{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:49:42Z","timestamp":1767314982329,"version":"3.48.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101914","type":"print"},{"value":"9783032101921","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-10192-1_31","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:45:51Z","timestamp":1767314751000},"page":"376-388","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ego and\u00a0Exo Views for\u00a0an\u00a0Object-Level Human Behavior Analysis and\u00a0Understanding Through Tracking in\u00a0Retail Spaces"],"prefix":"10.1007","author":[{"given":"Alessandro Sebastiano","family":"Catinello","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1672-667X","authenticated-orcid":false,"given":"Matteo","family":"Dunnhofer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6034-0432","authenticated-orcid":false,"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8893-9244","authenticated-orcid":false,"given":"Emanuele","family":"Frontoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6911-0302","authenticated-orcid":false,"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4503-7483","authenticated-orcid":false,"given":"Christian","family":"Micheloni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5523-7174","authenticated-orcid":false,"given":"Marina","family":"Paolanti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4343-7555","authenticated-orcid":false,"given":"Rocco","family":"Pietrini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devis","family":"Salierno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9341-7651","authenticated-orcid":false,"given":"Lorenzo","family":"Stacchio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6329-3500","authenticated-orcid":false,"given":"Asfand","family":"Yaar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"31_CR1","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N.: End-to-end object detection with transformers. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"31_CR3","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/s11263-022-01694-6","volume":"131","author":"M Dunnhofer","year":"2023","unstructured":"Dunnhofer, M., Furnari, A., Farinella, G.M., Micheloni, C.: Visual object tracking in first person vision. Int. J. Comput. Vision 131(1), 259\u2013283 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Dunnhofer, M., Simonato, K., Micheloni, C.: Combining complementary trackers for enhanced long-term visual object tracking. Image Vis. Comput. 122, 104448 (2022)","DOI":"10.1016\/j.imavis.2022.104448"},{"key":"31_CR5","unstructured":"Grauman, K., et\u00a0al.: Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"31_CR6","unstructured":"Grauman, K., et\u00a0al.: Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"31_CR7","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"31_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"31_CR9","unstructured":"Kristan, M., et\u00a0al.: The first visual object tracking segmentation vots2023 challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1796\u20131818 (2023)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Nguyen, T.D., et al.: Retail store customer behavior analysis system: design and implementation. In: IFIP International Conference on Artificial Intelligence Applications and Innovations, pp. 305\u2013318. Springer (2024)","DOI":"10.1007\/978-3-031-63223-5_23"},{"key":"31_CR11","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10846-017-0674-7","volume":"91","author":"M Paolanti","year":"2018","unstructured":"Paolanti, M., Liciotti, D., Pietrini, R., Mancini, A., Frontoni, E.: Modelling and forecasting customer navigation in intelligent retail environments. J. Intell. Robot. Syst. 91, 165\u2013180 (2018)","journal-title":"J. Intell. Robot. Syst."},{"key":"31_CR12","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.patrec.2022.07.011","volume":"161","author":"M Paolanti","year":"2022","unstructured":"Paolanti, M., Pierdicca, R., Pietrini, R., Martini, M., Frontoni, E.: Sesame: re-identification-based ambient intelligence system for museum environment. Pattern Recogn. Lett. 161, 17\u201323 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"31_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-020-01118-w","volume":"31","author":"M Paolanti","year":"2020","unstructured":"Paolanti, M., Pietrini, R., Mancini, A., Frontoni, E., Zingaretti, P.: Deep understanding of shopper behaviours and interactions using RGB-d vision. Mach. Vis. Appl. 31, 1\u201321 (2020)","journal-title":"Mach. Vis. Appl."},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Pazzaglia, G., et al.: People counting on low cost embedded hardware during the sars-cov-2 pandemic. In: Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10\u201315, 2021, Proceedings, Part II, pp. 521\u2013533. Springer (2021)","DOI":"10.1007\/978-3-030-68790-8_41"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Putra, P.U., Shima, K., Shimatani, K.: A deep neural network model for multi-view human activity recognition. PLoS ONE 17(1), e0262181 (2022)","DOI":"10.1371\/journal.pone.0262181"},{"key":"31_CR16","unstructured":"Ravi, N., et\u00a0al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Rodin, I., Furnari, A., Mavroeidis, D., Farinella, G.M.: Predicting the future from first person (egocentric) vision: A survey. Comput. Vis. Image Underst. 211, 103252 (2021)","DOI":"10.1016\/j.cviu.2021.103252"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Rodin, I., Furnari, A., Min, K., Tripathi, S., Farinella, G.M.: Action scene graphs for long-form understanding of egocentric videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18622\u201318632 (2024)","DOI":"10.1109\/CVPR52733.2024.01762"},{"issue":"23","key":"31_CR19","doi-asserted-by":"publisher","first-page":"4730","DOI":"10.3390\/electronics13234730","volume":"13","author":"M Shili","year":"2024","unstructured":"Shili, M., Jayasingh, S., Hammedi, S.: Advanced customer behavior tracking and heatmap analysis with yolov5 and deepsort in retail environment. Electronics 13(23), 4730 (2024)","journal-title":"Electronics"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1961\u20131970 (2016)","DOI":"10.1109\/CVPR.2016.216"},{"issue":"12","key":"31_CR21","doi-asserted-by":"publisher","first-page":"6283","DOI":"10.1007\/s00521-024-09422-6","volume":"36","author":"W Wei","year":"2024","unstructured":"Wei, W., Cheng, Y., He, J., Zhu, X.: A review of small object detection based on deep learning. Neural Comput. Appl. 36(12), 6283\u20136303 (2024)","journal-title":"Neural Comput. Appl."},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Yan, B.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3702\u20133712 (2019)","DOI":"10.1109\/ICCV.2019.00380"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10192-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:45:53Z","timestamp":1767314753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10192-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101914","9783032101921"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10192-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}