{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T11:37:04Z","timestamp":1744717024101,"version":"3.40.3"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031314346"},{"type":"electronic","value":"9783031314353"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-31435-3_28","type":"book-chapter","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T07:03:12Z","timestamp":1682492592000},"page":"412-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cleaner Categories Improve Object Detection and\u00a0Visual-Textual Grounding"],"prefix":"10.1007","author":[{"given":"Davide","family":"Rigoni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desmond","family":"Elliott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stella","family":"Frank","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"28_CR1","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, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"28_CR3","doi-asserted-by":"publisher","unstructured":"Beyer, L., H\u00e9naff, O.J., Kolesnikov, A., Zhai, X., van den Oord, A.: Are we done with imagenet? https:\/\/doi.org\/10.48550\/ARXIV.2006.07159. https:\/\/arxiv.org\/abs\/2006.07159","DOI":"10.48550\/ARXIV.2006.07159"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Bugliarello, E., Cotterell, R., Okazaki, N., Elliott, D.: Multimodal pretraining unmasked: a meta-analysis and a unified framework of vision-and-language BERTs. arXiv preprint arXiv:2011.15124 (2020)","DOI":"10.1162\/tacl_a_00408"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Cadene, R., Ben-Younes, H., Cord, M., Thome, N.: MUREL: multimodal relational reasoning for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1989\u20131998 (2019)","DOI":"10.1109\/CVPR.2019.00209"},{"key":"28_CR6","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D., et al.: RUBi: reducing unimodal biases for visual question answering. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Chen, K., Gao, J., Nevatia, R.: Knowledge aided consistency for weakly supervised phrase grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4042\u20134050 (2018)","DOI":"10.1109\/CVPR.2018.00425"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7373\u20137382 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"28_CR10","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"28_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-030-51310-8_24","volume-title":"Natural Language Processing and Information Systems","author":"S Dost","year":"2020","unstructured":"Dost, S., Serafini, L., Rospocher, M., Ballan, L., Sperduti, A.: Jointly linking visual and textual entity mentions with background knowledge. In: M\u00e9tais, E., Meziane, F., Horacek, H., Cimiano, P. (eds.) NLDB 2020. LNCS, vol. 12089, pp. 264\u2013276. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-51310-8_24"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Dost, S., Serafini, L., Rospocher, M., Ballan, L., Sperduti, A.: On visual-textual-knowledge entity linking. In: ICSC, pp. 190\u2013193. IEEE (2020)","DOI":"10.1109\/ICSC.2020.00039"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Dost, S., Serafini, L., Rospocher, M., Ballan, L., Sperduti, A.: VTKEL: a resource for visual-textual-knowledge entity linking. In: ACM, pp. 2021\u20132028 (2020)","DOI":"10.1145\/3341105.3373958"},{"key":"28_CR14","unstructured":"Dou, Z.Y., et al.: Coarse-to-fine vision-language pre-training with fusion in the backbone. arXiv preprint arXiv:2206.07643 (2022)"},{"key":"28_CR15","doi-asserted-by":"publisher","unstructured":"Frank, S., Bugliarello, E., Elliott, D.: Vision-and-language or vision-for-language. On Cross-Modal Influence in Multimodal Transformers. (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.775 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.775"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Gan, Z., Li, L., Li, C., Wang, L., Liu, Z., Gao, J., et al.: Vision-language pre-training: basics, recent advances, and future trends. Found. Trends\u00ae Comput. Graph. Vis. 14(3\u20134), 163\u2013352 (2022)","DOI":"10.1561\/0600000105"},{"key":"28_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-58580-8_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Gupta","year":"2020","unstructured":"Gupta, T., Vahdat, A., Chechik, G., Yang, X., Kautz, J., Hoiem, D.: Contrastive learning for weakly supervised phrase grounding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 752\u2013768. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_44"},{"key":"28_CR18","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"28_CR19","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 770\u2013778. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Jing, C., Jia, Y., Wu, Y., Liu, X., Wu, Q.: Maintaining reasoning consistency in compositional visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5099\u20135108 (2022)","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"28_CR21","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3389\/frai.2019.00028","volume":"2","author":"K Kafle","year":"2019","unstructured":"Kafle, K., Shrestha, R., Kanan, C.: Challenges and prospects in vision and language research. Front. Artif. Intell. 2, 28 (2019)","journal-title":"Front. Artif. Intell."},{"key":"28_CR22","doi-asserted-by":"publisher","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 1760\u20131770. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00180","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"28_CR23","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"28_CR24","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"issue":"1","key":"28_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10313\u201310322 (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"28_CR27","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Li, L.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"},{"issue":"1","key":"28_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102432","volume":"58","author":"WH Li","year":"2021","unstructured":"Li, W.H., Yang, S., Wang, Y., Song, D., Li, X.Y.: Multi-level similarity learning for image-text retrieval. Inf. Process. Manage. 58(1), 102432 (2021)","journal-title":"Inf. Process. Manage."},{"key":"28_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","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.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"28_CR31","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"},{"issue":"2","key":"28_CR32","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vision 128(2), 261\u2013318 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"28_CR33","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019 (December), pp. 8\u201314, 2019. Vancouver, BC, Canada, pp. 13\u201323 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/c74d97b01eae257e44aa9d5bade97baf-Abstract.html"},{"key":"28_CR34","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015)"},{"key":"28_CR35","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1613\/jair.1.11688","volume":"71","author":"A Mogadala","year":"2021","unstructured":"Mogadala, A., Kalimuthu, M., Klakow, D.: Trends in integration of vision and language research: a survey of tasks, datasets, and methods. J, Artif. Intell. Res. 71, 1183\u20131317 (2021)","journal-title":"J, Artif. Intell. Res."},{"key":"28_CR36","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1613\/jair.1.12125","volume":"70","author":"C Northcutt","year":"2021","unstructured":"Northcutt, C., Jiang, L., Chuang, I.: Confident learning: estimating uncertainty in dataset labels. J. Artif. Intell. Res. 70, 1373\u20131411 (2021)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"28_CR39","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 28 (2015)"},{"key":"28_CR40","doi-asserted-by":"publisher","unstructured":"Rigoni, D., Serafini, L., Sperduti, A.: A better loss for visual-textual grounding. In: Hong, J., Bures, M., Park, J.W., Cern\u00fd, T. (eds.) SAC 2022: The 37th ACM\/SIGAPP Symposium on Applied Computing, Virtual Event, 25\u201329 April 2022, pp. 49\u201357. ACM (2022). https:\/\/doi.org\/10.1145\/3477314.3507047","DOI":"10.1145\/3477314.3507047"},{"key":"28_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: Focus regions for visual question answering. In: CVPR, pp. 4613\u20134621 (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"28_CR43","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"28_CR45","doi-asserted-by":"publisher","unstructured":"Song, H., Kim, M., Park, D., Shin, Y., Lee, J.G.: Learning from noisy labels with deep neural networks: A survey. IEEE Transactions on Neural Networks and Learning Systems, pp. 1\u201319 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3152527","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"28_CR46","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5100\u20135111 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, H., Xu, K.: Categorizing concepts with basic level for vision-to-language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00521"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, J., Li, Y., Xu, K., Yang, Z., Yu, D.: Improving weakly supervised visual grounding by contrastive knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14090\u201314100 (2021)","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"28_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Q., Tan, H., Shen, S., Mahoney, M.W., Yao, Z.: MAF: multimodal alignment framework for weakly-supervised phrase grounding. arXiv preprint arXiv:2010.05379 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.159"},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Wang, R., Qian, Y., Feng, F., Wang, X., Jiang, H.: Co-VQA: answering by interactive sub question sequence. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2396\u20132408 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.188"},{"key":"28_CR54","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., Shan, S., Chen, X.: Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2020)","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"28_CR55","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, S., Yu, Z., Feng, L., Zhang, W.: Scale-equalizing pyramid convolution for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13359\u201313368 (2020)","DOI":"10.1109\/CVPR42600.2020.01337"},{"key":"28_CR56","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3060\u20133069 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"28_CR57","unstructured":"Yang, J., Li, C., Gao, J.: Focal modulation networks. arXiv preprint arXiv:2203.11926 (2022)"},{"key":"28_CR58","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: RepPoints: point set representation for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9657\u20139666 (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"28_CR59","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: PEVL: position-enhanced pre-training and prompt tuning for vision-language models. arXiv preprint arXiv:2205.11169 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"28_CR60","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"28_CR61","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Xiang, C., Zhao, Z., Tian, Q., Tao, D.: Rethinking diversified and discriminative proposal generation for visual grounding. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 1114\u20131120 (2018)","DOI":"10.24963\/ijcai.2018\/155"},{"key":"28_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, H., Niu, Y., Chang, S.F.: Grounding referring expressions in images by variational context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4158\u20134166 (2018)","DOI":"10.1109\/CVPR.2018.00437"},{"key":"28_CR63","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"28_CR64","unstructured":"Zhang, H., et al.: Glipv2: unifying localization and vision-language understanding. arXiv preprint arXiv:2206.05836 (2022)"},{"key":"28_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lei, Z., Zhang, Z., Li, S.Z.: Context-aware attention network for image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"28_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"28_CR67","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv preprint arXiv:1512.02167 (2015)"},{"key":"28_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31435-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T13:26:07Z","timestamp":1702301167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31435-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314346","9783031314353"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31435-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lapland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/scia2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT 3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}