{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:39:24Z","timestamp":1791913164014,"version":"4.3.4"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_21","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:19:01Z","timestamp":1733289541000},"page":"359-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Towards Open-Ended Visual Recognition with\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Qihang","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"21_CR1","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"21_CR2","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"21_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"21_CR4","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"21_CR5","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"21_CR7","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"21_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"21_CR9","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"21_CR11","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"21_CR12","unstructured":"Chiang, W.L., et al.: Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality, March 2023. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"21_CR13","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"21_CR14","unstructured":"Conti, A., Fini, E., Mancini, M., Rota, P., Wang, Y., Ricci, E.: Vocabulary-free image classification. In: NeurIPS (2023)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"21_CR16","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500 (2023)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2018)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"21_CR20","unstructured":"Ding, Z., Wang, J., Tu, Z.: Open-vocabulary panoptic segmentation with MaskCLIP. In: ICML (2023)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: EVA: exploring the limits of masked visual representation learning at scale. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"21_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-031-20059-5_31","volume-title":"ECCV 2022","author":"G Ghiasi","year":"2022","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.) ECCV 2022. LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"21_CR26","unstructured":"Gu, X., et al.: DaTaSeg: taming a universal multi-dataset multi-task segmentation model. In: NeurIPS (2023)"},{"key":"21_CR27","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":"21_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR30","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: ICLR (2021)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"21_CR32","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Kim, D., Lin, T.Y., Angelova, A., Kweon, I.S., Kuo, W.: Learning open-world object proposals without learning to classify. In: ICRA (2022)","DOI":"10.1109\/LRA.2022.3146922"},{"key":"21_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"21_CR37","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Lambert, J., Liu, Z., Sener, O., Hays, J., Koltun, V.: MSeg: a composite dataset for multi-domain semantic segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"21_CR39","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"21_CR40","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: ACL (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"21_CR42","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-20077-9_17","volume-title":"ECCV 2022","author":"Y Li","year":"2022","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17"},{"key":"21_CR43","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":"21_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"21_CR46","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"21_CR47","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":"21_CR48","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":"21_CR49","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"21_CR50","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"21_CR51","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"21_CR52","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"21_CR53","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"21_CR55","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"21_CR56","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"21_CR57","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. (2020)"},{"key":"21_CR58","doi-asserted-by":"crossref","unstructured":"Rewatbowornwong, P., Chatthee, N., Chuangsuwanich, E., Suwajanakorn, S.: Zero-guidance segmentation using zero segment labels. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00113"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Roberts, A., Raffel, C., Shazeer, N.: How much knowledge can you pack into the parameters of a language model? In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"21_CR60","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"21_CR61","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NeurIPS (2014)"},{"key":"21_CR62","unstructured":"Thoppilan, R., et\u00a0al.: LaMDA: language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)"},{"key":"21_CR63","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"21_CR64","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"21_CR65","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Adam, H., Yuille, A., Chen, L.C.: MaX-DeepLab: end-to-end panoptic segmentation with mask transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"21_CR66","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. In: NeurIPS (2023)"},{"key":"21_CR67","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"21_CR68","unstructured":"Wang, X., Li, S., Kallidromitis, K., Kato, Y., Kozuka, K., Darrell, T.: Hierarchical open-vocabulary universal image segmentation. In: NeurIPS, vol. 36 (2024)"},{"key":"21_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Detecting everything in the open world: towards universal object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"21_CR70","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. In: ICLR (2022)"},{"key":"21_CR71","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS (2022)"},{"key":"21_CR72","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"21_CR73","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"21_CR74","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-19818-2_42","volume-title":"ECCV 2022","author":"M Xu","year":"2022","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42"},{"key":"21_CR75","unstructured":"Yang, L., Wang, Y., Li, X., Wang, X., Yang, J.: Fine-grained visual prompting. In: NeurIPS, vol. 36 (2024)"},{"key":"21_CR76","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Gao, C., Yu, G., Shen, C., Sang, N.: Context prior for scene segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"21_CR77","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"21_CR78","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Convolutions die hard: open-vocabulary segmentation with single frozen convolutional CLIP. In: NeurIPS (2023)"},{"key":"21_CR79","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-031-19818-2_17","volume-title":"ECCV 2022","author":"Q Yu","year":"2022","unstructured":"Yu, Q., et al.: k-means mask transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 288\u2013307. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_17"},{"key":"21_CR80","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"21_CR81","unstructured":"Zhao, Y., Lin, Z., Zhou, D., Huang, Z., Feng, J., Kang, B.: BuboGPT: enabling visual grounding in multi-modal LLMs. arXiv preprint arXiv:2307.08581 (2023)"},{"key":"21_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"21_CR83","unstructured":"Zhou, Q., Liu, Y., Yu, C., Li, J., Wang, Z., Wang, F.: LMSeg: language-guided multi-dataset segmentation. In: ICLR (2023)"},{"key":"21_CR84","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"ECCV 2022","author":"X Zhou","year":"2022","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.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"},{"key":"21_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Simple multi-dataset detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"21_CR86","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"21_CR87","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2020)"}],"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\/978-3-031-72630-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:38:00Z","timestamp":1768199880000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}