{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:51:53Z","timestamp":1775245913122,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012243","type":"print"},{"value":"9783030012250","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01225-0_43","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T04:39:54Z","timestamp":1538973594000},"page":"734-749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["End-to-End Joint Semantic Segmentation of Actors and Actions in Video"],"prefix":"10.1007","author":[{"given":"Jingwei","family":"Ji","sequence":"first","affiliation":[]},{"given":"Shyamal","family":"Buch","sequence":"additional","affiliation":[]},{"given":"Alvaro","family":"Soto","sequence":"additional","affiliation":[]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"43_CR1","first-page":"265","volume":"16","author":"M Abadi","year":"2016","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. OSDI 16, 265\u2013283 (2016)","journal-title":"OSDI"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"43_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/978-3-319-46466-4_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Dai","year":"2016","unstructured":"Dai, J., He, K., Li, Y., Ren, S., Sun, J.: Instance-sensitive fully convolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 534\u2013549. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_32"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3150\u20133158 (2016)","DOI":"10.1109\/CVPR.2016.343"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 759\u2013768 (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Herath, S., Harandi, M., Porikli, F.: Going deeper into action recognition: a survey. arXiv preprint arXiv:1605.04988 (2016)","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Joint learning of object and action detectors. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.219"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy, A., et al.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"43_CR13","unstructured":"Li, X., et al.: Video object segmentation with re-identification. arXiv preprint arXiv:1708.00197 (2017)"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, vol. 1, p. 4 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"43_CR15","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":"43_CR16","unstructured":"Pinheiro, P.O., Collobert, R., Doll\u00e1r, P.: Learning to segment object candidates. In: Advances in Neural Information Processing Systems, pp. 1990\u20131998 (2015)"},{"key":"43_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-319-46448-0_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"PO Pinheiro","year":"2016","unstructured":"Pinheiro, P.O., Lin, T.-Y., Collobert, R., Doll\u00e1r, P.: Learning to refine object segments. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 75\u201391. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_5"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5534\u20135542. IEEE (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"43_CR19","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, pp. 91\u201399 (2015)"},{"issue":"3","key":"43_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Russell, C., Kohli, P., Torr, P.H., et al.: Associative hierarchical CRFs for object class image segmentation. In: IEEE 12th International Conference on Computer Vision, pp. 739\u2013746. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"43_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: NIPS (2014)"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)","DOI":"10.5244\/C.31.116"},{"key":"43_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"43_CR26","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arXiv:1712.04851 (2017)"},{"key":"43_CR27","doi-asserted-by":"publisher","unstructured":"Xu, C., Corso, J.J.: Actor-action semantic segmentation with grouping process models. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3083\u20133092, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.336","DOI":"10.1109\/CVPR.2016.336"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Xu, C., Hsieh, S.H., Xiong, C., Corso, J.J.: Can humans fly? Action understanding with multiple classes of actors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2015). http:\/\/web.eecs.umich.edu\/~jjcorso\/pubs\/xu_corso_CVPR2015_A2D.pdf","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Yan, Y., Xu, C., Cai, D., Corso, J.J.: Weakly supervised actor-action segmentation via robust multi-task ranking. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.115"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01225-0_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:54:10Z","timestamp":1775242450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01225-0_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012243","9783030012250"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01225-0_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}