{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:47:57Z","timestamp":1777657677156,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73337-6_18","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"312-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["LaMI-DETR: Open-Vocabulary Detection with\u00a0Language Model Instruction"],"prefix":"10.1007","author":[{"given":"Penghui","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Errui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"18_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. NIPS 33, 1877\u20131901 (2020)"},{"key":"18_CR3","unstructured":"Chen, Q., et\u00a0al.: LW-DETR: a transformer replacement to yolo for real-time detection. arXiv preprint arXiv:2406.03459 (2024)"},{"key":"18_CR4","unstructured":"Dave, A., Doll\u00e1r, P., Ramanan, D., Kirillov, A., Girshick, R.: Evaluating large-vocabulary object detectors: the devil is in the details. arXiv preprint arXiv:2102.01066 (2021)"},{"key":"18_CR5","unstructured":"Demirel, B., Cinbis, R.G., Ikizler-Cinbis, N.: Zero-shot object detection by hybrid region embedding. In: BMVC (2018)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.C.: Learning to prompt for open-vocabulary object detection with vision-language model. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Feng, C., et al.: PromptDet: towards open-vocabulary detection using uncurated images. In: ECCV, pp. 701\u2013717. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"18_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"18_CR9","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"18_CR11","unstructured":"Hu, Z., Sun, Y., Wang, J., Yang, Y.: DAC-DETR: divide the attention layers and conquer. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773, https:\/\/doi.org\/10.5281\/zenodo.5143773, if you use this software, please cite it as below","DOI":"10.5281\/zenodo.5143773"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Contrastive feature masking open-vocabulary vision transformer (2023)","DOI":"10.1109\/ICCV51070.2023.01430"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: CVPR, pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"18_CR15","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A.: Open-vocabulary object detection upon frozen vision and language models. In: ICLR (2023). https:\/\/openreview.net\/forum?id=MIMwy4kh9lf"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Li*, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"18_CR19","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: CoDet: co-occurrence guided region-word alignment for open-vocabulary object detection. In: NIPS (2023)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Minderer, M., Gritsenko, A.: Scaling open-vocabulary object detection. NeurIPS, N.H. (2023)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"18_CR21","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. ICLR (2023)"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection. In: ECCV, pp. 728\u2013755. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., Farhadi, A.: What does a platypus look like? generating customized prompts for zero-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15691\u201315701 (2023)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"18_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR26","unstructured":"Rasheed, H., Maaz, M., Khattak, M.U., Khan, S., Khan, F.S.: Bridging the gap between object and image-level representations for open-vocabulary detection. In: NIPS (2022)"},{"key":"18_CR27","unstructured":"Ren, T., et al.: detrex: benchmarking detection transformers (2023)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: EdaDet: open-vocabulary object detection using early dense alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2023)","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"18_CR30","unstructured":"Shizhen, Z., Changxin, G., Yuanjie, S., Lerenhan, L., Changqian, Y., Zhong, J., Nong, S.: GTNet: generative transfer network for zero-shot object detection. In: AAAI (2020)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Su, H., et al.: One embedder, any task: instruction-finetuned text embeddings (2022). https:\/\/arxiv.org\/abs\/2212.09741","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, H., Hong, H., Jin, X., He, Y., Xue, H., Zhao, Z.: Open-vocabulary object detection with an open corpus. In: ICCV, pp. 6759\u20136769 (2023)","DOI":"10.1109\/ICCV51070.2023.00622"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Object-aware distillation pyramid for open-vocabulary object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wang, T.: Learning to detect and segment for open vocabulary object detection. In: CVPR, pp. 7051\u20137060 (2023)","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"18_CR35","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":"18_CR36","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. arXiv preprint arxiv: abs\/2303.13076 (2023)","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Yao, L., Han, J., Liang, X., Xu, D., Zhang, W., Li, Z., Xu, H.: DetCLIPv2: scalable open-vocabulary object detection pre-training via word-region alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23497\u201323506 (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"18_CR39","first-page":"9125","volume":"35","author":"L Yao","year":"2022","unstructured":"Yao, L., et al.: DetCLIP: dictionary-enriched visual-concept paralleled pre-training for open-world detection. NIPS 35, 9125\u20139138 (2022)","journal-title":"NIPS"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching (2022)","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"18_CR42","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection (2022)"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, C., Sun, Y., Wang, W., Chen, Q., Ding, E., Yang, Y., Wang, J.: MS-DETR: efficient DETR training with mixed supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17027\u201317036 (2024)","DOI":"10.1109\/CVPR52733.2024.01611"},{"key":"18_CR44","doi-asserted-by":"publisher","unstructured":"Zhao, S., et al.: Exploiting unlabeled data with vision and language models for object detection. In: ECCV, pp. 159\u2013175. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_10","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: CVPR, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"18_CR46","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: ECCV, pp. 350\u2013368. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"18_CR47","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. In: arXiv preprint arXiv:2103.07461 (2021)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, P., Wang, H., Saligrama, V.: Don\u2019t even look once: synthesizing features for zero-shot detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01171"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73337-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:59:34Z","timestamp":1732978774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}