{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:37:16Z","timestamp":1742913436221,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726392"},{"type":"electronic","value":"9783031726408"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_6","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"95-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Point-Supervised Panoptic Segmentation via\u00a0Estimating Pseudo Labels from\u00a0Learnable Distance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8968-1513","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6989-2711","authenticated-orcid":false,"given":"Junsong","family":"Fan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"6_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46478-7_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Bearman","year":"2016","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What\u2019s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_34"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bu, X., Peng, J., Yan, J., Tan, T., Zhang, Z.: Gaia: a transfer learning system of object detection that fits your needs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 274\u2013283 (2021)","DOI":"10.1109\/CVPR46437.2021.00034"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Parkhi, O., Kirillov, A.: Pointly-supervised instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2617\u20132626 (2022)","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"6_CR6","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"6_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge 88, 303\u2013338 (2009)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"6_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-031-20056-4_19","volume-title":"ECCV 2022","author":"J Fan","year":"2022","unstructured":"Fan, J., Zhang, Z., Tan, T.: Pointly-supervised panoptic segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 319\u2013336. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_19"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L.D., Maji, S., Malik, J.: Semantic contours from inverse detectors, pp. 991\u2013998 (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Fan, J., Wang, Y., Yang, Y., Zhang, Z.: Coarse mask guided interactive object segmentation. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3322564"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Fan, J., Zhang, Z.: Towards noiseless object contours for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16856\u201316865 (2022)","DOI":"10.1109\/CVPR52688.2022.01635"},{"key":"6_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-01267-0_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Q Li","year":"2018","unstructured":"Li, Q., Arnab, A., Torr, P.H.S.: Weakly- and semi-supervised panoptic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 106\u2013124. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_7"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Point2mask: point-supervised panoptic segmentation via optimal transport. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 572\u2013581 (2023)","DOI":"10.1109\/ICCV51070.2023.00059"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Fully convolutional networks for panoptic segmentation with point-based supervision. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3200416"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Panoptic segformer: delving deeper into panoptic segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1280\u20131289 (2022)","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Liang, Z., Wang, T., Zhang, X., Sun, J., Shen, J.: Tree energy loss: towards sparsely annotated semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16907\u201316916 (2022)","DOI":"10.1109\/CVPR52688.2022.01640"},{"key":"6_CR22","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":"6_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhang, Z., Chen, L.Z., Cheng, M.M., Lu, S.P.: Interactive image segmentation with first click attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13339\u201313348 (2020)","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., et.: An end-to-end network for panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6172\u20136181 (2019)","DOI":"10.1109\/CVPR.2019.00633"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representation (2019)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Maninis, K.K., Caelles, S., Pont-Tuset, J., Gool, L.V.: Deep extreme cut: from extreme points to object segmentation, pp. 616\u2013625 (2018)","DOI":"10.1109\/CVPR.2018.00071"},{"key":"6_CR29","unstructured":"Obukhov, A., Georgoulis, S., Dai, D., Van\u00a0Gool, L.: Gated CRF loss for weakly supervised semantic image segmentation. arXiv preprint arXiv:1906.04651 (2019)"},{"issue":"10","key":"6_CR30","doi-asserted-by":"publisher","first-page":"11856","DOI":"10.1109\/TPAMI.2023.3276392","volume":"45","author":"J Peng","year":"2023","unstructured":"Peng, J., et al.: Gaia-universe: everything is super-netify. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 11856\u201311868 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR31","unstructured":"Peng, J., Sun, M., Zhang, Z.X., Tan, T., Yan, J.: Efficient neural architecture transformation search in channel-level for object detection. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Peng, J., Sun, M., Zhang, Z., Tan, T., Yan, J.: Pod: fractical object detection with scale-sensitive network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9607\u20139616 (2019)","DOI":"10.1109\/ICCV.2019.00970"},{"key":"6_CR33","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"issue":"1","key":"6_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-1186-y","volume":"17","author":"H Ruan","year":"2023","unstructured":"Ruan, H., Song, H., Liu, B., Cheng, Y., Liu, Q.: Intellectual property protection for deep semantic segmentation models. Front. Comp. Sci. 17(1), 171306 (2023)","journal-title":"Front. Comp. Sci."},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: Toward joint thing-and-stuff mining for weakly supervised panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16694\u201316705 (2021)","DOI":"10.1109\/CVPR46437.2021.01642"},{"key":"6_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-030-58598-3_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Shen","year":"2020","unstructured":"Shen, Y., et al.: Enabling deep residual networks for\u00a0weakly supervised object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 118\u2013136. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_8"},{"issue":"8","key":"6_CR37","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR38","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":"6_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-030-01270-0_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Tang","year":"2018","unstructured":"Tang, M., Perazzi, F., Djelouah, A., Ayed, I.B., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised CNN segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 524\u2013540. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_31"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Wang, X., Chen, H.: BoxInst: high-performance instance segmentation with box annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5443\u20135452 (2021)","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"6_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wang, B., et al.: Boundary perception guidance: a scribble-supervised semantic segmentation approach. In: IJCAI International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/508"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liew, J.H., Wei, Y., Wei, S., Zhao, Y.: Interactive object segmentation with inside-outside guidance, pp. 12234\u201312244 (2020)","DOI":"10.1109\/CVPR42600.2020.01225"},{"key":"6_CR44","first-page":"10326","volume":"34","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-net: towards unified image segmentation. Adv. Neural. Inf. Process. Syst. 34, 10326\u201310338 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"6_CR45","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1007\/s11263-021-01573-6","volume":"130","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Pan, C., Peng, J.: Delving into the effectiveness of receptive fields: Learning scale-transferrable architectures for practical object detection. Int. J. Comput. Vision 130(4), 970\u2013989 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR46","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable Detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72640-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:39:49Z","timestamp":1730108389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","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"}}]}}