{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:30:57Z","timestamp":1753601457313,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031262920"},{"type":"electronic","value":"9783031262937"}],"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\/978-3-031-26293-7_25","type":"book-chapter","created":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T20:02:47Z","timestamp":1678478567000},"page":"414-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Causal-SETR: A SEgmentation TRansformer Variant Based on\u00a0Causal Intervention"],"prefix":"10.1007","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,11]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Badde, S., Hong, F., Landy, M.S.: Causal inference and the evolution of opposite neurons. Proceed. Nat. Acad. Sci. 118(36), e2112686118 (2021)","DOI":"10.1073\/pnas.2112686118"},{"key":"25_CR2","unstructured":"Bengio, Y., et al.: A meta-transfer objective for learning to disentangle causal mechanisms. arXiv preprint arXiv:1901.10912 (2019)"},{"key":"25_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":"25_CR4","unstructured":"Chalupka, K., Perona, P., Eberhardt, F.: Visual causal feature learning. arXiv preprint arXiv:1412.2309 (2014)"},{"issue":"4","key":"25_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR6","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1109\/LSP.2020.3025128","volume":"27","author":"S Chen","year":"2020","unstructured":"Chen, S., Li, Z., Tang, Z.: Relation R-CNN: a graph based relation-aware network for object detection. IEEE Signal Process. Lett. 27, 1680\u20131684 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, Z., Yang, X.: Knowledge reasoning for semantic segmentation. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2340\u20132344 (2021)","DOI":"10.1109\/ICASSP39728.2021.9415022"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"25_CR9","unstructured":"Dasgupta, I., et al.: Causal reasoning from meta-reinforcement learning. arXiv preprint arXiv:1901.08162 (2019)"},{"key":"25_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhang, L., Cheng, M.M., Feng, J.: Strip pooling: rethinking spatial pooling for scene parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4003\u20134012 (2020)","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: Criss-Cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"25_CR14","unstructured":"Kalainathan, D., Goudet, O., Guyon, I., Lopez-Paz, D., Sebag, M.: Sam: structural agnostic model, causal discovery and penalized adversarial learning (2018)"},{"key":"25_CR15","unstructured":"Kocaoglu, M., Snyder, C., Dimakis, A.G., Vishwanath, S.: CausalGAN: learning causal implicit generative models with adversarial training. arXiv preprint arXiv:1709.02023 (2017)"},{"issue":"1","key":"25_CR16","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"issue":"6","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1007\/s00521-020-05087-z","volume":"33","author":"Z Li","year":"2021","unstructured":"Li, Z., Sun, Y., Zhu, J., Tang, S., Zhang, C., Ma, H.: Improve relation extraction with dual attention-guided graph convolutional networks. Neural Comput. Appl. 33(6), 1773\u20131784 (2021)","journal-title":"Neural Comput. Appl."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Lopez-Paz, D., Nishihara, R., Chintala, S., Scholkopf, B., Bottou, L.: Discovering causal signals in images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6979\u20136987 (2017)","DOI":"10.1109\/CVPR.2017.14"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Theoretical impediments to machine learning with seven sparks from the causal revolution. arXiv preprint arXiv:1801.04016 (2018)","DOI":"10.1145\/3159652.3176182"},{"key":"25_CR22","unstructured":"Pearl, J., Glymour, M., Jewell, N.P.: Causal inference in statistics: a primer. John Wiley & Sons (2016)"},{"key":"25_CR23","unstructured":"Pearl, J., Mackenzie, D.: The book of why: the new science of cause and effect. Basic books (2018)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"9","key":"25_CR25","doi-asserted-by":"publisher","first-page":"4299","DOI":"10.1007\/s00521-020-05255-1","volume":"33","author":"Y Quan","year":"2021","unstructured":"Quan, Y., Li, Z., Chen, S., Zhang, C., Ma, H.: Joint deep separable convolution network and border regression reinforcement for object detection. Neural Comput. Appl. 33(9), 4299\u20134314 (2021)","journal-title":"Neural Comput. Appl."},{"issue":"7","key":"25_CR26","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.1109\/TIP.2019.2901393","volume":"28","author":"C Redondo-Cabrera","year":"2019","unstructured":"Redondo-Cabrera, C., Baptista-R\u00edos, M., L\u00f3pez-Sastre, R.J.: Learning to exploit the prior network knowledge for weakly supervised semantic segmentation. IEEE Trans. Image Process. 28(7), 3649\u20133661 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR27","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. arXiv preprint arXiv:2105.05633 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"25_CR29","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Wang, T., Huang, J., Zhang, H., Sun, Q.: Visual commonsense representation learning via causal inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPRW50498.2020.00197"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Wei, H., Li, Z., Huang, F., Zhang, C., Ma, H., Shi, Z.: Integrating scene semantic knowledge into image captioning. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(2), 1\u201322 (2021)","DOI":"10.1145\/3439734"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: CvT: introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"25_CR33","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, H., Qi, G., Cai, J.: Causal attention for vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9847\u20139857 (2021)","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"25_CR35","unstructured":"Zhang, D., Zhang, H., Tang, J., Hua, X.S., Sun, Q.: Causal intervention for weakly-supervised semantic segmentation. In: Advances in Neural Information Processing Systems 33 (2020)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 548\u2013557 (2019)","DOI":"10.1109\/CVPR.2019.00064"},{"key":"25_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103170","volume":"78","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Li, Z., Zhang, C., Ma, H.: Stable self-attention adversarial learning for semi-supervised semantic image segmentation. J. Vis. Commun. Image Represent. 78, 103170 (2021)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, M., Bai, S., Huang, T., Bai, X.: Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 593\u2013602 (2019)","DOI":"10.1109\/ICCV.2019.00068"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26293-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T20:09:14Z","timestamp":1678478954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26293-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262920","9783031262937"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26293-7_25","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":"11 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"0","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":"33% - 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":"3.3","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":"2.6","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}