Lorenzo SEIDENARI

Ruolo attuale:: Professore Associato
SSD:: IINF-05/A - Sistemi di elaborazione delle informazioni
Afferenza organizzativa:: Dipartimento di Ingegneria dell'Informazione

Recapiti

	0552758602
	lorenzo.seidenari(AT)unifi.it

Ulteriori Recapiti

	Viale Morgagni 65, 50134, Firenze
	+39 055 275 1395
	lorenzo.seidenari(AT)unifi.it
	www.micc.unifi.it/seidenari

Lorenzo SEIDENARI

Orario di ricevimento (aggiornato al 06/09/2024)

Ricevimento telematico/in presenza tramite prenotazione:

Prenota!

Nella prenotazione indicare se si vuole effettuare il ricevimento in presenza.

Lorenzo SEIDENARI

Biografia

Lorenzo Seidenari si è laureato in Ingegneria Informatica nel 2008 e ha ottenuto il Dottorato in Ingegneria Informatica, Multimedia e Telecomunicazioni nel 2012 con una tesi sul riconoscimento supervisionato e semi-supervisionato di eventi tramite l'uso di descrittori locali spazio-temporali. Nel 2013 è stato visiting scholar presso la University of Michigan. Dal 2012 al 2018 è stato assegnista di ricerca presso il Media Integration and Communication Center. Ha ricoperto il ruolo di Ricercatore a Tempo Determinato (a) dal 2018 al 2020 e successivamente di Ricercatore a Tempo Determinato (b). Nel 2018 ha ricevuto l'abilitazione per Professore di Seconda fascia nei settori 09/H1 e 01/B1.

Nel 2019 ha cofondato lo Spin-off universitario SmallPixels.

Nel 2021 è stato nominato ELLIS Scholar.

Dal 2023 è Professore Associato in Sistemi di Elaborazione delle Informazioni (IINF/05) e insegna Fondamenti di Informatica nei corsi di Laurea Triennali di Ingegneria Meccanica e Gestionale, Generative Models e Deep Learning Applications nel corso di Laurea Magistrale in Intelligenza Artificiale.

Lorenzo SEIDENARI

Curriculum

Lorenzo Seidenari è Professore Associato presso l'Università di Firenze. In precedenza, è stato ricercatore postdoc presso il Media Integration and Communication Center dell'Università di Firenze. Ha conseguito il dottorato di ricerca in ingegneria informatica nel 2012 presso l'Università di Firenze. La sua ricerca si concentra sul riconoscimento di oggetti e azioni in video e immagini utilizzando il deep learning.

È stato membro del comitato organizzatore di ACM MM 2010, ECCV 2012, CBMI 2017. È revisore per numerose conferenze internazionali, tra cui: CBMI, ICIAP, ACM MM, CAIP, CIARP, IEEE CVPR, IEEE ECCV, IEEE ICME, IAPR ICPR, WIAMIS, ICVS, AVSS. Inoltre, collabora frequentemente come revisore per diverse riviste prestigiose, tra cui: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Human Machine Systems (THMS), IEEE Transactions on Circuit and Systems for Video Technology (TCSVT), IEEE Transactions on Cybernetics (TCYB), ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Pattern Recognition Letters (PRL), Computer Vision and Image Understanding (CVIU), Pattern Recognition (PR), Multimedia Tools and Applications (MTAP), Pattern Analysis and Applications (PAAA).

Ricopre frequentemente il ruolo di Area Chair per ACM Multimedia e British Machine Vision Conference.

È Associate Editor per IEEE Transactions on Multimedia e Elsevier Pattern Recognition.

Fa parte del Comitato del programma di dottorato in Ingegneria dell'Informazione. Ha insegnato un corso a livello di dottorato presso le Scuole di Dottorato in Smart Computing e Ingegneria Informatica sul riconoscimento delle immagini. Ha supervisionato 8 studenti di dottorato, 20 studenti di laurea magistrale e 7 studenti di laurea triennale.

È autore di oltre 25 articoli su riviste scientifiche e di più di 50 articoli in conferenze con revisione paritaria.

Secondo Google Scholar, le sue pubblicazioni hanno ricevuto 3134 citazioni con un H-Index di 29 (https://scholar.google.com/citations?user=mBMXVPAAAAAJ&hl=en&oi=ao).

Lorenzo SEIDENARI

Interessi

Computer Vision; Machine Learning; Multimedia Analysis

Lorenzo SEIDENARI

Pubblicazioni

Legenda

Contributo su rivista |

Articolo su libro |

Libro |

Contributo in atti di convegno (proceeding) |

Brevetto |

Curatela | Altro

Altro |

Tesi di Dottorato

Cores, Daniel; Seidenari, Lorenzo; Bimbo, Alberto Del; Brea, Víctor M.; Mucientes, Manuel (2025). A fine-tuning approach based on spatio-temporal features for few-shot video object detection. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, vol. 146, pp. 0-0, ISSN:0952-1976 DOI

Ciamarra, Andrea; Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto (2024). FLODCAST: Flow and depth forecasting via multimodal recurrent architectures. PATTERN RECOGNITION, pp. 0-0, ISSN:0031-3203 DOI

Marchetti, Francesco; Becattini, Federico; Seidenari, Lorenzo; Bimbo, Alberto Del (2024). SMEMO: Social Memory for Trajectory Forecasting. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. PP, pp. 1-15, ISSN:0162-8828 DOI

Marchetti, Francesco; Mordan, Taylor; Becattini, Federico; Seidenari, Lorenzo; Bimbo, Alberto Del; Alahi, Alexandre (2024). CrossFeat: Semantic Cross-modal Attention for Pedestrian Behavior Forecasting. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, pp. 1-10, ISSN:2379-8904 DOI

Simoni, Alessandro; Marchetti, Francesco; Borghi, Guido; Becattini, Federico; Seidenari, Lorenzo; Vezzani, Roberto; Del Bimbo, Alberto (2024). 3D Pose Nowcasting: Forecast the future to improve the present. COMPUTER VISION AND IMAGE UNDERSTANDING, vol. 251, pp. 1-9, ISSN:1077-3142 DOI

Andrea Ciamarra, Roberto Caldelli, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo (2024). Deepfake detection by exploiting surface anomalies: the SurFake approach. In: IEEE/CVF Winter Conference on Applications of Computer Vision 2024, Waikoloa, Hawaii, 04/01/2024, IEEE Computer Society, vol. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1024-1033. Accesso ONLINE all'editore

Guimard, Quentin; Sassatelli, Lucile; Marchetti, Francesco; Becattini, Federico; Seidenari, Lorenzo; Bimbo, Alberto Del (2024). Deep Variational Learning for 360° Adaptive Streaming. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS, pp. 0-0, ISSN:1551-6857 DOI

Francesco Marchetti; Federico Becattini; Lorenzo Seidenari; Alberto Del Bimbo (2023). Multiple Trajectory Prediction of Moving Agents with Memory Augmented Networks. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, pp. 0-0, ISSN:0162-8828 DOI

Bubnicki, Jakub W.; Norton, Ben; Baskauf, Steven J.; Bruce, Tom; Cagnacci, Francesca; Casaer, Jim; Churski, Marcin; Cromsigt, Joris P. G. M.; Farra, Simone Dal; Fiderer, Christian; Forrester, Tavis D.; Hendry, Heidi; Heurich, Marco; Hofmeester, Tim R.; Jansen, Patrick A.; Kays, Roland; Kuijper, Dries P. J.; Liefting, Yorick; Linnell, John D. C.; Luskin, Matthew S.; Mann, Christopher; Milotic, Tanja; Newman, Peggy; Niedballa, Jürgen; Oldoni, Damiano; Ossi, Federico; Robertson, Tim; Rovero, Francesco; Rowcliffe, Marcus; Seidenari, Lorenzo; Stachowicz, Izabela; Stowell, Dan; Tobler, Mathias W.; Wieczorek, John; Zimmermann, Fridolin; Desmet, Peter (2023). Camtrap DP: an open standard for the FAIR exchange and archiving of camera trap data. REMOTE SENSING IN ECOLOGY AND CONSERVATION, pp. 1-13, ISSN:2056-3485 DOI

Cultrera L.; Becattini F.; Seidenari L.; Pala P.; Del Bimbo A. (2023). Explaining autonomous driving with visual attention and end-to-end trainable region proposals. JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, pp. 1-13, ISSN:1868-5137 DOI Accesso ONLINE all'editore

Bosquet B.; Cores D.; Seidenari L.; Brea V.M.; Mucientes M.; Del Bimbo A.; (2023). A full data augmentation pipeline for small object detection based on generative adversarial networks. PATTERN RECOGNITION, vol. 133, pp. 1-12, ISSN:0031-3203 DOI

Cultrera, Luca; Becattini, Federico; Seidenari, Lorenzo; Pala, Pietro; Bimbo, Alberto Del (2023). Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, pp. 1-10, ISSN:2379-8904 DOI

Ciamarra A.; Becattini F.; Seidenari L.; Del Bimbo A. (2022). Forecasting Future Instance Segmentation with Learned Optical Flow and Warping. In: International Conference on Image Analysis and Processing, Springer, vol. 13233 LNCS, pp. 349-361, ISBN:978-3-031-06432-6 DOI

Guimard Q.; Sassatelli L.; Marchetti F.; Becattini F.; Seidenari L.; Del Bimbo A.; (2022). Deep variational learning for multiple trajectory prediction of 360° head movements. In: Multimedia Systems, ACM, pp. 12-26, ISBN:9781450392839 DOI

Galteri, Leonardo; Seidenari, Lorenzo; Bongini, Pietro; Bertini, Marco; Bimbo, Alberto Del (2022). LANBIQUE: LANguage-based Blind Image QUality Evaluation. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS, pp. 1-19, ISSN:1551-6857 DOI

Zappardino, Fabio; Uricchio, Tiberio; Seidenari, Lorenzo; del Bimbo, Alberto (2021). Learning Group Activities from Skeletons without Individual Action Labels. In: 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp. 10412-10417, ISBN:978-1-7281-8808-9 DOI

Lorenzo Seidenari; Leonardo Galteri; Pietro Bongini; Marco Bertini; Alberto Del Bimbo (2021). Language Based Image Quality Assessment. In: Multimedia Asia, ACM, pp. 1-7, ISBN:9781450386074 DOI

Federico Becattini, Tiberio Uricchio, Lorenzo Seidenari, Lamberto Ballan, Alberto Del Bimbo (2021). Am I done? Predicting action progress in videos. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS, pp. 1-24, ISSN:1551-6857 DOI

Galteri L.; Seidenari L.; Uricchio T.; Bertini M.; Bimbo A.D. (2020). Preserving low-quality video through deep learning. In: 2nd International Conference Florence Heri-Tech: The Future of Heritage Science and Technologies, HERITECH 2020, 2020, IOP Publishing Ltd, vol. 949, pp. 0-0. DOI

Galteri L.; Bertini M.; Seidenari L.; Uricchio T.; Del Bimbo A. (2020). Increasing Video Perceptual Quality with GANs and Semantic Coding. In: 28th ACM International Conference on Multimedia, MM 2020, usa, 2020, Association for Computing Machinery, Inc, pp. 862-870, ISBN:9781450379885 DOI

Berlincioni L.; Becattini F.; Seidenari L.; Del Bimbo A. (2020). Multiple future prediction leveraging synthetic trajectories. In: 25th International Conference on Pattern Recognition, ICPR 2020, ita, 2021, Institute of Electrical and Electronics Engineers Inc., pp. 6081-6088, ISBN:978-1-7281-8808-9 DOI

Francesco Marchetti;Federico Becattini;Lorenzo Seidenari; Alberto Del Bimbo (2020). COMPUTER-IMPLEMENTED METHOD FOR PREDICTING MULTIPLE FUTURE TRAJECTORIES OF MOVING OBJECTS. Numero: EP3916676A1;WO2021239998A1 IMRA Europe

Cultrera L.; Seidenari L.; Becattini F.; Pala P.; Del Bimbo A. (2020). Explaining autonomous driving by learning end-to-end visual attention. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, usa, 2020, IEEE Computer Society, vol. 2020-, pp. 1389-1398, ISBN:978-1-7281-9360-1 DOI

Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo (2020). Mantra: Memory augmented networks for multiple trajectory prediction. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020, IEEE Computer Society, pp. 7141-7150, ISBN:978-1-7281-7168-5 DOI

Menardi M.; Falcon A.; Mohamed S.S.; Seidenari L.; Serra G.; Del Bimbo A.; Tasso C. (2020). Text-to-Image Synthesis Based on Machine Generated Captions. In: 16th Italian Research Conference on Digital Libraries, IRCDL 2020, ita, 2020, Springer, vol. 1177, pp. 62-74, ISBN:978-3-030-39904-7 DOI

Quero J.M.; Cruciani F.; Seidenari L.; Espinilla M.; Nugent C. (2019). Straightforward Recognition of Daily Objects in Smart Environments from Wearable Vision Sensor. In: 2019 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2019, jpn, 2019, Institute of Electrical and Electronics Engineers Inc., pp. 46-51, ISBN:978-1-5386-9151-9 DOI

Lorenzo Seidenari, Alessandro Rozza, Alberto Del Bimbo (2019). Real-Time Demographic Profiling from Face Imagery with Fisher Vectors. MACHINE VISION AND APPLICATIONS, pp. 1-16, ISSN:0932-8092 DOI

Federico Becattini, Lorenzo Seidenari, Lorenzo Berlincioni, Leonardo Galteri, Alberto Del Bimbo (2019). Vehicle Trajectories from Unlabeled Data through Iterative Plane Registration. In: International Conference on Image Analysis and Processing, Springer, pp. 0-0. DOI

Pala, Pietro; Seidenari, Lorenzo; Berretti, Stefano; Del Bimbo, Alberto (2019). Enhanced skeleton and face 3D data for person re-identification from depth cameras. COMPUTERS & GRAPHICS, vol. 79, pp. 69-80, ISSN:0097-8493 DOI Accesso ONLINE all'editore

Quero J.M.; Cruciani F.; Seidenari L.; Espinilla M.; Nugent C. (2019). Straightforward Recognition of Daily Objects in Smart Environments from Wearable Vision Sensor. In: 2019 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2019, jpn, 2019, Institute of Electrical and Electronics Engineers Inc., pp. 46-51, ISBN:978-1-5386-9151-9 DOI

Leonardo Galteri , Lorenzo Seidenari , Marco Bertini , Alberto Del Bimbo (2019). Deep Universal Generative Adversarial Compression Artifact Removal. IEEE TRANSACTIONS ON MULTIMEDIA, pp. 1-15, ISSN:1520-9210 DOI

Lorenzo Berlincioni, Federico Becattini, Leonardo Galteri, Lorenzo Seidenari, Alberto Del Bimbo (2019). Road layout understanding by generative adversarial inpainting. In: Escalera, S., Ayache, S., Wan, J., Madadi, M., Güçlü, U., Baró, X.. Inpainting and Denoising Challenges, pp. 111-128 Springer, Cham, ISBN:978-3-030-25614-2. DOI

Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Uricchio, Tiberio; Del Bimbo, Alberto (2019). Fast Video Quality Enhancement using GANs. In: ACM Multimedia, ACM, pp. 1065-1067, ISBN:9781450368896 DOI

Francesco Turchini, Lorenzo Seidenari, Leonardo Galteri, Andrea Ferracani, Giuseppe Becchi, Alberto Del Bimbo (2019). Flexible Automatic Football Filming and Summarization. In: 27th ACM International Conference on Multimedia, MM 2019, Association for Computing Machinery, New York, NY, United States, pp. 108-114.

Galteri L.; Seidenari L.; Bertini M.; Del Bimbo A. (2019). Towards Real-Time Image Enhancement GANs. In: 18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019, ita, 2019, Springer Verlag, vol. 11678, pp. 183-195, ISBN:978-3-030-29887-6 DOI Accesso ONLINE all'editore

Lorenzo Seidenari, Claudio Baecchi, Tiberio Uricchio, Andrea Ferracani, Marco Bertini, Alberto Del Bimbo (2018). Wearable Systems for Improving Museum Experience. In: Xavier Alameda-Pineda, Elisa Ricci, Nicu Sebe. Multi-Modal Behavioral Analysis in the Wild: Advances and Challenges, pp. 3-28 Elsevier, ISBN:9780128146019.

Francesco Turchini, Lorenzo Seidenari,Tiberio Uricchio, Alberto Del Bimbo (2018). Deep Learning Based Surveillance System for Open Critical Areas. INVENTIONS, vol. 3, pp. 1-13, ISSN:2411-5134 DOI Accesso ONLINE all'editore

Leonardo Galteri, Marco Bertini, Lorenzo Seidenari, Alberto Del Bimbo (2018). Video Compression for Object Detection Algorithms. In: International Conference on Pattern Recognition 2018, Beijing, China, 20-24 August 2018, IEEE, pp. 0-0. DOI

P. Pala, L. Seidenari, S. Berretti, A. Del Bimbo (2018). Person Re-Identification from Depth Cameras using Skeleton and 3D Face Data. In: 11th Eurographics Workshop on 3D Object Retrieval} (3DOR 2018), Delft, Olanda, 15-16 Maggio, 2018, Eurographics, pp. 1-7.

Seidenari, Lorenzo; Baecchi, Claudio; Uricchio, Tiberio; Ferracani, Andrea; Bertini, Marco; Del Bimbo, Alberto; (2018). Object Recognition and Tracking for Smart Audio Guides. In: Italian Research Conference on Digital Libraries (IRCDL 2018), Springer, pp. 1-6. DOI

Bondi, Enrico; Pala, Pietro; Seidenari, Lorenzo; Berretti, Stefano; Del Bimbo, Alberto (2018). Long Term Person Re-Identification from Depth Cameras using Facial and Skeleton Data. In: 2nd International Workshop on Understanding Human Activities through 3D Sensors (UHA3DS'16), Cancun, Mexico, 4 December, 2016, Springer, vol. 10188 LNCS, pp. 29-41, ISBN:978-3-319-91862-4 DOI Accesso ONLINE all'editore

Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Indexing quantized ensembles of exemplar-SVMs with rejecting taxonomies. MULTIMEDIA TOOLS AND APPLICATIONS, pp. 1-22, ISSN:1380-7501 DOI

Lorenzo, Seidenari; Claudio, Baecchi; Tiberio, Uricchio; Andrea, Ferracani; Marco, Bertini; Alberto Del, Bimbo (2017). Deep artwork detection and retrieval for context aware smart audio guides. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS, pp. 0-21, ISSN:1551-6857 DOI

Galteri, Leonardo; Seidenari, Lorenzo; Bertini, Marco; Del Bimbo, Alberto (2017). Spatio-Temporal Closed-Loop Object Detection. IEEE TRANSACTIONS ON IMAGE PROCESSING, pp. 0-0, ISSN:1057-7149 DOI

Ferracani, Andrea; Pezzatini, Daniele; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Natural Interaction in Medical Training. Tools and Applications. Springer International Publishing, ISBN:978-3319610351

Del Bimbo, Alberto; Bertini, Marco; Seidenari, Lorenzo; Uricchio, Tiberio; Baecchi, Claudio; Ferracani, Andrea (2017). Portable computer vision for new "intelligent" audio guides. In: EVA 2017 Florence - Electroning Imaging \& the Visual Arts, Aracne Editrice, pp. 0-0.

Baecchi, Claudio; Uricchio, Tiberio; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Outdoor object recognition for smart audio guides. In: 25th ACM International Conference on Multimedia, MM 2017, Computer History Museum, usa, 2017, Association for Computing Machinery, Inc, pp. 1247-1248, ISBN:9781450349062 DOI

Galteri, Leonardo; Bazazian, Dena; Seidenari, Lorenzo; Bertini, Marco; Andrew D Bagdanov, ; Nicolau, Anguelos; Karatzas, Dimosthenis; Del Bimbo, Alberto (2017). Reading Text in the Wild from Compressed Images. In: International Conference on Computer Vision Workshops, Venezia, IEEE, pp. 0-0, ISBN:978-1-5386-1034-3 DOI

Turchini, Francesco; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Understanding and Localizing Activities from Correspondences of Clustered Trajectories. COMPUTER VISION AND IMAGE UNDERSTANDING, pp. 0-0, ISSN:1077-3142 DOI

Uricchio, Tiberio; Ballan, Lamberto; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Automatic image annotation via label transfer in the semantic space. PATTERN RECOGNITION, vol. 71, pp. 144-157, ISSN:0031-3203 DOI

Leonardo, Galteri; Lorenzo, Seidenari; Marco, Bertini; Alberto Del, Bimbo (2017). Deep Generative Adversarial Compression Artifact Removal. In: International Conference on Computer Vision, Venezia, 22-29 October, IEEE, pp. 4826-4835, ISBN:978-1-5386-1032-9 DOI Accesso ONLINE all'editore

Turchini, Francesco; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). Convex polytope ensembles for spatio-temporal anomaly detection. In: 19th International Conference on Image Analysis and Processing, ICIAP 2017, ita, 2017, Springer Verlag, vol. 10484, pp. 174-184, ISBN:9783319685595 DOI Accesso ONLINE all'editore

Bartoli, Federico; Lisanti, Giuseppe; Seidenari, Lorenzo; Del Bimbo, Alberto (2017). PACE: Prediction-based annotation for crowded environments. In: 17th ACM International Conference on Multimedia Retrieval, ICMR 2017, rou, 2017, Association for Computing Machinery, Inc, pp. 121-124, ISBN:9781450347013 DOI

Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto (2016). Indexing ensembles of exemplar-SVMs with rejecting taxonomies. In: Content-Based Multimedia Indexing (CBMI), 2016 14th International Workshop on, IEEE, pp. 0-0. DOI

Cuffaro, Giovanni; Becattini, Federico; Baecchi, Claudio; Seidenari, Lorenzo; Del Bimbo, Alberto (2016). Segmentation Free Object Discovery in Video. In: Computer Vision – ECCV 2016 Workshops, Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Springer, vol. 9915, pp. 25-31, ISBN:978-3-319-49409-8 DOI Accesso ONLINE all'editore

Bruni, Matteo; Uricchio, Tiberio; Seidenari, Lorenzo; Del Bimbo, Alberto (2016). Do textual descriptions help action recognition?. In: ACM Multimedia, gbr, 2016, Association for Computing Machinery, Inc, pp. 645-649, ISBN:9781450336031 DOI

Taverriti, Giovanni; Lombini, Stefano; Seidenari, Lorenzo; Bertini, Marco; Del Bimbo, Alberto (2016). Real-time wearable computer vision system for improved museum experience. In: 24th ACM Multimedia Conference, MM 2016, gbr, 2016, Association for Computing Machinery, Inc, pp. 703-704, ISBN:9781450336031 DOI

Bartoli, Federico; Lisanti, Giuseppe; Seidenari, Lorenzo; Del Bimbo, Alberto (2016). User interest profiling using tracking-free coarse gaze estimation. In: 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun Center, mex, 2016, Institute of Electrical and Electronics Engineers Inc., pp. 1839-1844, ISBN:9781509048472 DOI Accesso ONLINE all'editore

Seidenari, Lorenzo; Rozza, Alessandro; Del Bimbo, Alberto (2015). Real-Time age estimation from face imagery using fisher vectors. In: 18th International Conference on Image Analysis and Processing, ICIAP 2015, ita, 2015, Springer Verlag, vol. 9280, pp. 172-182, ISBN:9783319232331 DOI Accesso ONLINE all'editore

Turchini, Francesco ; Seidenari, Lorenzo; Del Bimbo, Alberto (2015). Understanding sport activities from correspondences of clustered trajectories. In: 2nd IEEE International Workshop on Computer Vision in Sports (CVsports), Santiago, CHILE, IEEE, pp. 0-0, ISBN:978-1-4673-9711-7

Bartoli, Federico; Lisanti, Giuseppe; Seidenari, Lorenzo; Karaman, Svebor; Del Bimbo, Alberto (2015). MuseumVisitors: a dataset for pedestrian and group detection, gaze estimation and behavior understanding. In: Computer Vision and Pattern Recognition, IEEE, pp. 19-27, ISBN:978-1-4673-6759-2 DOI

Ciolini, Andrea; Seidenari, Lorenzo; Karaman, Svebor; Del Bimbo, Alberto (2015). Efficient hough forest object detection for low-power devices. In: 2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015, ita, 2015, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, ISBN:9781479970797 DOI

Uricchio, Tiberio; Bertini, Marco; Seidenari, Lorenzo; Del Bimbo, Alberto (2015). Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging. In: International Conference on Computer Vision Workshops 2015, IEEE, pp. 9-15, ISBN:978-1-4673-9711-7 DOI

Bartoli, Federico; Seidenari, Lorenzo; Lisanti, Giuseppe; Karaman, Svebor; Del Bimbo, Alberto (2015). WATSS: a Web Annotation Tool for Surveillance Scenarios. In: ACM Multimedia Conference, ACM, pp. 701-704, ISBN:978-1-4503-3459-4

Lorenzo Seidenari; Giuseppe Serra; Andrew D. Bagdanov; and Alberto Del Bimbo (2014). Local Pyramidal Descriptors for Image Recognition. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 36, pp. 1033-1040, ISSN:0162-8828 DOI

Enrico Bondi;Lorenzo Seidenari;Andrew D. Bagdanov;Alberto Del Bimbo (2014). Real-time people counting from depth imagery of crowded environments. In: AVSS, IEEE, pp. 337-342, ISBN:9781479948710 DOI

S. Karaman;L. Seidenari;S. Ma;A. Del Bimbo;S. Sclaroff (2014). Adaptive structured pooling for action recognition. In: BMVC, 2014, British Machine Vision Association, pp. 1-12. Accesso ONLINE all'editore

C. Baecchi*; F. Turchini*; L. Seidenari; A. D. Bagdanov; A. Del Bimbo (2014). Fisher Vectors over Random Density Forest for Object Recognition. In: ICPR, Stockholm, Sweden, ICPR, pp. ---, ISBN:978-1-4799-5209-0 DOI

Andrea Ferracani;Daniele Pezzatini;Lorenzo Seidenari;Alberto Del Bimbo (2014). Natural and virtual environments for the training of emergency medicine personnel. UNIVERSAL ACCESS IN THE INFORMATION SOCIETY, pp. 1-12, ISSN:1615-5289 DOI

Lamberto Ballan; Tiberio Uricchio; Lorenzo Seidenari; Alberto Del Bimbo (2014). A Cross-media Model for Automatic Image Annotation. In: ACM International Conference on Multimedia Retrieval (ICMR), Glasgow, UK, April 1-4, ACM, pp. ---, ISBN:978-1-4503-2782-4

L. Ballan; L. Seidenari; G. Serra; M. Bertini; A. Del Bimbo (2013). Recognizing Human Actions by Using Effective Codebooks and Tracking. In: G. M. Farinella, S. Battiato, R. Cipolla. Advanced Topics in Computer Vision, pp. 65-93, London: Springer-Verlag, ISBN:9781447155195. DOI

L. Seidenari; V. Varano; S. Berretti; A. Del Bimbo; P. Pala (2013). Weakly Aligned Multi-Part Bag-of-Poses for Action Recognition from Depth Cameras. In: International Workshop on Social Behaviour Analyis (SBA'13), Napoli, Italia, 10 Settembre 2013, Springer-Verlag Berlin Heidelberg, vol. 8158, pp. 446-455, ISBN:978-3-642-41189-2 DOI Accesso ONLINE all'editore

Alberto Del Bimbo;Andrea Ferracani;Daniele Pezzatini;Lorenzo Seidenari (2013). A Natural Interface for the Training of Medical Personnel in an Immersive and Virtual Reality System. In: Image Analysis and Processing, Springer, vol. 8156, pp. 763-772, ISBN:9783642411809 DOI

Lorenzo Seidenari;Vincenzo Varano;Stefano Berretti;Alberto Del Bimbo;Pietro Pala (2013). Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses. In: International Conference on Computer Vision and Pattern Recognition, Portland, Oregon, USA, 23-28 June 2013, IEEE, pp. 479-485, ISBN:978-0-7695-4990-3 DOI Accesso ONLINE all'editore

M. Bertini;A. Del Bimbo;L. Seidenari (2012). Multi-scale and real-time non-parametric approach for anomaly detection and localization. COMPUTER VISION AND IMAGE UNDERSTANDING, vol. 116, pp. 320-329, ISSN:1077-3142 DOI

M. Bertini;A. Del Bimbo;L. Seidenari (2012). Scene and crowd behaviour analysis with local space-time descriptors. In: Proc. of 5th International Symposium on Communications, Control, and Signal Processing (ISCCSP), 2012-May, IEEE, pp. 1-6. DOI

Lorenzo Seidenari (2012). Supervised and Semi-supervised Event Detection with Local Spatio-Temporal Features. (Tutor: Alberto Del Bimbo)

A. D. Bagdanov; A. Del Bimbo; L. Seidenari; L. Usai (2012). Real-time hand status recognition from RGB-D imagery. In: International Conference on Pattern Recognition, Novembre 2012, IEEE, pp. 2456-2459. Accesso ONLINE all'editore

L. Ballan;M. Bertini;A. Del Bimbo;L. Seidenari;G. Serra (2012). Effective Codebooks for Human Action Representation and Classification in Unconstrained Videos. IEEE TRANSACTIONS ON MULTIMEDIA, vol. 14:4, pp. 1234-1245, ISSN:1520-9210 DOI

Giovanna Bartoli;Alberto Del Bimbo;Martino Faconti;Andrea Ferracani;Vittoria Marini;Daniele Pezzatini;Lorenzo Seidenari;Felipe Zilleruelo (2012). Emergency medicine training with gesture driven interactive 3D simulations. In: ACM workshop on User experience in e-learning and augmented technologies in education - UXeLATE '12, ACM, pp. 25-29, ISBN:9781450315937 DOI

Costantini, L.; Seidenari, L.; Serra, G.; Del Bimbo, A.; Capodiferro, L. (2011). Space-time Zernike Moments and Pyramid Kernel Descriptors for Action Classification. In: International Conference on Image Analysis and Processing, 2011-September, IAPR, pp. 199-208. Accesso ONLINE all'editore

Lamberto Ballan; Marco Bertini; Alberto Del Bimbo; Lorenzo Seidenari; Giuseppe Serra (2011). Event Detection and Recognition for Semantic Annotation of Video. MULTIMEDIA TOOLS AND APPLICATIONS, vol. 51:1, pp. 279-302, ISSN:1380-7501 DOI

A. D. Bagdanov;M. Bertini;A. Del Bimbo;L. Seidenari (2011). Adaptive Video Compression for Video Surveillance Applications. In: International Symposium on Multimedia, 2011-December, IEEE, pp. 190-197. DOI Accesso ONLINE all'editore

L. Seidenari;M. Bertini;A. D. Bimbo (2010). Dense Spatio-temporal Features For Non-parametric Anomaly Detection And Localization. In: ACM Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS), 2010-Oct, ACM / Association for Computing Machinery:1515 Broadway, 17th Floor:New York, NY 10036:(212)869-7440, EMAIL: acmhelp@hq.acm.org, INTERNET: http://www.acm.org, Fax: (212)944-1318, pp. 27-32.

L. Seidenari;M. Bertini (2010). Non-parametric Anomaly Detection Exploiting Space-time Features. In: ACM International Conference on Multimedia (ACM MM), 2010-Oct, ACM, pp. 1139-1142.

Lamberto Ballan; Marco Bertini; Alberto Del Bimbo; Fabrizio Dini; Giuseppe Lisanti; Lorenzo Seidenari; Giuseppe Serra (2010). Recent research activities in videosurveillance at UNIFI:MICC. In: Convegno del Gruppo Italiano Ricercatori in Pattern Recognition (GIRPR), Marina di Ascea (SA), Itally, -, pp. ---.

Lamberto Ballan;Marco Bertini;Alberto Del Bimbo;Lorenzo Seidenari;Giuseppe Serra (2009). Effective Codebooks for Human Action Categorization. In: IEEE International Conference on Computer Vision - VOEC Workshop, Kyoto, Japan, September 27, IEEE, pp. 506-513. DOI

Lamberto Ballan;Marco Bertini;Alberto Del Bimbo;Lorenzo Seidenari;Giuseppe Serra (2009). Recognizing Human Actions by Fusing Spatio-temporal Appearance and Motion Descriptors. In: IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 7-12, IEEE, pp. 3569-3572. DOI

L. Ballan;M. Bertini;A. Del Bimbo;L. Seidenari;G. Serra (2009). Human Action Recognition and Localization using Spatio-temporal Descriptors and Tracking. In: AI*IA International Workshop on Pattern Recognition and Artificial Intelligence for Human Behaviour Analysis (PRAI*HBA), 2009-Dec, Reggio Emilia, Italy:, AI*IA, pp. 1-8.

Lorenzo SEIDENARI

Biography

Lorenzo Seidenari graduated in Computer Engineering in 2008 and obtained a Ph.D. in Computer Engineering, Multimedia, and Telecommunications in 2012 with a dissertation on supervised and semi-supervised event recognition using space-time local descriptors. In 2013, he was a visiting scholar at the University of Michigan. From 2012 to 2018, he was a research fellow at the Media Integration and Communication Center. He held the position of Fixed-Term Researcher (a) from 2018 to 2020 and subsequently of Fixed-Term Researcher (b). In 2018, he obtained the National Scientific Qualification for Associate Professor in the fields 09/H1 and 01/B1.

In 2019, he co-founded the university spin-off SmallPixels.

In 2021, he was appointed an ELLIS Scholar.

Since 2023, he has been an Associate Professor in Information Processing Systems (IINF/05) and teaches Fundamentals of Computer Programming in the Bachelor's Degree programs in Mechanical and Management Engineering, as well as Generative Models and Deep Learning Applications in the Master's Degree program in Artificial Intelligence.

Lorenzo SEIDENARI

Curriculum

Lorenzo Seidenari is an Associate Professor at the University of Florence. Previously he was a Postdoc researcher at Media Integration and Communication Center of the University of Florence. He received his Ph.D. degree in computer engineering in 2012 from the University of Florence. His research focuses on object and action recognition in video and images using deep learning.

He has been in the organizing committee of ACM MM 2010, ECCV 2012, CBMI 2017. He is a reviewer for several international conferences: CBMI, ICIAP, ACM MM, CAIP, CIARP, IEEE CVPR, IEEE ECCV, IEEE ICME, IAPR ICPR, WIAMIS, ICVS, AVSS. He frequently serves as a reviewer for several prestigious journals: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Human Machine Systems (THMS), IEEE Transactions on Circuit and Systems for Video Technology(TCSVT), IEEE Transactions on Cybernetics (TCYB), ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Pattern Recognition Letters (PRL), Computer Vision and Image Understanding (CVIU), Pattern Recognition (PR), Multimedia Tools and Applications (MTAP), Pattern Analysis and Applications (PAAA).

He frequently serves as Area Chair for ACM Multimedia and British Machine Vision Conference.

He is an Associate Editor for IEEE Transactions of Multimedia and Elsevier Pattern Recognition.

He is in the Commitee of the PhD program in Information Engineering. He has taught a PhD level class at the Smart Computing and Computer Engineering PhD Schools on image recognition. He advised, 8 Phd, 20 Msc and 7 Bsc students.

He is author 25+ journal papers and more than 50 peer-reviewed conference papers.

According to Google Scholar his publication have 3134 Citations with an H-Index of 29 (https://scholar.google.com/citations?user=mBMXVPAAAAAJ&hl=en&oi=ao)