{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:55:40Z","timestamp":1743112540637,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985487"},{"type":"electronic","value":"9789819985494"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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\/978-981-99-8549-4_34","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"407-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Expanding the\u00a0Horizons: Exploring Further Steps in\u00a0Open-Vocabulary Segmentation"],"prefix":"10.1007","author":[{"given":"Xihua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"34_CR1","unstructured":"Bucher, M., et al.: Zero-shot semantic segmentation. In: NeurIPS (2019)"},{"key":"34_CR2","unstructured":"Cen, J., et al.: Segment anything in 3D with NeRFs (2023)"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Cha, J., et al.: Learning to generate text-grounded mask for open-world semantic segmentation from only image-text pairs. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Cho, S., et al.: CAT-Seg: cost aggregation for open-vocabulary semantic segmentation. CoRR (2023)","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"34_CR5","unstructured":"Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Ding, J., et al.: Decoupling zero-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"34_CR7","unstructured":"Ding, Z., et al.: Open-vocabulary panoptic segmentation with MaskCLIP. arXiv preprint arXiv:2208.08984 (2022)"},{"key":"34_CR8","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"34_CR9","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Karazija, L., et al.: Diffusion models for zero-shot open-vocabulary segmentation. CoRR (2023)","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"34_CR11","unstructured":"Ke, L., et al.: Segment anything in high quality (2023)"},{"key":"34_CR12","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"34_CR13","unstructured":"Li, B., et al.: Language-driven semantic segmentation. In: ICLR (2022)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"34_CR15","unstructured":"Liu, H., et al.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"34_CR16","doi-asserted-by":"publisher","unstructured":"Liu, Q., Wen, Y., Han, J., Xu, C., Xu, H., Liang, X.: Open-world semantic segmentation via contrasting and clustering vision-language embedding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13680, pp. 275\u2013292. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_16","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., et al.: Image segmentation using text and image prompts. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"34_CR18","unstructured":"Luo, H., et al.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: ICML (2023)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"34_CR21","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"34_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., et al.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"34_CR25","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"34_CR26","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023)"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: segmenting everything in context. arXiv preprint arXiv:2304.03284 (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Xian, Y., et al.: Semantic projection network for zero- and few-label semantic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00845"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"34_CR32","doi-asserted-by":"publisher","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753 . Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"34_CR33","doi-asserted-by":"publisher","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: Side adapter network for open-vocabulary semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"34_CR35","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection. arXiv preprint arXiv:2303.08131 (2023)"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Open vocabulary scene parsing. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.221"},{"key":"34_CR37","unstructured":"Zhao, W.X., et al.: A survey of large language models (2023)"},{"key":"34_CR38","unstructured":"Zhao, X., et al.: Fast segment anything (2023)"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: RegionCLIP: region-based language-image pretraining. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Zou, X., et al.: Generalized decoding for pixel, image, and language. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"34_CR42","unstructured":"Zou, X., et al.: Segment everything everywhere all at once (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8549-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:08:30Z","timestamp":1730923710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8549-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985487","9789819985494"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8549-4_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}