{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:24:22Z","timestamp":1743009862148,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755905"},{"type":"electronic","value":"9789819755912"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-5591-2_19","type":"book-chapter","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:02:42Z","timestamp":1723572162000},"page":"220-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Open-Vocabulary Object Detection by Novel-Class Feature Perception Enhancement"],"prefix":"10.1007","author":[{"given":"Kanghua","family":"Hui","sequence":"first","affiliation":[]},{"given":"Xianqiao","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Zhi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"19_CR1","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"19_CR2","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., et al.: Regionclip: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Pham, C., Vu, T., Nguyen, K.: Lp-ovod: open-vocabulary object detection by linear probing. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 779\u2013788 (2024)","DOI":"10.1109\/WACV57701.2024.00083"},{"key":"19_CR5","unstructured":"Wu, S., Zhang, W., Xu, L., et al.: Clipself: vision transformer distills itself for open-vocabulary dense prediction. arXiv preprint arXiv:2310.01403 (2023)"},{"key":"19_CR6","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, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"19_CR7","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et al.: Microsoft coco: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision \u2013 ECCV 2014. ECCV 2014. LNCS, vol. 8693. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Gao, M., Xing, C., Niebles, J.C., et al.: Open vocabulary object detection with pseudo bounding-box labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13670. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_16","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., et al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"19_CR11","doi-asserted-by":"publisher","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13669. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Wang, L., Liu, Y., Du, P., et al.: Object-aware distillation pyramid for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11186\u201311196 (2023)","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"19_CR13","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-VLM: Open-vocabulary object detection upon frozen vision and language models. arXiv preprint arXiv:2209.15639 (2022)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhu, F., Zhao, R., Li, H.: Cora: Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7031\u20137040 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Contrastive feature masking open-vocabulary vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15602\u201315612 (2023)","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et al.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, W., Jin, S., Liu, W., Loy, C.C.: Aligning bag of regions for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15254\u201315264 (2023)","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, W., Xu, L., et al.: Clim: contrastive language-image mosaic for region representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6117\u20136125 (2024)","DOI":"10.1609\/aaai.v38i6.28428"},{"key":"19_CR20","unstructured":"Zhang, X., Wang, Y., Boularias, A.: Detect every thing with few examples. arXiv preprint arXiv:2309.12969 (2023)"},{"key":"19_CR21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5591-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:05:51Z","timestamp":1723572351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5591-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755905","9789819755912"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5591-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}