Yayınlar & Eserler

Makaleler 43
Tümü (43)
SCI-E, SSCI, AHCI (40)
SCI-E, SSCI, AHCI, ESCI (42)
ESCI (2)
Scopus (42)
Diğer Yayınlar (1)
Hakemli Bilimsel Toplantılarda Yayımlanmış Bildiriler 84

2. Bucketed Ranking-Based Losses for Efficient Training of Object Detectors

18th European Conference on Computer Vision (ECCV), Milan, İtalya, 29 Eylül - 04 Ekim 2024, cilt.15117, ss.93-109, (Tam Metin Bildiri) Sürdürülebilir Kalkınma identifier identifier

3. Machine Learning Fairness for Depression Detection Using EEG Data

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025, Texas, Amerika Birleşik Devletleri, 14 - 17 Nisan 2025, (Tam Metin Bildiri) identifier

4. XoFTR: Cross-modal Feature Matching Transformer

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Washington, Amerika Birleşik Devletleri, 17 - 21 Haziran 2024, ss.4275-4286, (Tam Metin Bildiri) identifier

5. U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection

4th Machine Learning for Health symposium-ML4H, Vancouver, Kanada, 15 - 16 Aralık 2024, cilt.259, ss.203-218, (Tam Metin Bildiri) identifier identifier

6. RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Washington, Amerika Birleşik Devletleri, 16 - 22 Haziran 2024, ss.3239-3249, (Tam Metin Bildiri) Sürdürülebilir Kalkınma identifier identifier

7. Transfer Learning-Based Prediction of Heating Energy Consumption Using Urban Building Energy Models (UBEM)

31st International Workshop on Intelligent Computing in Engineering, EG-ICE 2024, Vigo, İspanya, 3 - 05 Temmuz 2024, ss.580-589, (Tam Metin Bildiri) identifier

8. FairReFuse: Referee-Guided Fusion for Multimodal Causal Fairness in Depression Detection

33rd International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, Güney Kore, 3 - 09 Ağustos 2024, ss.7224-7232, (Tam Metin Bildiri) identifier

9. BASENET: A Learning-based Mobile Manipulator Base Pose Sequence Planning for Pickup Tasks

2024 International Conference on Intelligent Robots and Systems, Abu Dhabi, Birleşik Arap Emirlikleri, 14 - 18 Ekim 2024, ss.3666-3673, (Tam Metin Bildiri) Creative Commons License identifier identifier identifier

10. Towards Gender Fairness for Mental Health Prediction

32nd Int. Joint Conf. on Artificial Intelligence (IJCAI), MAKAO, 19 Ağustos 2023, (Tam Metin Bildiri) identifier

11. Correlation Loss: Enforcing Correlation between Classification and Localization

Thirty-Seventh AAAI Conference on Artificial Intelligence, Amerika Birleşik Devletleri, 7 - 14 Şubat 2023, (Tam Metin Bildiri) identifier

12. Useful Daylight Illuminance Prediction Under Data Imbalance in an Urban Context

41st Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2023, Graz, Avusturya, 20 - 22 Eylül 2023, cilt.2, ss.599-608, (Tam Metin Bildiri) Creative Commons License identifier

13. A Novel Graph Neural Network for Zone-Level Urban-Scale Building Energy Use Estimation

10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys), İstanbul, Türkiye, 15 - 16 Kasım 2023, ss.169-176, (Tam Metin Bildiri) Sürdürülebilir Kalkınma identifier identifier

14. Causal Structure Learning of Bias for Fair Affect Recognition

2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2023, Hawaii, Amerika Birleşik Devletleri, 3 - 07 Ocak 2023, ss.340-349, (Tam Metin Bildiri) Creative Commons License identifier identifier

15. Towards Causal Replay for Knowledge Rehearsal in Continual Learning

1st AAAI Bridge Program on Continual Causality, Washington, Amerika Birleşik Devletleri, 7 - 08 Şubat 2023, cilt.208, ss.63-70, (Tam Metin Bildiri) identifier

16. Towards Gender Fairness for Mental Health Prediction

32nd International Joint Conference on Artificial Intelligence, IJCAI 2023, Macao, Çin, 19 - 25 Ağustos 2023, cilt.2023-August, ss.5932-5940, (Tam Metin Bildiri) identifier

17. Counterfactual Fairness for Facial Expression Recognition

17th European Conference on Computer Vision, ECCV 2022, Tel-Aviv-Yafo, İsrail, 23 - 27 Ekim 2022, cilt.13805 LNCS, ss.245-261, (Tam Metin Bildiri) identifier

18. Compiling Open Datasets to Improve Urban Building Energy Models with Occupancy and Layout Data

Conference of the Association for ComputerAided Architectural Design Research in Asia (CAADRIA) 2022, Sydney, Avustralya, 12 Nisan - 14 Mayıs 2022, cilt.2, ss.669-678, (Tam Metin Bildiri) Creative Commons License Sürdürülebilir Kalkınma

19. An Analysis on Disentanglement in Machine Learning Makine Öǧrenmesinde Ayrişiklik Üzerine Bir Analiz

30th Signal Processing and Communications Applications Conference, SIU 2022, Safranbolu, Türkiye, 15 - 18 Mayıs 2022, (Tam Metin Bildiri) identifier

20. AssembleRL: Learning to Assemble Furniture from Their Point Clouds

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japonya, 23 - 27 Ekim 2022, cilt.2022-October, ss.2748-2753, (Tam Metin Bildiri) identifier identifier

21. Segment Augmentation and Differentiable Ranking for Logo Retrieval

26th International Conference on Pattern Recognition, ICPR 2022, Montreal, Kanada, 21 - 25 Ağustos 2022, cilt.2022-August, ss.1621-1627, (Tam Metin Bildiri) Creative Commons License identifier identifier

22. Object Detection for Autonomous Driving: High-Dynamic Range vs. Low-Dynamic Range Images

24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022, Shanghai, Çin, 26 - 28 Eylül 2022, (Tam Metin Bildiri) identifier identifier

23. Spatio-Temporal Analysis of Facial Actions using Lifecycle-Aware Capsule Networks

IEEE International Conference on Automatic Face and Gesture Recognition, Hindistan, 15 - 18 Aralık 2021, (Tam Metin Bildiri) identifier identifier

24. Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation

The 32nd British Machine Vision Conference, Birleşik Krallık, 22 Kasım 2021, (Tam Metin Bildiri)

25. Rank & Sort Loss for Object Detection and Instance Segmentation

IEEE/CVF International Conference on Computer Vision (ICCV), Amerika Birleşik Devletleri, 11 Ekim 2021, ss.3009-3018, (Tam Metin Bildiri)

27. Lifelong learning and personalization in long-term human-robot interaction (LEAP-HRI)

2021 ACM/IEEE International Conference on Human-Robot Interaction, HRI 2021, Virtual, Online, Amerika Birleşik Devletleri, 8 - 11 Mart 2021, ss.724-727, (Tam Metin Bildiri) identifier identifier

28. Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection

25th International Conference on Pattern Recognition (ICPR), ELECTR NETWORK, 10 - 15 Ocak 2021, ss.9577-9584, (Tam Metin Bildiri) Sürdürülebilir Kalkınma identifier identifier

29. Rank & Sort Loss for Object Detection and Instance Segmentation

18th IEEE/CVF International Conference on Computer Vision (ICCV), ELECTR NETWORK, 11 - 17 Ekim 2021, ss.2989-2998, (Tam Metin Bildiri) identifier identifier

30. A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection

2020 Conference on Neural Information Processing Systems, Montreal, Kanada, 6 - 12 Aralık 2020, cilt.33, ss.15534-15545, (Tam Metin Bildiri) Creative Commons License

31. Investigating Bias and Fairness in Facial Expression Recognition

ECCV2020 Workshop: ChaLearn Looking at People workshop ECCV: Fair Face Recognition and Analysis, 28 Ağustos 2020, (Tam Metin Bildiri) identifier

34. Vision-Based Lighting State Detection and Curtain Openness Ratio Prediction

The Symposium on Simulation for Architecture and Urban Design (SimAUD), Vienna, Avusturya, 23 - 25 Mayıs 2020, (Tam Metin Bildiri)

35. Generating positive bounding boxes for balanced training of object detectors

2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020, Colorado, Amerika Birleşik Devletleri, 1 - 05 Mart 2020, ss.883-892, (Tam Metin Bildiri) identifier identifier

36. A ranking-based, balanced loss function unifying classification and localisation in object detection

34th Conference on Neural Information Processing Systems, NeurIPS 2020, Virtual, Online, 6 - 12 Aralık 2020, cilt.2020-December, (Tam Metin Bildiri) identifier

37. Continual Learning for Affective Robotics: Why, What and How?

29th IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN), ELECTR NETWORK, 31 Ağustos - 04 Eylül 2020, ss.425-431, (Tam Metin Bildiri) identifier identifier

38. Video Content Analysis-Based Detection of Occupant Presence for Building Energy Modelling

CIB W78: Conference: Advances in ICT in Design, Construction and Management in Architecture, Engineering, Construction and Operations (AECO), Newcastle-Upon-Tyne, Birleşik Krallık, 18 - 20 Eylül 2019, (Tam Metin Bildiri) Creative Commons License

39. Automated building energy modeling for existing buildings using computer vision

CIB W78: Conference: Advances in ICT in Design, Construction and Management in Architecture, Engineering, Construction and Operations (AECO), Newcastle-Upon-Tyne, Birleşik Krallık, 18 - 20 Eylül 2019, (Tam Metin Bildiri) Creative Commons License

41. Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, Çin, 4 - 08 Kasım 2019, ss.4992-4999, (Tam Metin Bildiri) Sürdürülebilir Kalkınma identifier identifier

42. Learning to Increment A Contextual Model

Continual Learning Workshop at Neural Information Processing Systems, Montreal, Kanada, 6 - 07 Aralık 2018, ss.1-4, (Tam Metin Bildiri)

43. CINet: A Learning Based Approach to Incremental Context Modeling in Robots

International Conference on Intelligent Robots (IROS 2018), Madrid, İspanya, 1 - 05 Ekim 2018, (Tam Metin Bildiri) Creative Commons License identifier identifier

44. Localization recall precision (LRP): A new performance metric for object detection

15th European Conference on Computer Vision, ECCV 2018, Munich, Almanya, 8 - 14 Eylül 2018, ss.521-537, (Tam Metin Bildiri) Creative Commons License identifier identifier

45. What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Avustralya, 21 - 25 Mayıs 2018, (Tam Metin Bildiri) Creative Commons License identifier

46. A Deep Incremental Boltzmann Machine for Modeling Context in Robots

2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Avustralya, 21 - 25 Mayıs 2018, (Tam Metin Bildiri) Creative Commons License identifier identifier

47. Dynamic gaze analysis: An application enviroment for face-to-face communication

2017 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Türkiye, 16 - 17 Eylül 2017, (Tam Metin Bildiri) identifier identifier

48. Using deep networks for drone detection

14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017, Lecce, İtalya, 29 Ağustos - 01 Eylül 2017, (Tam Metin Bildiri) Creative Commons License identifier identifier

49. Drone-vs-Bird detection challenge at IEEE AVSS2017

14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017, Lecce, İtalya, 29 Ağustos - 01 Eylül 2017, (Tam Metin Bildiri) Creative Commons License identifier identifier

50. A gaze-centered multimodal approach to human-human social interaction

3rd IEEE International Conference on Cybernetics, CYBCONF 2017, Exeter, Birleşik Krallık, 21 - 23 Haziran 2017, (Tam Metin Bildiri) identifier identifier

51. Analyzing deep features for trademark retrieval Marka Erişimi İcin Derin Özniteliklerin İncelenmesi

25th Signal Processing and Communications Applications Conference, SIU 2017, Antalya, Türkiye, 15 - 18 Mayıs 2017, (Tam Metin Bildiri) identifier

52. SHREC'16 track: Shape retrieval of low-cost RGB-D captures

9th Eurographics Workshop on 3D Object Retrieval, 3DOR 2016, Lisbon, Portekiz, 08 Mayıs 2016, ss.69-78, (Tam Metin Bildiri) identifier

54. Integrating Spatial Concepts into a Probabilistic Concept Web

International Conference on Advanced Robotics (ICAR), İstanbul, Türkiye, 27 - 31 Temmuz 2015, ss.259-264, (Tam Metin Bildiri) identifier identifier

55. METU Dataset: A Big Dataset for Benchmarking Trademark Retrieval

14th IAPR International Conference on Machine Vision Applications (MVA), Tokyo, Japonya, 18 - 22 Mayıs 2015, ss.514-517, (Tam Metin Bildiri) identifier identifier

56. An MRF Framework For Co-Solving Image Segmentation and Border Ownership

23nd Signal Processing and Communications Applications Conference (SIU), Malatya, Türkiye, 16 - 19 Mayıs 2015, ss.839-842, (Tam Metin Bildiri) identifier identifier

57. Learning and Using Context on a Humanoid Robot Using Latent Dirichlet Allocation

4th Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (IEEE ICDL-Epirob), Genoa, İtalya, 13 - 16 Ekim 2014, ss.201-207, (Tam Metin Bildiri) identifier identifier

58. Using Slowness Principle for Feature Selection: Relevant Feature Analysis

22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Türkiye, 23 - 25 Nisan 2014, ss.1540-1543, (Tam Metin Bildiri) identifier

59. Analysis of Widely-used Descriptors for Finger-vein Recognition

9th International Conference on Computer Vision Theory and Applications (VISAPP), Lisbon, Portekiz, 5 - 08 Ocak 2014, ss.564-571, (Tam Metin Bildiri) identifier

60. Recurrent Slow Feature Analysis for Developing Object Permanence in Robots

IROS Workshop on Neuroscience and Robotics, 03 Kasım 2013, (Tam Metin Bildiri)

61. Co-learning nouns and adjectives

2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013, Osaka, Japonya, 18 - 22 Ağustos 2013, (Tam Metin Bildiri) identifier identifier

62. Learning Social Affordances and Using Them for Planning

Proceedings of the Annual Meeting of the Cognitive Science Society, Berlin, Almanya, 31 Temmuz - 03 Ağustos 2013, ss.3604-3609, (Tam Metin Bildiri)

63. Multimodal Stereo Vision Using Mutual Information with Adaptive Windowing

Int. IAPR Conference on Machine Vision and Applications, Kyoto, Japonya, 20 - 23 Mayıs 2013, cilt.1, (Tam Metin Bildiri)

64. Global Binary Patterns A Novel Shape Descriptor

Int. IAPR Conference on Machine Vision and Applications, Kyoto, Japonya, 20 - 23 Mayıs 2013, cilt.1, (Tam Metin Bildiri)

65. Relating affordances with verbs, nouns and adjectives Sǎglarlik ile fiiller, isimler ve sifatlarin iliş kilendirilmesi

2013 21st Signal Processing and Communications Applications Conference, SIU 2013, Haspolat, Türkiye, 24 - 26 Nisan 2013, (Tam Metin Bildiri) identifier

66. A novel shape descriptor: Intersection consistency histograms Yeni bir ş ekil betimleyici: Kesişimlerin tutarlilǐgi histogram

2013 21st Signal Processing and Communications Applications Conference, SIU 2013, Haspolat, Türkiye, 24 - 26 Nisan 2013, (Tam Metin Bildiri) identifier

67. A comprehensive database for border ownership Sinir Sahiplǐgi Için Kapsamli Bir Veri Taban

2013 21st Signal Processing and Communications Applications Conference, SIU 2013, Haspolat, Türkiye, 24 - 26 Nisan 2013, (Tam Metin Bildiri) identifier

68. Extraction of border ownership information by conditional random field model Koşullu rastgele alan modeli ile sinir sahipligi bilgisi çikarimi

2013 21st Signal Processing and Communications Applications Conference, SIU 2013, Haspolat, Türkiye, 24 - 26 Nisan 2013, (Tam Metin Bildiri) identifier

69. Learning adjectives and nouns from affordances on the iCub humanoid robot

12th International Conference on Simulation of Adaptive Behavior, SAB 2012, Odense, Danimarka, 27 - 30 Ağustos 2012, cilt.7426 LNAI, ss.330-340, (Tam Metin Bildiri) Creative Commons License identifier

70. Human and robotics hands grasping danger

International Joint Conference on Neural Networks (IJCNN), Brisbane, Avustralya, 10 - 15 Haziran 2012, (Tam Metin Bildiri) Creative Commons License identifier identifier

71. Learning affordances for categorizing objects and their properties

2010 20th International Conference on Pattern Recognition, ICPR 2010, İstanbul, Türkiye, 23 - 26 Ağustos 2010, ss.3089-3092, (Tam Metin Bildiri) identifier

72. Affordances and Emergence of Concepts

Proceedings of the Tenth International Conference on Epigenetic Robotics , Lund, İsveç, 5 - 07 Kasım 2010, ss.1-8, (Tam Metin Bildiri)

73. Using 3D contours and their relations for cognitive vision and robotics

2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009, Guzelyurt, Kıbrıs (Gkry), 14 - 16 Eylül 2009, ss.409-414, (Tam Metin Bildiri) identifier

74. Bayesian classification of image structures

16th Scandinavian Conference on Image Analysis, SCIA 2009, Oslo, Norveç, 15 - 18 Haziran 2009, cilt.5575 LNCS, ss.676-685, (Tam Metin Bildiri) Creative Commons License identifier

75. Relations Between Reconstructed 3D entities

Proceedings of the Third International Conference on Computer Vision Theory and Applications, Funchal, Portekiz, 22 - 25 Ocak 2008, ss.186-193, (Tam Metin Bildiri)

76. A Signal-Symbol Loop Mechanism For Enhanced Edge Extraction

Proceedings of the Third International Conference on Computer Vision Theory and Applications , Funchal, Portekiz, 22 - 25 Ocak 2008, ss.214-221, (Tam Metin Bildiri)

77. DEPTH PREDICTION AT HOMOGENEOUS IMAGE STRUCTURES

Proceedings of the Third International Conference on Computer Vision Theory and Applications, Funchal, Portekiz, 22 - 25 Ocak 2008, ss.520-527, (Tam Metin Bildiri)

78. Semantic Reasoning for Scene Interpretation

4th International Cognitive Vision Workshop (ICVW 2008), Santorini, Yunanistan, 12 - 15 Mayıs 2008, cilt.5329, ss.121-123, (Tam Metin Bildiri) identifier identifier

79. A scene representation based on multi-modal 2D and 3D features

2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brezilya, 14 - 21 Ekim 2007, (Tam Metin Bildiri) identifier

80. Improving junction detection by semantic interpretation

Proceedings of the Second International Conference on Computer Vision Theory and Applications , Barcelona, İspanya, 8 - 11 Mart 2007, ss.264-271, (Tam Metin Bildiri)

81. Statistical analysis of second-order relations of 3D structures

Proceedings of the Second International Conference on Computer Vision Theory and Applications, Barcelona, İspanya, 8 - 11 Mart 2007, ss.13-20, (Tam Metin Bildiri)

82. Utilizing semantic interpretation of junctions for 3D-2D pose estimation

3rd International Symposium on Visual Computing, ISVC 2007, Lake Tahoe, NV, Amerika Birleşik Devletleri, 26 - 28 Kasım 2007, cilt.4841 LNCS, ss.692-701, (Tam Metin Bildiri) identifier

83. Statistical analysis of local 3D structure in 2D images

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, Amerika Birleşik Devletleri, 17 - 22 Haziran 2006, cilt.1, ss.1114-1121, (Tam Metin Bildiri) identifier

84. Optic Flow Statistics and Intrinsic Dimensionality

Brain Inspired Cognitive Systems, Stirling, Birleşik Krallık, 29 Ağustos - 01 Eylül 2004, ss.1-7, (Tam Metin Bildiri)
Metrikler

Yayın

131

Yayın (WoS)

75

Yayın (Scopus)

101

Atıf (WoS)

1438

H-İndeks (WoS)

16

Atıf (Scopus)

1876

H-İndeks (Scopus)

19

Atıf (Scholar)

700

H-İndeks (Scholar)

13

Atıf (Diğer Toplam)

2

Proje

24

Fikri Mülkiyet

1

Tez Danışmanlığı

47

Açık Erişim

46
BM Sürdürülebilir Kalkınma Amaçları