{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:10:34Z","timestamp":1773414634066,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031064296","type":"print"},{"value":"9783031064302","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06430-2_22","type":"book-chapter","created":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T08:03:16Z","timestamp":1652688196000},"page":"263-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Weakly Supervised Attended Object Detection Using Gaze Data as\u00a0Annotations"],"prefix":"10.1007","author":[{"given":"Michele","family":"Mazzamuto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Ragusa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Signorello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Bearman, A.L., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What\u2019s the point: semantic segmentation with point supervision. In: European Conference on Computer Vision, pp. 549\u2013565 (2016)","DOI":"10.1007\/978-3-319-46478-7_34"},{"issue":"4","key":"22_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, B., Parkhi, O., Kirillov, A.: Pointly-supervised instance segmentation. arXiv preprint arXiv:2104.06404 (2021)","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"22_CR4","unstructured":"Chiaro, R.D., Bagdanov, A.D., Bimbo, A.: Noisyart: a dataset for webly-supervised artwork recognition. In: International Conference on Computer Vision Theory and Applications (2019)"},{"issue":"8","key":"22_CR5","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. Trans. Pattern Anal. Mach. Intell. 35(8), 1915\u20131929 (2013)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR6","unstructured":"Farhadi, A., Redmon, J.: Yolov3: an incremental improvement. In: Computer Vision and Pattern Recognition, vol. 1804 (2018)"},{"issue":"11","key":"22_CR7","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1109\/TPAMI.2020.2992889","volume":"43","author":"A Furnari","year":"2021","unstructured":"Furnari, A., Farinella, G.: Rolling-unrolling LSTMs for action anticipation from first-person video. Trans. Pattern Anal. Mach. Intell. 43(11), 4021\u20134036 (2021)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-319-46604-0_34","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"A Furnari","year":"2016","unstructured":"Furnari, A., Farinella, G.M., Battiato, S.: Temporal segmentation of egocentric videos to highlight personal locations of interest. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 474\u2013489. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_34"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Garcia, N., et al.: A dataset and baselines for visual question answering on art. In: European Conference on Computer Vision Workshops, pp. 92\u2013108 (2020)","DOI":"10.1007\/978-3-030-66096-3_8"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: European Conference on Computer Vision, pp. 297\u2013312 (2014)","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"22_CR14","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/jimaging8020018","volume":"8","author":"BIE Ibrahim","year":"2022","unstructured":"Ibrahim, B.I.E., Eyharabide, V., Le Page, V., Billiet, F.: Few-shot object detection: application to medieval musicological studies. J. Imaging 8(2), 18 (2022)","journal-title":"J. Imaging"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Joyce, J.M.: Kullback-Leibler Divergence, pp. 720\u2013722. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-04898-2_327","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Karthikeyan, S., Jagadeesh, V., Shenoy, R., Ecksteinz, M., Manjunath, B.: From where and how to what we see. In: International Conference on Computer Vision, pp. 625\u2013632 (2013)","DOI":"10.1109\/ICCV.2013.83"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Karthikeyan, S., Ngo, T., Eckstein, M., Manjunath, B.: Eye tracking assisted extraction of attentionally important objects from videos. In: Computer Vision and Pattern Recognition, pp. 3241\u20133250 (2015)","DOI":"10.1109\/CVPR.2015.7298944"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Tas, Y., Zhang, H., Harandi, M., Porikli, F., Zhang, R.: Museum exhibit identification challenge for the supervised domain adaptation and beyond. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01270-0_48"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Hou, X., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation. In: Computer Vision and Pattern Recognition), pp. 280\u2013287 (2014)","DOI":"10.1109\/CVPR.2014.43"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Transactions on Pattern Analysis and Machine Intelligence (2020)","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: Single shot multibox detector. In: European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Mishra, A., Aloimonos, Y., Fah, C.L.: Active segmentation with fixation. In: International Conference on Computer Vision, pp. 468\u2013475 (2009)","DOI":"10.1109\/ICCV.2009.5459254"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D.P., Clarke, A.D.F., Keller, F., Ferrari, V.: Training object class detectors from eye tracking data. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_24"},{"key":"22_CR25","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.culher.2021.01.002","volume":"48","author":"R Pathak","year":"2021","unstructured":"Pathak, R., Saini, A., Wadhwa, A., Sharma, H., Sangwan, D.: An object detection approach for detecting damages in heritage sites using 3-d point clouds and 2-d visual data. J. Cult. Herit. 48, 74\u201382 (2021)","journal-title":"J. Cult. Herit."},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Furnari, A., Battiato, S., Signorello, G., Farinella, G.M.: Egocentric point of interest recognition in cultural sites. In: International Conference on Computer Vision Theory and Applications (VISAPP) (2019)","DOI":"10.5220\/0007365503810392"},{"key":"22_CR27","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.patrec.2019.12.016","volume":"131","author":"F Ragusa","year":"2020","unstructured":"Ragusa, F., Furnari, A., Battiato, S., Signorello, G., Farinella, G.M.: EGO-CH: dataset and fundamental tasks for visitors behavioral understanding using egocentric vision. Pattern Recogn. Lett. 131, 150\u2013157 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"22_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"22_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3092832","volume":"13","author":"L Seidenari","year":"2017","unstructured":"Seidenari, L., Baecchi, C., Uricchio, T., Ferracani, A., Bertini, M., Bimbo, A.D.: Deep artwork detection and retrieval for automatic context-aware audio guides. Trans. Multim. Comput. Commun. Appl. 13, 1\u201321 (2017)","journal-title":"Trans. Multim. Comput. Commun. Appl."},{"key":"22_CR31","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. Trans. Pattern Anal. Mach. Intell. 39, 640\u2013651 (2017)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Subramanian, R., Yanulevskaya, V., Sebe, N.: Can computers learn from humans to see better? inferring scene semantics from viewers\u2019 eye movements. In: International Conference on Multimedia (ACM), pp. 33\u201342 (2011)","DOI":"10.1145\/2072298.2072305"},{"key":"22_CR33","doi-asserted-by":"publisher","first-page":"2876","DOI":"10.1109\/TIP.2021.3055632","volume":"30","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Hou, J., Hou, X., Chau, L.P.: A self-training approach for point-supervised object detection and counting in crowds. Trans. Image Process. 30, 2876\u20132887 (2021)","journal-title":"Trans. Image Process."},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Yoo, I., Yoo, D., Paeng, K.: Pseudoedgenet: nuclei segmentation only with point annotations. In: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 731\u2013739 (2019)","DOI":"10.1007\/978-3-030-32239-7_81"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Yun, K., Peng, Y., Samaras, D., Zelinsky, G.J., Berg, T.L.: Studying relationships between human gaze, description, and computer vision. In: Computer Vision and Pattern Recognition, pp. 739\u2013746 (2013)","DOI":"10.1109\/CVPR.2013.101"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06430-2_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:47:43Z","timestamp":1710337663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06430-2_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031064296","9783031064302"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06430-2_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 May 2022","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":"Lecce","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2021.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"168","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}