{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T04:45:47Z","timestamp":1765169147127,"version":"3.46.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032049674"},{"type":"electronic","value":"9783032049681"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04968-1_24","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T08:04:42Z","timestamp":1758009882000},"page":"283-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Open-Vocabulary Models for\u00a0Category-Free Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9162-4073","authenticated-orcid":false,"given":"Pablo","family":"Garcia-Fernandez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5548-4837","authenticated-orcid":false,"given":"Daniel","family":"Cores","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1735-3585","authenticated-orcid":false,"given":"Manuel","family":"Mucientes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"24_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv:2303.08774 (2023)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.: Towards open world recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Dhamija, A., Gunther, M., Ventura, J., Boult, T.: The overlooked elephant of object detection: open set. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1021\u20131030 (2020)","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Fang, R., Pang, G., Bai, X.: Simple image-level classification improves open-vocabulary object detection. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i2.27939"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Feng, C., et al.: Promptdet: Towards open-vocabulary detection using uncurated images. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"24_CR7","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Narayan, S., Joseph, K., Khan, S., Khan, F.S., Shah, M.: OW-DETR: open-world detection transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Han, J., Ren, Y., Ding, J., Pan, X., Yan, K., Xia, G.S.: Expanding low-density latent regions for open-set object detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00937"},{"key":"24_CR10","unstructured":"Hugging Face: Introducing idefics: An open reproduction of state-of-the-art visual language model (2023). https:\/\/huggingface.co\/blog\/idefics. Accessed 30 Apr 2025"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Joseph, K., Khan, S., Khan, F.S., Balasubramanian, V.N.: Towards open world object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"24_CR12","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: F-VLM: open-vocabulary object detection upon frozen vision and language models. arXiv:2209.15639 (2022)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Distilling DETR with visual-linguistic knowledge for open-vocabulary object detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00598"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"24_CR15","unstructured":"Lin, C., et al.: Learning object-language alignments for open-vocabulary object detection. In: ICLR (2023)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"24_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., et al.: Open-set semi-supervised object detection. In: ECCV. Springer (2022)","DOI":"10.1007\/978-3-031-20056-4_9"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR21","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: CoDet: co-occurrence guided region-word alignment for open-vocabulary object detection. In: NeurIPS (2023)"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Miller, D., Nicholson, L., Dayoub, F., S\u00fcnderhauf, N.: Dropout sampling for robust object detection in open-set conditions. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3243\u20133249. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"24_CR24","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"24_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"24_CR26","unstructured":"Wu, J., et al.: Towards open vocabulary learning: a survey. In: PAMI (2024)"},{"key":"24_CR27","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"24_CR28","unstructured":"Wu, S., et al.: Clipself: vision transformer distills itself for open-vocabulary dense prediction. In: ICLR (2024)"},{"key":"24_CR29","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhao, X., Ma, Y., Wang, D., Liu, X.: Two-branch objectness-centric open world detection. In: Proceedings of the 3rd International Workshop on Human-Centric Multimedia Analysis, pp. 35\u201340 (2022)","DOI":"10.1145\/3552458.3556453"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lu, Y., Chen, X., Wu, Z., Kang, L., Yu, J.: UC-OWOD: unknown-classified open world object detection. In: ECCV. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_12"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Detclipv2: Scalable open-vocabulary object detection pre-training via word-region alignment. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"24_CR33","unstructured":"Yao, L., et al.: Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection. In: NeurIPS (2022)"},{"key":"24_CR34","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data, 2024g. https:\/\/arxiv.org\/abs\/2410.02713"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, J., Li, W., Hong, J., Petersson, L., Barnes, N.: Towards open-set object detection and discovery. In: CVPR (2022)","DOI":"10.1109\/CVPRW56347.2022.00441"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: Regionclip: region-based language-image pretraining. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, L.: A survey on open-vocabulary detection and segmentation: past, present, and future. IEEE TPAMI (2024)","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Zohar, O., Wang, K.C., Yeung, S.: PROB: probabilistic objectness for open world object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01101"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04968-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T04:42:21Z","timestamp":1765168941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04968-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032049674","9783032049681"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04968-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Palmas de Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caip2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}