{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:02:44Z","timestamp":1781103764165,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819980727","type":"print"},{"value":"9789819980734","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8073-4_24","type":"book-chapter","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T08:02:54Z","timestamp":1699948974000},"page":"305-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TASFormer: Task-Aware Image Segmentation Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1407-2633","authenticated-orcid":false,"given":"Dmitry","family":"Yudin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5251-4930","authenticated-orcid":false,"given":"Aleksandr","family":"Khorin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-7336","authenticated-orcid":false,"given":"Tatiana","family":"Zemskova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2491-2245","authenticated-orcid":false,"given":"Darya","family":"Ovchinnikova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: Proceedings of the IEEE\/CVF CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE\/CVF CVPR, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"24_CR3","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=plKu2GByCNW"},{"key":"24_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 CVPR. pp, 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE\/CVF CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vlt: vision-language transformer and query generation for referring segmentation. IEEE Trans. Patt. Anal. Mach. Intell. (2022)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"24_CR7","unstructured":"Dong, N., Xing, E.P.: Few-shot semantic segmentation with prototype learning. In: BMVC. vol. 3 (2018)"},{"key":"24_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021), https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Ghodrati, A., Li, Z., Snoek, C.G.: Actor and action video segmentation from a sentence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5958\u20135966 (2018)","DOI":"10.1109\/CVPR.2018.00624"},{"key":"24_CR10","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=lL3lnMbR4WU"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: Oneformer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF CVPR, pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF ICCV, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Karimi Mahabadi, R., Ruder, S., Dehghani, M., Henderson, J.: Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. In: Annual Meeting of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Kirilenko, D., Kovalev, A.K., Solomentsev, Y., Melekhin, A., Yudin, D.A., Panov, A.I.: Vector symbolic scene representation for semantic place recognition. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892761"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF CVPR, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"24_CR17","unstructured":"Liu, S., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv:2303.05499 (2023)"},{"issue":"12","key":"24_CR18","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.1007\/s11263-022-01677-7","volume":"130","author":"W Liu","year":"2022","unstructured":"Liu, W., Zhang, C., Lin, G., Liu, F.: CRCNet: few-shot segmentation with cross-reference and region-global conditional networks. Int. J. Comput. Vision 130(12), 3140\u20133157 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al..: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Lu, K., Grover, A., Abbeel, P., Mordatch, I.: Pretrained transformers as universal computation engines. Proc. of the AAAI Conf. Artif. Intell. 36, 7628\u20137636 (06 2022). https:\/\/doi.org\/10.1609\/aaai.v36i7.20729","DOI":"10.1609\/aaai.v36i7.20729"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF CVPR, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"McCormac, J., Handa, A., Leutenegger, S., Davison, A.J.: Scenenet RGB-D: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? In: Proceedings. of the IEEE\/CVF ICCV, pp. 2697\u20132706 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.292","DOI":"10.1109\/ICCV.2017.292"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Pan, H., Hong, Y., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans. Intell. Transp. Syst. 24(3), 3448\u20133460 (2022)","DOI":"10.1109\/TITS.2022.3228042"},{"key":"24_CR24","unstructured":"Rakelly, K., Shelhamer, E., Darrell, T., Efros, A., Levine, S.: Conditional networks for few-shot semantic segmentation. ICLR Workshop (2018)"},{"key":"24_CR25","doi-asserted-by":"publisher","unstructured":"Schlegel, K., Neubert, P., Protzel, P.: A comparison of vector symbolic architectures. Artif. Intell. Rev. 55, 4523\u20134555 (2021). https:\/\/doi.org\/10.1007\/s10462-021-10110-3","DOI":"10.1007\/s10462-021-10110-3"},{"key":"24_CR26","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58555-6_13","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV","author":"S Seo","year":"2020","unstructured":"Seo, S., Lee, J.-Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV, pp. 208\u2013223. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_13"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. In: British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.167"},{"issue":"9","key":"24_CR28","doi-asserted-by":"publisher","first-page":"14779","DOI":"10.1109\/TITS.2021.3133799","volume":"23","author":"I Shepel","year":"2021","unstructured":"Shepel, I., Adeshkin, V., Belkin, I., Yudin, D.A.: Occupancy grid generation with dynamic obstacle segmentation in stereo images. IEEE Trans. Intell. Transp. Syst. 23(9), 14779\u201314789 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Song, S., P., S., Lichtenberg, Xiao, J.: Sun RGB-D: A RGB-D scene understanding benchmark suite. Proceedings of the IEEE CVPR (2015). https:\/\/rgbd.cs.princeton.edu\/","DOI":"10.1109\/CVPR.2015.7298655"},{"issue":"3","key":"24_CR30","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Image as a foreign language: beit pretraining for vision and vision-language tasks. In: CVPR, pp. 19175\u201319186 (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Wu, C., Lin, Z., Cohen, S., Bui, T., Maji, S.: Phrasecut: language-based image segmentation in the wild. In: Proceedings of the IEEE\/CVF CVPR, pp. 10216\u201310225 (2020)","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: Proceedings of the IEEE\/CVF CVPR, pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"24_CR34","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"24_CR35","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":"24_CR36","doi-asserted-by":"crossref","unstructured":"Xu, J., Xiong, Z., Bhattacharyya, S.P.: Pidnet: a real-time semantic segmentation network inspired by PID controllers. In: CVPR, pp. 19529\u201319539 (2023)","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF CVP, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"24_CR38","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II, pp. 69\u201385. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"24_CR40","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight SAM for mobile applications (2023)"},{"issue":"3","key":"24_CR41","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vis. 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Zou, X., et al.: Generalized decoding for pixel, image, and language. In: Proceedings of the IEEE\/CVF CVPR, pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8073-4_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:39:41Z","timestamp":1710355181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8073-4_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"ISBN":["9789819980727","9789819980734"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8073-4_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,15]]},"assertion":[{"value":"15 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}