{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:11:57Z","timestamp":1743124317086,"version":"3.40.3"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031733826"},{"type":"electronic","value":"9783031733833"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73383-3_8","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:05:01Z","timestamp":1730549101000},"page":"127-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7899-0288","authenticated-orcid":false,"given":"William Yicheng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-7762","authenticated-orcid":false,"given":"Keren","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5846-9002","authenticated-orcid":false,"given":"Junjie","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7085-834X","authenticated-orcid":false,"given":"Jiahui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-4886","authenticated-orcid":false,"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1455-7662","authenticated-orcid":false,"given":"Peyman","family":"Milanfar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6195-2089","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00904"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Al-Halah, Z., Tapaswi, M., Stiefelhagen, R.: Recovering the missing link: predicting class-attribute associations for unsupervised zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5975\u20135984 (2016)","DOI":"10.1109\/CVPR.2016.643"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"8_CR5","unstructured":"Bao, H., et al.: VLMO: unified vision-language pre-training with mixture-of-modality-experts. Adv. Neural Inf. Process. Syst. 35, 32897\u201332912 (2022)"},{"key":"8_CR6","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. In: Advances in Neural Information Processing Systems, vol. 13 (2000)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: OvarNet: towards open-vocabulary object attribute recognition. arXiv preprint arXiv:2301.09506 (2023)","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"8_CR8","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. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Grauman, K.: Compare and contrast: learning prominent visual differences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1267\u20131276 (2018)","DOI":"10.1109\/CVPR.2018.00138"},{"key":"8_CR10","unstructured":"Chen, X., et\u00a0al.: PaLI-X: on scaling up a multilingual vision and language model. arXiv preprint arXiv:2305.18565 (2023)"},{"key":"8_CR11","unstructured":"Chen, X., et\u00a0al.: PaLI: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"8_CR12","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: learning universal image-text representations. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00532"},{"key":"8_CR15","unstructured":"Chowdhery, A., et\u00a0al.: PaLM: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"8_CR16","doi-asserted-by":"publisher","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, vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Durand, T., Mehrasa, N., Mori, G.: Learning a deep convnet for multi-label classification with partial labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00074"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1778\u20131785. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"8_CR19","unstructured":"Ferrari, V., Zisserman, A.: Learning visual attributes. In: Advances in Neural Information Processing Systems, vol. 20 (2007)"},{"key":"8_CR20","unstructured":"Frome, A., et al.: DeViSE: a deep visual-semantic embedding model. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a026. Curran Associates, Inc. (2013). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/7cce53cf90577442771720a370c3c723-Paper.pdf"},{"key":"8_CR21","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"8_CR22","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":"8_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.322"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR25","unstructured":"Jayaraman, D., Grauman, K.: Zero-shot recognition with unreliable attributes. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"8_CR26","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., Chen, X.: In defense of grid features for visual question answering. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"8_CR29","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"8_CR30","unstructured":"Kolesnikov, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Kovashka, A., Parikh, D., Grauman, K.: WhittleSearch: image search with relative attribute feedback. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2973\u20132980. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248026"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 951\u2013958. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"8_CR35","doi-asserted-by":"publisher","unstructured":"Li, X., et al.: OSCAR: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Luo, J.: Improving pairwise ranking for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.199"},{"key":"8_CR37","doi-asserted-by":"publisher","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016. ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Ma, H., et al.: EI-CLIP: entity-aware interventional contrastive learning for e-commerce cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18051\u201318061, June 2022","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Materzy\u0144ska, J., Torralba, A., Bau, D.: Disentangling visual and written concepts in clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16410\u201316419, June 2022","DOI":"10.1109\/CVPR52688.2022.01592"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Misra, I., Gupta, A., Hebert, M.: From red wine to red tomato: composition with context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.129"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., Akata, Z.: Learning graph embeddings for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 953\u2013962, June 2021","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"8_CR42","doi-asserted-by":"publisher","unstructured":"Nagarajan, T., Grauman, K.: Attributes as operators: factorizing unseen attribute-object compositions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. ECCV 2018. LNCS, vol. 11205, pp. 169\u2013185. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_11","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Nan, Z., Liu, Y., Zheng, N., Zhu, S.C.: Recognizing unseen attribute-object pair with generative model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8811\u20138818 (2019)","DOI":"10.1609\/aaai.v33i01.33018811"},{"key":"8_CR44","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Parikh, D., Grauman, K.: Relative attributes. In: 2011 International Conference on Computer Vision, pp. 503\u2013510. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Patterson, G., Hays, J.: COCO attributes: attributes for people, animals, and objects. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11\u201314 October 2016, Proceedings, Part VI 14, pp. 85\u2013100. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46466-4_6"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Pham, K., et al.: Learning to predict visual attributes in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13018\u201313028, June 2021","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"8_CR48","doi-asserted-by":"publisher","unstructured":"Pham, K., et al.: Improving closed and open-vocabulary attribute prediction using transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13685, pp. 201\u2013219. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19806-9_12","DOI":"10.1007\/978-3-031-19806-9_12"},{"key":"8_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"8_CR50","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al: DenseClip: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18082\u201318091, June 2022","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Reddy, S., Chen, D., Manning, C.D.: CoQA: a conversational question answering challenge. Trans. Assoc. Comput. Linguist. 7, 249\u2013266 (2019)","DOI":"10.1162\/tacl_a_00266"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"8_CR55","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"8_CR56","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015: 18th International Conference, Munich, Germany, 5\u20139 October 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer, Cham (2015)"},{"key":"8_CR57","doi-asserted-by":"publisher","unstructured":"Sarafianos, N., Xu, X., Kakadiaris, I.A.: Deep imbalanced attribute classification using visual attention aggregation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. ECCV 2018. LNCS, vol. 11215, pp. 680\u2013697. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_42","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"8_CR58","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"8_CR59","doi-asserted-by":"publisher","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. Association for Computational Linguistics, Melbourne, Australia, July 2018. https:\/\/doi.org\/10.18653\/v1\/P18-1238, https:\/\/aclanthology.org\/P18-1238","DOI":"10.18653\/v1\/P18-1238"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Shi, H., Hayat, M., Wu, Y., Cai, J.: ProposalClip: unsupervised open-category object proposal generation via exploiting clip cues. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9611\u20139620, June 2022","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"8_CR61","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"8_CR62","unstructured":"Sohn, K.: Improved deep metric learning with multi-class N-pair loss objective. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"8_CR64","unstructured":"Thoppilan, R., et\u00a0al.: LaMDA: language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)"},{"key":"8_CR65","unstructured":"Tsimpoukelli, M., Menick, J.L., Cabi, S., Eslami, S., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. Adv. Neural Inf. Process. Syst. 34, 200\u2013212 (2021)"},{"key":"8_CR66","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, S., Tang, J., Liu, H., Li, B.: PPP: joint pointwise and pairwise image label prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.646"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: CLIP-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11686\u201311695, June 2022","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"8_CR69","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"8_CR70","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"8_CR71","doi-asserted-by":"crossref","unstructured":"Yang, Y., Yih, W.T., Meek, C.: WikiQA: a challenge dataset for open-domain question answering. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2013\u20132018 (2015)","DOI":"10.18653\/v1\/D15-1237"},{"key":"8_CR72","unstructured":"Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T.S., Sun, M.: CPT: colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)"},{"key":"8_CR73","doi-asserted-by":"publisher","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00166, https:\/\/aclanthology.org\/Q14-1006","DOI":"10.1162\/tacl_a_00166"},{"key":"8_CR74","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Fine-grained visual comparisons with local learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 192\u2013199 (2014)","DOI":"10.1109\/CVPR.2014.32"},{"key":"8_CR75","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":"8_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and Yang: balancing and answering binary visual questions. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"8_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5579\u20135588, June 2021","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"8_CR78","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: RegionClip: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16793\u201316803, June 2022","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"8_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16816\u201316825, June 2022","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"8_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","DOI":"10.1007\/s11263-022-01653-1"}],"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\/978-3-031-73383-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:07:59Z","timestamp":1730549279000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73383-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733826","9783031733833"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73383-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 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"}}]}}