{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T10:08:40Z","timestamp":1774606120527,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031264306","type":"print"},{"value":"9783031264313","type":"electronic"}],"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\/978-3-031-26431-3_1","type":"book-chapter","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T18:13:33Z","timestamp":1682619213000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Waste Classification from Digital Images Using ConvNeXt"],"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":[[2023,4,28]]},"reference":[{"key":"1_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, M.Y.: YOLOv4: optimal speed and accuracy of object detection. arXiv (2020)"},{"key":"1_CR2","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":"1_CR3","doi-asserted-by":"publisher","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."},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv (2020)"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.wasman.2020.09.032","volume":"119","author":"OL Funch","year":"2021","unstructured":"Funch, O.L., Marhaug, R., Kohtala, S., Steinert, M.: Detecting glass and metal in consumer trash bags during waste collection using convolutional neural networks. Waste Manag. 119, 30\u201338 (2021)","journal-title":"Waste Manag."},{"issue":"11","key":"1_CR7","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665\u2013673 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. IEEE ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1_CR9","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":"1_CR10","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv (2016)"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Ji, H., Liu, Z., Yan, W.Q., Klette, R.: Early diagnosis of Alzheimer\u2019s disease based on selective kernel network with spatial attention. In: Palaiahnakote, S., Sanniti di Baja, G., Wang, L., Yan, W. (eds.) Pattern Recognition. ACPR 2019. LNCS, vol. 12047, pp. 503\u2013515. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-41299-9_39","DOI":"10.1007\/978-3-030-41299-9_39"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Ji, H., Liu, Z., Yan, W., Klette, R.: Early diagnosis of Alzheimer\u2019s disease using deep learning. ACM ICCCV (2019)","DOI":"10.1145\/3341016.3341024"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"140019","DOI":"10.1109\/ACCESS.2020.3010496","volume":"8","author":"Z Kang","year":"2020","unstructured":"Kang, Z., Yang, J., Li, G.L., Zhang, Z.Y.: An automatic garbage classification system based on deep learning. IEEE Access. 8, 140019\u2013140029 (2020)","journal-title":"IEEE Access."},{"key":"1_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Liang, S., Yan, W.: A hybrid CTC+Attention model based on end-to-end framework for multilingual speech recognition. Multimed. Tools Appl. 81, 41295\u201341308 (2022)","DOI":"10.1007\/s11042-022-12136-3"},{"key":"1_CR16","doi-asserted-by":"publisher","unstructured":"Liu, X., Neuyen, M., Yan, W.Q.: Vehicle-related scene understanding using deep learning. In: Cree, M., Huang, F., Yuan, J., Yan, W. (eds.) Pattern Recognition. ACPR 2019. Communications in Computer and Information Science, vol. 1180, pp. 61\u201373. Springer, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-3651-9_7","DOI":"10.1007\/978-981-15-3651-9_7"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR18","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":"1_CR19","doi-asserted-by":"crossref","unstructured":"Luo, Z., Nguyen, M., Yan, W.: Kayak and sailboat detection based on the improved YOLO with transformer. ACM ICCCV (2022)","DOI":"10.1145\/3561613.3561619"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Luo, Z., Nguyen, M., Yan,W.: Sailboat detection based on automated search attention mechanism and deep learning models. IEEE IVCNZ (2021)","DOI":"10.1109\/IVCNZ54163.2021.9653237"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Nie, Z.F., Duan, W.J., Li, X.D.: Domestic garbage recognition and detection based on Faster R-CNN. J. Phys. Conf. Ser. 1738(1), 012089 (2021). https:\/\/doi.org\/10.1088\/1742-6596\/1738\/1\/012089","DOI":"10.1088\/1742-6596\/1738\/1\/012089"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Nixon, M., Aguado, A.: Feature Extraction and Image Processing for Computer Vision. Academic Press, Cambridge (2019)","DOI":"10.1016\/B978-0-12-814976-8.00003-8"},{"issue":"27-28","key":"1_CR23","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":"1_CR24","doi-asserted-by":"publisher","first-page":"4773","DOI":"10.1109\/TIP.2021.3074796","volume":"30","author":"C Pan","year":"2022","unstructured":"Pan, C., Liu, J., Yan, W., et al.: Salient object detection based on visual perceptual saturation and two-stream hybrid networks. IEEE Trans. Image Process. 30, 4773\u20134787 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Pan, C., Yan, W.: A learning-based positive feedback in salient object detection. In: IVCNZ, pp. 311\u2013317 (2018)","DOI":"10.1109\/IVCNZ.2018.8634717"},{"key":"1_CR26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511996504","volume-title":"Computer Vision: Models, Learning, and Inference","author":"SJ Prince","year":"2012","unstructured":"Prince, S.J.: Computer Vision: Models, Learning, and Inference. Cambridge University Press, Cambridge (2012)"},{"key":"1_CR27","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI 1(8), 9 (2019)"},{"key":"1_CR28","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":"1_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. NIPS 28 (2015)"},{"key":"1_CR30","doi-asserted-by":"publisher","first-page":"114516","DOI":"10.1016\/j.eswa.2020.114516","volume":"173","author":"A Sakalle","year":"2021","unstructured":"Sakalle, A., Tomar, P., Bhardwaj, H., Acharya, D., Bhardwaj, A.: A LSTM based deep learning network for recognizing emotions using wireless brainwave driven system. Expert Syst. Appl. 173, 114516 (2021)","journal-title":"Expert Syst. Appl."},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Shen, D., Xin, C., Nguyen, M., Yan, W.: Flame detection using deep learning. In: International Conference on Control, Automation and Robotics (2018)","DOI":"10.1109\/ICCAR.2018.8384711"},{"key":"1_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2014)"},{"key":"1_CR33","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Geoffrey, H., Alex, K., Ilya, S., Ruslan, S.: Dropout: a simple way to prevent neural networks from overfitting. J. Mac. Lear. 15, 1929\u20131958 (2014)","journal-title":"J. Mac. Lear."},{"key":"1_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2019)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1_CR36","doi-asserted-by":"publisher","unstructured":"Xiao, B., Nguyen, M., Yan, W.Q.: Apple ripeness identification using deep learning. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) Geometry and Vision. ISGV 2021. Communications in Computer and Information Science, vol. 1386, pp. 53\u201367. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72073-5_5","DOI":"10.1007\/978-3-030-72073-5_5"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Xin, C., Nguyen, M., Yan, W.: Multiple flames recognition using deep learning. In: Handbook of Research on Multimedia Cyber Security, pp. 296\u2013307 (2020)","DOI":"10.4018\/978-1-7998-2701-6.ch015"},{"key":"1_CR38","doi-asserted-by":"publisher","unstructured":"Yan, W.Q.: Computational Methods for Deep Learning - Theoretic. Practice and Applications. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-030-61081-4","DOI":"10.1007\/978-3-030-61081-4"},{"key":"1_CR39","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-10713-0"}],"container-title":["Lecture Notes in Computer Science","Image and Video Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26431-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T16:37:48Z","timestamp":1702312668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26431-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264306","9783031264313"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26431-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"28 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PSIVT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Rim Symposium on Image and Video Technology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"psivt2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cis-ram.org\/psivt2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}