz, Cemil; ; Graduate School of Sciences and Engineering;In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the two graphs. Our assumption about the source and the target domains is that the local behavior of the label function, such as its spread and speed of variation on the graph, bears resemblance between the two graphs. We estimate the unknown target labels by solving an optimization problem where the label information is transferred from the source graph to the target graph based on the prior that the projections of the label functions onto localized graph bases be similar between the source and the target graphs. In order to efficiently capture the local variation of the label functions on the graphs, spectral graph wavelets are used as the graph bases. Experimentation on various data sets shows that the proposed method yields quite satisfactory classification accuracy compared to reference domain adaptation methods.Publication Metadata only Geolocation risk scores for credit scoring models(Springer Science and Business Media Deutschland Gmbh, 2024) Ćnal, Erdem; Aydın, UÄur; KoraÅ, Murat; Department of Computer Engineering;Department of Industrial Engineering; AkgĆ¼n, BarıÅ; Gƶnen, Mehmet; College of EngineeringCustomer location is considered as one of the most informative demographic data for predictive modeling. It has been widely used in various sectors including finance. Commercial banks use this information in the evaluation of their credit scoring systems. Generally, customer city and district are used as demographic features. Even if these features are quite informative, they are not fully capable of capturing socio-economical heterogeneity of customers within cities or districts. In this study, we introduced a micro-region approach alternative to this district or city approach. We created features based on characteristics of micro-regions and developed predictive credit risk models. Since models only used micro-region specific data, we were able to apply it to all possible locations and calculate risk scores of each micro-region. We showed their positive contribution to our regular credit risk models.Publication Metadata only Topics in assistive technologies and inclusion for older people: introduction to the special thematic session(Springer Science and Business Media Deutschland GmbH, 2024) Hallewell Haslwanter, Jean D.; Panek, Paul; Department of Media and Visual Arts; SubaÅı, Ćzge; Department of Media and Visual Arts; College of Social Sciences and HumanitiesThis special session aims to carry forward discussions on Active Assisted Living (AAL), focusing on both new technologies for older adults and the various social aspects of their development. The papers cover different aspects of the special theme. Some detail the creation or introduction of tailored technologies to meet the specific needs of seniors, including monitor technologies and an interactive system. Others explore methods like co-design and new heuristics to ensure these systems truly address real-world needs. While yet others focus on topics of concern, such as ageist biases of computer science graduates and designing living spaces to better allow existing technologies to be integrated. Overall, the papers recognize the unique challenges of developing systems for older adults while acknowledging the diversity within this age group.Publication Metadata only HyperE2VID: improving event-based video reconstruction via hypernetworks(IEEE-Inst Electrical Electronics Engineers Inc, 2024) Ercan, Burak; Eker, Onur; SaÄlam, Canberk; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Department of Computer Engineering; KoƧ Ćniversitesi Ä°Å Bankası Enfeksiyon Hastalıkları Uygulama ve AraÅtırma Merkezi (EHAM) / KoƧ University Ä°Åbank Center for Infectious Diseases (KU-IS CID); College of Engineering;Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events remains challenging due to the highly sparse and varying nature of event data. To address this, in this study, we propose HyperE2VID, a dynamic neural network architecture for event-based video reconstruction. Our approach uses hypernetworks to generate per-pixel adaptive filters guided by a context fusion module that combines information from event voxel grids and previously reconstructed intensity images. We also employ a curriculum learning strategy to train the network more robustly. Our comprehensive experimental evaluations across various benchmark datasets reveal that HyperE2VID not only surpasses current state-of-the-art methods in terms of reconstruction quality but also achieves this with fewer parameters, reduced computational requirements, and accelerated inference times.Publication Metadata only AffectON: Incorporating affect into dialog generation(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Bucinca, Zana; Department of Computer Engineering; Yemez, YĆ¼cel; Erzin, Engin; Sezgin, Tevfik Metin; Department of Computer Engineering; KoƧ Ćniversitesi Ä°Å Bankası Yapay Zeka Uygulama ve AraÅtırma Merkezi (KUIS AI)/ KoƧ University Ä°Å Bank Artificial Intelligence Center (KUIS AI); College of EngineeringDue to its expressivity, natural language is paramount for explicit and implicit affective state communication among humans. The same linguistic inquiry (e.g., How are you?) might induce responses with different affects depending on the affective state of the conversational partner(s) and the context of the conversation. Yet, most dialog systems do not consider affect as constitutive aspect of response generation. In this article, we introduce AffectON, an approach for generating affective responses during inference. For generating language in a targeted affect, our approach leverages a probabilistic language model and an affective space. AffectON is language model agnostic, since it can work with probabilities generated by any language model (e.g., sequence-to-sequence models, neural language models, n-grams). Hence, it can be employed for both affective dialog and affective language generation. We experimented with affective dialog generation and evaluated the generated text objectively and subjectively. For the subjective part of the evaluation, we designed a custom user interface for rating and provided recommendations for the design of such interfaces. The results, both subjective and objective demonstrate that our approach is successful in pulling the generated language toward the targeted affect, with little sacrifice in syntactic coherence.