{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:42:52Z","timestamp":1743072172587,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":47,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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\/978-981-97-8505-6_30","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:03:05Z","timestamp":1730930585000},"page":"421-436","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Open-Vocabulary Instance Segmentation-Boundary IS-Goal"],"prefix":"10.1007","author":[{"given":"Quan","family":"Tang","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"He, K., et al.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","key":"30_CR1","DOI":"10.1109\/ICCV.2017.322"},{"issue":"8","key":"30_CR2","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.1109\/83.855433","volume":"9","author":"W-Y Ma","year":"2000","unstructured":"Ma, W.-Y., Manjunath, B.S.: EdgeFlow: a technique for boundary detection and image segmentation. IEEE Trans. Image Process. 9(8), 1375\u20131388 (2000)","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: OverlapNet: loop closing for LiDAR-based SLAM. arXiv preprint arXiv:2105.11344 (2021)","key":"30_CR3","DOI":"10.15607\/RSS.2020.XVI.009"},{"doi-asserted-by":"crossref","unstructured":"Sautier, C., et al.: Image-to-lidar self-supervised distillation for autonomous driving data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","key":"30_CR4","DOI":"10.1109\/CVPR52688.2022.00966"},{"doi-asserted-by":"crossref","unstructured":"Cui, Z., Li, C., Wang, W.: ToothNet: automatic tooth instance segmentation and identification from cone beam CT images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","key":"30_CR5","DOI":"10.1109\/CVPR.2019.00653"},{"doi-asserted-by":"crossref","unstructured":"Zhen, M., et al.: Joint semantic segmentation and boundary detection using iterative pyramid contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","key":"30_CR6","DOI":"10.1109\/CVPR42600.2020.01368"},{"unstructured":"Liao, Y., et al.: Mobile-seed: joint semantic segmentation and boundary detection for mobile robots. arXiv preprint arXiv:2311.12651 (2023)","key":"30_CR7"},{"doi-asserted-by":"crossref","unstructured":"Bolya, D., et al.: Yolact: real-time instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","key":"30_CR8","DOI":"10.1109\/ICCV.2019.00925"},{"doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: Soit: segmenting objects with instance-aware transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36. no. 3 (2022)","key":"30_CR9","DOI":"10.1609\/aaai.v36i3.20227"},{"doi-asserted-by":"crossref","unstructured":"Ke, L., et al.: Mask transfiner for high-quality instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","key":"30_CR10","DOI":"10.1109\/CVPR52688.2022.00437"},{"doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: Centermask: real-time anchor-free instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","key":"30_CR11","DOI":"10.1109\/CVPR42600.2020.01392"},{"doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Gated-scnn: Gated shape cnns for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","key":"30_CR12","DOI":"10.1109\/ICCV.2019.00533"},{"unstructured":"Li, X., et al.: Improving semantic segmentation via decoupled body and edge supervision. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVII 16. Springer International Publishing (2020)","key":"30_CR13"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"30_CR14"},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)","key":"30_CR15"},{"unstructured":"Xie, E., et al.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021)","key":"30_CR16"},{"doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Topformer: token pyramid transformer for mobile semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","key":"30_CR17","DOI":"10.1109\/CVPR52688.2022.01177"},{"unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)","key":"30_CR18"},{"doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Casenet: deep category-aware semantic edge detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"30_CR19","DOI":"10.1109\/CVPR.2017.191"},{"doi-asserted-by":"crossref","unstructured":"Hu, Yuan, et al. \"Dynamic feature fusion for semantic edge detection.\" arXiv preprint arXiv:1902.09104 (2019)","key":"30_CR20","DOI":"10.24963\/ijcai.2019\/110"},{"unstructured":"Zou, X., Liu, H., Lee, Y.J.: End-to-end instance edge detection. arXiv preprint arXiv:2204.02898 (2022)","key":"30_CR21"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Semantic edge detection with diverse deep supervision. Int. J. Comput. Vis. 130(1), 179\u2013198 (2022)","key":"30_CR22","DOI":"10.1007\/s11263-021-01539-8"},{"unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning. PMLR (2021)","key":"30_CR23"},{"unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021)","key":"30_CR24"},{"doi-asserted-by":"crossref","unstructured":"Huynh, D., et al.: Open-vocabulary instance segmentation via robust cross-modal pseudo-labeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","key":"30_CR25","DOI":"10.1109\/CVPR52688.2022.00689"},{"unstructured":"Vibashan, V.S., et al.: Mask-free ovis: open-vocabulary instance segmentation without manual mask annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","key":"30_CR26"},{"doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Towards open-vocabulary video instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","key":"30_CR27","DOI":"10.1109\/ICCV51070.2023.00375"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Betrayed by captions: joint caption grounding and generation for open vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","key":"30_CR28","DOI":"10.36227\/techrxiv.22082723.v1"},{"doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","key":"30_CR29","DOI":"10.1109\/ICCV51070.2023.00100"},{"unstructured":"Qin, J., et al.: Freeseg: unified, universal and open-vocabulary image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","key":"30_CR30"},{"doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","key":"30_CR31","DOI":"10.1109\/CVPR.2015.7298965"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"30_CR32","DOI":"10.1109\/CVPR.2017.472"},{"unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)","key":"30_CR33"},{"doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","key":"30_CR34","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","key":"30_CR35","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"crossref","unstructured":"He, J., et al.: FastInst: A simple query-based model for real-time instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","key":"30_CR36","DOI":"10.1109\/CVPR52729.2023.02266"},{"doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"30_CR37","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Acuna, D., Kar, A., Fidler, S.: Devil is in the edges: learning semantic boundaries from noisy annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","key":"30_CR38","DOI":"10.1109\/CVPR.2019.01133"},{"doi-asserted-by":"crossref","unstructured":"Hayder, Z., He, X., Salzmann, M.: Boundary-aware instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"30_CR39","DOI":"10.1109\/CVPR.2017.70"},{"unstructured":"Cheng, T., et al.: Boundary-preserving mask r-cnn. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16. Springer International Publishing (2020)","key":"30_CR40"},{"unstructured":"Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"30_CR41"},{"doi-asserted-by":"crossref","unstructured":"Sandler, M., et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","key":"30_CR42","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"crossref","unstructured":"Cheng, T., et al.: YOLO-World: real-time open-vocabulary object detection. arXiv preprint arXiv:2401.17270 (2024)","key":"30_CR43","DOI":"10.1109\/CVPR52733.2024.01599"},{"unstructured":"Lin, T.-Y., et al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13. Springer International Publishing (2014)","key":"30_CR44"},{"doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","key":"30_CR45","DOI":"10.1109\/CVPR.2019.00550"},{"unstructured":"Everingham, M., Winn, J.: The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn. Tech. Rep. 2007 5, 1\u201345 (2012)","key":"30_CR46"},{"doi-asserted-by":"crossref","unstructured":"Xing, M., et al.: Learning by erasing: conditional entropy based transferable out-of-distribution detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 6 (2024)","key":"30_CR47","DOI":"10.1609\/aaai.v38i6.28444"}],"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\/978-981-97-8505-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:07:29Z","timestamp":1730930849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}