{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T16:56:02Z","timestamp":1767372962901,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031258244"},{"type":"electronic","value":"9783031258251"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25825-1_22","type":"book-chapter","created":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T19:02:52Z","timestamp":1675450972000},"page":"301-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Small Visual Object Detection in Smart Waste Classification Using Transformers with Deep Learning"],"prefix":"10.1007","author":[{"given":"Jianchun","family":"Qi","sequence":"first","affiliation":[]},{"given":"Minh","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Wei Qi","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,4]]},"reference":[{"key":"22_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv (2020)"},{"key":"22_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-46493-0_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Cai","year":"2016","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354\u2013370. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22"},{"key":"22_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"22_CR4","doi-asserted-by":"publisher","first-page":"137193","DOI":"10.1016\/j.scitotenv.2020.137193","volume":"717","author":"SS Chen","year":"2020","unstructured":"Chen, S.S., et al.: Carbon emissions under different domestic waste treatment modes induced by garbage classification: case study in pilot communities in Shanghai, China. Sci. Total Environ. 717, 137193 (2020)","journal-title":"Sci. Total Environ."},{"issue":"4","key":"22_CR5","doi-asserted-by":"publisher","first-page":"2300","DOI":"10.1109\/TCYB.2020.3004636","volume":"52","author":"L Cui","year":"2022","unstructured":"Cui, L., et al.: Context-aware block net for small object detection. IEEE Trans. Cybern. 52(4), 2300\u20132313 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE CVPR, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"22_CR7","unstructured":"Dosovitskiy, A.,et al.: An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. arXiv (2020)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: IEEE CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Kisantal, M., Wojna, Z., Murawski, J., Naruniec, J., Cho, K.: Augmentation for small object detection. arXiv (2019)","DOI":"10.5121\/csit.2019.91713"},{"key":"22_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1\u20139 (2012)"},{"issue":"5","key":"22_CR13","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2016","unstructured":"Li, J., et al.: Attentive contexts for object detection. IEEE Trans. Multimed. 19(5), 944\u2013954 (2016). https:\/\/doi.org\/10.1109\/TMM.2016.2642789","journal-title":"IEEE Trans. Multimed."},{"key":"22_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H.Z., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie. S.N.: A ConvNet for the 2020s. arXiv (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"22_CR16","unstructured":"Li, Z., Zhou, F.: FSSD: feature fusion single shot multibox detector. arXiv:1712.00960 (2017)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Z., Nguyen, M., Yan, W.: Sailboat detection based on automated search attention mechanism and deep learning models. In: IEEE IVCNZ (2021)","DOI":"10.1109\/IVCNZ54163.2021.9653237"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Nie, Z.F., Duan, W.J., Li, X.D.: Domestic garbage recognition and detection based on Faster R-CNN. In: Journal of Physics: Conference Series (2021)","DOI":"10.1088\/1742-6596\/1738\/1\/012089"},{"issue":"12","key":"22_CR19","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2017","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2017)","journal-title":"Trends Cogn. Sci."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Pan, C., Yan, W.: A learning-based positive feedback in salient object detection. In: IEEE IVCNZ (2018)","DOI":"10.1109\/IVCNZ.2018.8634717"},{"issue":"27-28","key":"22_CR21","doi-asserted-by":"publisher","first-page":"19925","DOI":"10.1007\/s11042-020-08866-x","volume":"79","author":"C Pan","year":"2020","unstructured":"Pan, C., Yan, W.Q.: Object detection based on saturation of visual perception. Multimed. Tools Appl. 79(27\u201328), 19925\u201319944 (2020). https:\/\/doi.org\/10.1007\/s11042-020-08866-x","journal-title":"Multimed. Tools Appl."},{"key":"22_CR22","doi-asserted-by":"publisher","first-page":"4773","DOI":"10.1109\/TIP.2021.3074796","volume":"30","author":"C Pan","year":"2021","unstructured":"Pan, C., Liu, J., Yan, W., Zhou, Y.: Salient object detection based on visual perceptual saturation and two-stream hybrid networks. IEEE Trans. Image Process. 30, 4773\u20134787 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Qi, J., Nguyen, M., Yan, W.: Waste classification from digital images using ConvNeXt. In: PSIVT (2022)","DOI":"10.1007\/978-3-031-26431-3_1"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE CVPR, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Shen, D., Xin, C., Nguyen, M., Yan, W.: Flame detection using deep learning. In: ICCAR (2018)","DOI":"10.1109\/ICCAR.2018.8384711"},{"key":"22_CR28","unstructured":"Vaswani, A.,et al.: Attention is all you need. In: NIPS (2019)"},{"key":"22_CR29","unstructured":"Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using DropConnect. In: ICML, pp. 1058\u20131066 (2013)"},{"key":"22_CR30","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1093\/aob\/mcg029","volume":"91","author":"X Yin","year":"2002","unstructured":"Yin, X., Goudriaan, J.A.N., Lantinga, E.A., Vos, J.A.N., Spiertz, H.J.: A flexible sigmoid function of determinate growth. Ann. Bot. 91, 361\u2013371 (2002)","journal-title":"Ann. Bot."},{"key":"22_CR31","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-030-72073-5_5","volume-title":"Geometry and Vision","author":"B Xiao","year":"2021","unstructured":"Xiao, B., Nguyen, M., Yan, W.Q.: Apple ripeness identification using deep learning. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) ISGV 2021. CCIS, vol. 1386, pp. 53\u201367. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72073-5_5"},{"key":"22_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61081-4","volume-title":"Computational Methods for Deep Learning \u2013 Theoretic, Practice and Applications","author":"WQ Yan","year":"2021","unstructured":"Yan, W.Q.: Computational Methods for Deep Learning \u2013 Theoretic, Practice and Applications. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-030-61081-4"},{"key":"22_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10713-0","volume-title":"Introduction to Intelligent Surveillance - Surveillance Data Capture, Transmission, and Analytics","author":"WQ Yan","year":"2019","unstructured":"Yan, W.Q.: Introduction to Intelligent Surveillance - Surveillance Data Capture, Transmission, and Analytics, 3rd edn. Springer, Heidelberg (2019). https:\/\/doi.org\/10.1007\/978-3-030-10713-0","edition":"3"},{"key":"22_CR34","unstructured":"Yu, F., Koltun, V.: Multiscale context aggregation by dilated convolutions. In: ICLR (2016)"}],"container-title":["Lecture Notes in Computer Science","Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25825-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T15:59:37Z","timestamp":1728835177000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25825-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031258244","9783031258251"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25825-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IVCNZ","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Vision Computing New Zealand","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ivcnz2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ivcnz2022.aut.ac.nz\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","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":"14","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":"23","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":"18% - 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":"2.7","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":"3.1","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}