TY - JOUR AU - Szűcs, Gábor AU - Borsodi, R. AU - Papp, Dávid TI - Multi-camera trajectory matching based on hierarchical clustering and constraints JF - MULTIMEDIA TOOLS AND APPLICATIONS: AN INTERNATIONAL JOURNAL J2 - MULTIMED TOOLS APPL VL - 83 PY - 2024 SP - 44879 EP - 44902 PG - 24 SN - 1380-7501 DO - 10.1007/s11042-023-17397-0 UR - https://m2.mtmt.hu/api/publication/34231292 ID - 34231292 N1 - Export Date: 2 November 2023 CODEN: MTAPF Correspondence Address: Szűcs, G.; Department of Telecommunications and Media Informatics, Műegyetem Rkp. 3., Hungary; email: szucs@tmit.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Papp, Dávid AU - Borsodi, Regő TI - Determining Hybrid Re-id Features of Vehicles in Videos for Transport Analysis JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMM J VL - 14 PY - 2022 IS - 1 SP - 17 EP - 23 PG - 7 SN - 2061-2079 DO - 10.36244/ICJ.2022.1.3 UR - https://m2.mtmt.hu/api/publication/32630750 ID - 32630750 N1 - Export Date: 24 May 2022 AB - The research topic presented in this paper belongs to computer vision problems in the transport application area, where the statistical data of the results give the input for the transport analysis. Although object tracking in a controlled environment could be performed with good results in general, accurate and detailed annotation of vehicles is a common problem in traffic analysis. Such annotation includes static and dynamic attributes of numerous vehicles. Most recent object trackers employ CNNs to compute the so-called re-identification features of the bounding boxes. In this paper we introduce hybrid re-identification features, which combine latent, static, and dynamic attributes to improve tracking. Furthermore, we propose a lightweight solution that could be integgrated in a real-time multi-camera tracking system. LA - English DB - MTMT ER - TY - JOUR AU - Szűcs, Gábor AU - Papp, Dávid TI - Zero Initialised Unsupervised Active Learning by Optimally Balanced Entropy-Based Sampling for Imbalanced Problems JF - JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE J2 - J EXP THEOR ARTIF IN VL - 34 PY - 2022 IS - 5 SP - 781 EP - 814 PG - 34 SN - 0952-813X DO - 10.1080/0952813X.2021.1924871 UR - https://m2.mtmt.hu/api/publication/32236541 ID - 32236541 N1 - Export Date: 30 September 2022 Correspondence Address: Szűcs, G.; Department of Telecommunications and Media Informatics, Hungary; email: szucs@tmit.bme.hu AB - Given the challenge of gathering labelled training data for machine learning tasks, active learning has become popular. This paper focuses on the beginning of unsupervised active learning, where there are no labelled data at all. The aim of this zero initialised unsupervised active learning is to select the most informative examples – even from an imbalanced dataset – to be labelled manually. Our solution with proposed selection strategy, called Optimally Balanced Entropy-Based Sampling (OBEBS) reaches a balanced training set at each step to avoid imbalanced problems. Two theorems of the optimal solution for selection strategy are also presented and proved in the paper. At the beginning of the active learning, there is not enough information for supervised machine learning method, thus our selection strategy is based on unsupervised learning (clustering). The cluster membership likelihoods of the items are essential for the algorithm to connect the clusters and the classes, i.e., to find assignment between them. For the best assignment, the Hungarian algorithm is used, and single, multi, and adaptive assignment variants of OBEBS method are developed. Based on generated and real images datasets of handwritten digits, the experimental results show that our method surpasses the state-of-the-art methods. LA - English DB - MTMT ER - TY - THES AU - Papp, Dávid TI - Felügyelet nélküli és kiegyenlítettség-vezérelt aktív tanulásos képosztályozás PB - Budapesti Műszaki és Gazdaságtudományi Egyetem PY - 2021 SP - 140 UR - https://m2.mtmt.hu/api/publication/32745833 ID - 32745833 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Gulyás, Gábor György AU - Gönczy, László AU - Kocsis, Imre AU - Magyar, Gábor AU - Papp, Dávid AU - Szűcs, Gábor ED - Magyar, Gábor ED - Nemeslaki, András ED - Szakadát, István TI - Digitális lábnyomok és hatásuk a pénzügyi rendszerre T2 - A digitális transzformáció technológiai kérdései PB - Gondolat Kiadó CY - Budapest SN - 9789635561988 PY - 2021 SP - 19 EP - 171 PG - 153 UR - https://m2.mtmt.hu/api/publication/32546390 ID - 32546390 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Papp, Dávid TI - Zero Initialized Active Learning with Spectral Clustering using Hungarian Method JF - ACTA CYBERNETICA J2 - ACTA CYBERN-SZEGED VL - 25 PY - 2021 IS - 2 SP - 401 EP - 419 PG - 19 SN - 0324-721X DO - 10.14232/ACTACYB.288006 UR - https://m2.mtmt.hu/api/publication/32534202 ID - 32534202 N1 - Export Date: 2 May 2022 CODEN: ACCYD Correspondence Address: Papp, D.; Dept. of Telecommunications and Media Informatics, Hungary; email: pappd@tmit.bme.hu LA - English DB - MTMT ER - TY - CONF AU - Regő, Borsodi AU - Papp, Dávid ED - Faggioli, Guglielmo ED - Ferro, Nicola ED - Joly, Alexis ED - Maistro, Maria ED - Piroi, FLorina TI - Incorporation of object detection models and location data into snake species classification T2 - Proceedings of the Working Notes of CLEF 2021 T3 - CEUR Workshop Proceedings, ISSN 1613-0073 PY - 2021 SP - 1499 EP - 1511 PG - 13 UR - https://m2.mtmt.hu/api/publication/32508257 ID - 32508257 N1 - Scopus:hiba:85113470782 2022-10-12 16:51 típus nem egyezik AB - Photo-based automatic snake species identification could assist in clinical management of snakebites. LifeCLEF announced the SnakeCLEF 2021 challenge, which aimed attention on this task and provided location metadata for most snake images. This paper describes the participation of the BME-TMIT team in this challenge. In order to reduce clutter and drop the unnecessary background, we employed the state-of-the-art EfficientDet object detector, which was fine-tuned on manually annotated images. Detected snakes were then classified by EfficientNet weighted with the likelihood of location information. Based on the official evaluation of SnakeCLEF 2021, our solution achieved an F1 country score of 0.903, which placed our team at rank 1 position in the challenge. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). LA - English DB - MTMT ER - TY - CONF AU - Papp, Dávid TI - Spectral Clustering based Active Zero-shot Learning T2 - The 12th Conference of PhD Students in Computer Science PB - Szegedi Tudományegyetem (SZTE) C1 - Szeged PY - 2020 SP - 54 EP - 57 PG - 4 UR - https://m2.mtmt.hu/api/publication/31656568 ID - 31656568 LA - English DB - MTMT ER - TY - JOUR AU - Papp, Dávid AU - Knoll, Zsolt AU - Szűcs, Gábor TI - Graph construction with condition-based weights for spectral clustering of hierarchical datasets JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMM J VL - 12 PY - 2020 IS - 2 SP - 34 EP - 40 PG - 7 SN - 2061-2079 DO - 10.36244/ICJ.2020.2.5 UR - https://m2.mtmt.hu/api/publication/31615387 ID - 31615387 N1 - Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary BME Balatonfüred Student Research Group, Hungary Export Date: 14 June 2022 AB - Most of the unsupervised machine learning algorithms focus on clustering the data based on similarity metrics, while ignoring other attributes, or perhaps other type of connections between the data points. In case of hierarchical datasets, groups of points (point-sets) can be defined according to the hierarchy system. Our goal was to develop such spectral clustering approach that preserves the structure of the dataset throughout the clustering procedure. The main contribution of this paper is a set of conditions for weighted graph construction used in spectral clustering. Following the requirements – given by the set of conditions – ensures that the hierarchical formation of the dataset remains unchanged, and therefore the clustering of data points imply the clustering of point-sets as well. The proposed spectral clustering algorithm was tested on three datasets, the results were compared to baseline methods and it can be concluded the algorithm with the proposed conditions always preserves the hierarchy structure. LA - English DB - MTMT ER - TY - CHAP AU - Papp, Dávid AU - Szűcs, Gábor AU - Knoll, Zsolt TI - Machine preparation for human labelling of hierarchical train sets by spectral clustering T2 - 10th IEEE International Conference on Cognitive Infocommunications, (CogInfoCom 2019) PB - IEEE CY - Piscataway (NJ) SN - 9781728147925 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2019 SP - 157 EP - 162 PG - 6 DO - 10.1109/CogInfoCom47531.2019.9089906 UR - https://m2.mtmt.hu/api/publication/31014870 ID - 31014870 N1 - Budapest University of Technology and Economics, Department of Telecommunications and Media Informatics, Budapest, Hungary Budapest University of Technology and Economics, Balatonfüred Student Research Group, Balatonfüred, Hungary Cited By :1 Export Date: 6 December 2021 LA - English DB - MTMT ER -