{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:20:45Z","timestamp":1771950045779,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031928048","type":"print"},{"value":"9783031928055","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-92805-5_22","type":"book-chapter","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T12:59:24Z","timestamp":1747918764000},"page":"342-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Temporal-Consistent CAMs for\u00a0Weakly Supervised Video Segmentation in\u00a0Waste Sorting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4418-110X","authenticated-orcid":false,"given":"Andrea","family":"Marelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0598-8279","authenticated-orcid":false,"given":"Luca","family":"Magri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0331-4032","authenticated-orcid":false,"given":"Federica","family":"Arrigoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1650-3054","authenticated-orcid":false,"given":"Giacomo","family":"Boracchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","unstructured":"Adeyinka, A.A., Adebiyi, M.O., Akande, N.O., Ogundokun, R.O., Kayode, A.A., Oladele, T.O.: A deep convolutional encoder-decoder architecture for retinal blood vessels segmentation. In: Misra, S., et al. (eds.) ICCSA 2019, Part V. LNCS, vol. 11623, pp. 180\u2013189. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-24308-1_15","DOI":"10.1007\/978-3-030-24308-1_15"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bashkirova, D., et al.: ZeroWaste dataset: towards deformable object segmentation in cluttered scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21147\u201321157 (2022)","DOI":"10.1109\/CVPR52688.2022.02047"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Belharbi, S., Ben\u00a0Ayed, I., McCaffrey, L., Granger, E.: TCAM: temporal class activation maps for object localization in weakly-labeled unconstrained videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 137\u2013146 (2023)","DOI":"10.1109\/WACV56688.2023.00022"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Belharbi, S., Murtaza, S., Pedersoli, M., Ayed, I.B., McCaffrey, L., Granger, E.: CoLo-CAM: class activation mapping for object co-localization in weakly-labeled unconstrained videos. arXiv preprint arXiv:2303.09044 (2023)","DOI":"10.1109\/WACV56688.2023.00022"},{"key":"22_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-319-46448-0_23","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Caesar","year":"2016","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Region-based semantic segmentation with end-to-end training. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 381\u2013397. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_23"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1635\u20131643 (2015)","DOI":"10.1109\/ICCV.2015.191"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Convolutional feature masking for joint object and stuff segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3992\u20134000 (2015)","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"22_CR9","doi-asserted-by":"publisher","unstructured":"Fan, J., Cui, L., Fei, S.: Waste detection system based on data augmentation and YOLO EC. Sensors 23(7) (2023). https:\/\/doi.org\/10.3390\/s23073646. https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3646","DOI":"10.3390\/s23073646"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"22_CR11","doi-asserted-by":"publisher","unstructured":"Gundupalli, S.P., Hait, S., Thakur, A.: A review on automated sorting of source-separated municipal solid waste for recycling. Waste Manage. 60, 56\u201374 (2017). https:\/\/doi.org\/10.1016\/j.wasman.2016.09.015. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0956053X16305189, special Thematic Issue: Urban Mining and Circular Economy","DOI":"10.1016\/j.wasman.2016.09.015"},{"key":"22_CR12","doi-asserted-by":"publisher","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"22_CR13","unstructured":"Hong, J., Fulton, M.S., Sattar, J.: TrashCan 1.0 an instance-segmentation labeled dataset of trash observations (2020)"},{"key":"22_CR14","unstructured":"Hou, Q., Jiang, P., Wei, Y., Cheng, M.M.: Self-erasing network for integral object attention. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Wang, J., Liu, W., Wang, J.: Weakly-supervised semantic segmentation network with deep seeded region growing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7014\u20137023 (2018)","DOI":"10.1109\/CVPR.2018.00733"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Jin, B., Ortiz\u00a0Segovia, M.V., Susstrunk, S.: Webly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3626\u20133635 (2017)","DOI":"10.1109\/CVPR.2017.185"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Jo, S., Yu, I.J.: Puzzle-CAM: improved localization via matching partial and full features. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 639\u2013643. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506058"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 876\u2013885 (2017)","DOI":"10.1109\/CVPR.2017.181"},{"key":"22_CR19","doi-asserted-by":"publisher","unstructured":"Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 695\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_42","DOI":"10.1007\/978-3-319-46493-0_42"},{"issue":"2","key":"22_CR20","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MRA.2021.3066040","volume":"28","author":"M Koskinopoulou","year":"2021","unstructured":"Koskinopoulou, M., Raptopoulos, F., Papadopoulos, G., Mavrakis, N., Maniadakis, M.: Robotic waste sorting technology: toward a vision-based categorization system for the industrial robotic separation of recyclable waste. IEEE Robot. Autom. Mag. 28(2), 50\u201360 (2021). https:\/\/doi.org\/10.1109\/MRA.2021.3066040","journal-title":"IEEE Robot. Autom. Mag."},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Kumsetty, N.V., Nekkare, A.B., Kamath, S., et\u00a0al.: Trashbox: trash detection and classification using quantum transfer learning. In: 2022 31st Conference of Open Innovations Association (FRUCT), pp. 125\u2013130. IEEE (2022)","DOI":"10.23919\/FRUCT54823.2022.9770922"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., Yoon, S.: FickleNet: weakly and semi-supervised semantic image segmentation using stochastic inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5267\u20135276 (2019)","DOI":"10.1109\/CVPR.2019.00541"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., Yoon, S.: Frame-to-frame aggregation of active regions in web videos for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6808\u20136818 (2019)","DOI":"10.1109\/ICCV.2019.00691"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., Sun, J.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3159\u20133167 (2016)","DOI":"10.1109\/CVPR.2016.344"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1742\u20131750 (2015)","DOI":"10.1109\/ICCV.2015.203"},{"key":"22_CR27","unstructured":"Proen\u00e7a, P.F., Simoes, P.: TACO: trash annotations in context for litter detection. arXiv preprint arXiv:2003.06975 (2020)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Ferrer, A., Gallego, A.J., Valero-Mas, J.J., Calvo-Zaragoza, J.: The CleanSea Set: a benchmark corpus for underwater debris detection and recognition. In: Iberian Conference on Pattern Recognition and Image Analysis, pp. 616\u2013628. Springer (2022)","DOI":"10.1007\/978-3-031-04881-4_49"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"22_CR30","first-page":"13927","volume":"33","author":"D Shen","year":"2020","unstructured":"Shen, D., Ji, Y., Li, P., Wang, Y., Lin, D.: RANet: region attention network for semantic segmentation. Adv. Neural. Inf. Process. Syst. 33, 13927\u201313938 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Shimoda, W., Yanai, K.: Self-supervised difference detection for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5208\u20135217 (2019)","DOI":"10.1109\/ICCV.2019.00531"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., Wang, L.: Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3136\u20133145 (2019)","DOI":"10.1109\/CVPR.2019.00325"},{"key":"22_CR33","doi-asserted-by":"publisher","unstructured":"Sun, G., Wang, W., Dai, J., Van Gool, L.: Mining cross-image semantics for weakly supervised semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 347\u2013365. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_21","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Tang, M., Djelouah, A., Perazzi, F., Boykov, Y., Schroers, C.: Normalized cut loss for weakly-supervised CNN segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1818\u20131827 (2018)","DOI":"10.1109\/CVPR.2018.00195"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Vernaza, P., Chandraker, M.: Learning random-walk label propagation for weakly-supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7158\u20137166 (2017)","DOI":"10.1109\/CVPR.2017.315"},{"key":"22_CR36","first-page":"15220","volume":"33","author":"J Wang","year":"2020","unstructured":"Wang, J., Zhong, Y., Dai, Y., Zhang, K., Ji, P., Li, H.: Displacement-invariant matching cost learning for accurate optical flow estimation. Adv. Neural. Inf. Process. Syst. 33, 15220\u201315231 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"14","key":"22_CR37","doi-asserted-by":"publisher","first-page":"3816","DOI":"10.3390\/s20143816","volume":"20","author":"T Wang","year":"2020","unstructured":"Wang, T., Cai, Y., Liang, L., Ye, D.: A multi-level approach to waste object segmentation. Sensors 20(14), 3816 (2020)","journal-title":"Sensors"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1568\u20131576 (2017)","DOI":"10.1109\/CVPR.2017.687"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., Huang, T.S.: Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7268\u20137277 (2018)","DOI":"10.1109\/CVPR.2018.00759"},{"key":"22_CR40","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR41","unstructured":"Yang, M., Thung, G.: Classification of trash for recyclability status. CS229 Project Report 2016(1), 3 (2016)"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., Huang, T.S.: Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1325\u20131334 (2018)","DOI":"10.1109\/CVPR.2018.00144"},{"key":"22_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-01249-6_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Zhang, X., Peng, C., Xue, X., Sun, J.: ExFuse: enhancing feature fusion for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 273\u2013288. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_17"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92805-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T12:59:40Z","timestamp":1747918780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92805-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031928048","9783031928055"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92805-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}