{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:01:30Z","timestamp":1786978890139,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":90,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250842","type":"print"},{"value":"9783031250859","type":"electronic"}],"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\/978-3-031-25085-9_1","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T04:12:42Z","timestamp":1676088762000},"page":"3-23","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["YORO - Lightweight End to\u00a0End Visual Grounding"],"prefix":"10.1007","author":[{"given":"Chih-Hui","family":"Ho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srikar","family":"Appalaraju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhavan","family":"Jasani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Manmatha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuno","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: DocFormer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 993\u20131003, October 2021","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Litman, R., Xie, Y., Appalaraju, S., Manmatha, R.: LaTr: layout-aware transformer for scene-text VQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16548\u201316558, June 2022","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"1_CR3","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. ArXiv abs\/2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Deng, J., Luo, J.: Adaptive offline quintuplet loss for image-text matching. arXiv preprint arXiv:2003.03669 (2020)","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"1_CR6","unstructured":"Chen, X., Ma, L., Chen, J., Jie, Z., Liu, W., Luo, J.: Real-time referring expression comprehension by single-stage grounding network. ArXiv abs\/1812.03426 (2018)"},{"key":"1_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, P., Ma, L., Wong, K.Y.K., Wu, Q.: Cops-Ref: a new dataset and task on compositional referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"1_CR9","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: ICML (2021)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00808"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TransVG: end-to-end visual grounding with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1769\u20131779, October 2021","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"1_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"1_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"1_CR15","unstructured":"Du, Y., Fu, Z., Liu, Q., Wang, Y.: Visual grounding with transformers. CoRR abs\/2105.04281 (2021). https:\/\/arxiv.org\/abs\/2105.04281"},{"issue":"4","key":"1_CR16","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.cviu.2009.03.008","volume":"114","author":"HJ Escalante","year":"2010","unstructured":"Escalante, H.J., et al.: The segmented and annotated IAPR TC-12 benchmark. Comput. Vis. Image Underst. 114(4), 419\u2013428 (2010). https:\/\/doi.org\/10.1016\/j.cviu.2009.03.008","journal-title":"Comput. Vis. Image Underst."},{"key":"1_CR17","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. arXiv preprint arXiv:2106.00666 (2021)"},{"key":"1_CR18","doi-asserted-by":"publisher","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp. 457\u2013468. Association for Computational Linguistics, November 2016. https:\/\/doi.org\/10.18653\/v1\/D16-1044. https:\/\/aclanthology.org\/D16-1044","DOI":"10.18653\/v1\/D16-1044"},{"key":"1_CR19","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. In: NeurIPS (2020)"},{"key":"1_CR20","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: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"1_CR21","unstructured":"Han, K., et al.: A survey on visual transformer. ArXiv abs\/2012.12556 (2020)"},{"key":"1_CR22","doi-asserted-by":"publisher","unstructured":"Hao, X., et al.: MixGen: a new multi-modal data augmentation (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.08358. https:\/\/arxiv.org\/abs\/2206.08358","DOI":"10.48550\/ARXIV.2206.08358"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Howard, A.G., et al.: Searching for MobileNetV3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1_CR24","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017). http:\/\/arxiv.org\/abs\/1704.04861"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4418\u20134427 (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3296\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"1_CR28","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6693\u20136702 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"1_CR29","doi-asserted-by":"publisher","first-page":"128837","DOI":"10.1109\/ACCESS.2019.2939201","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao, L., et al.: A survey of deep learning-based object detection. IEEE Access 7, 128837\u2013128868 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2939201","journal-title":"IEEE Access"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Misra, I., Synnaeve, G., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. arXiv preprint arXiv:2104.12763 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M.A., Berg, T.L.: ReferitGame: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"1_CR32","unstructured":"Khan, S.H., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ArXiv abs\/2101.01169 (2021)"},{"key":"1_CR33","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5583\u20135594. PMLR, 18\u201324 July 2021. http:\/\/proceedings.mlr.press\/v139\/kim21k.html"},{"key":"1_CR34","unstructured":"Kovvuri, R., Nevatia, R.: PIRC Net: using proposal indexing, relationships and context for phrase grounding. CoRR abs\/1812.03213 (2018). http:\/\/arxiv.org\/abs\/1812.03213"},{"issue":"1\u20132","key":"1_CR35","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955). https:\/\/doi.org\/10.1002\/nav.3800020109","journal-title":"Naval Res. Logist. Q."},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. arXiv preprint arXiv:1803.08024 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"1_CR37","doi-asserted-by":"publisher","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703. https:\/\/aclanthology.org\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Li, C., Feh\u00e9rv\u00e1ri, I., Zhao, X., Macedo, I., Appalaraju, S.: SeeTek: very large-scale open-set logo recognition with text-aware metric learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2544\u20132553, January 2022","DOI":"10.1109\/WACV51458.2022.00066"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Liao, Y., et al.: A real-time cross-modality correlation filtering method for referring expression comprehension. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10877\u201310886 (2020)","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"1_CR41","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":"1_CR42","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00477"},{"key":"1_CR43","doi-asserted-by":"publisher","unstructured":"Liu, J., Wang, L., Yang, M.H.: Referring expression generation and comprehension via attributes. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4866\u20134874 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.520","DOI":"10.1109\/ICCV.2017.520"},{"key":"1_CR44","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2019","unstructured":"Liu, L., et al.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128, 261\u2013318 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01247-4","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Z., Shao, J., Wang, X., Li, H.: Improving referring expression grounding with cross-modal attention-guided erasing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00205"},{"key":"1_CR46","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. ArXiv abs\/1907.11692 (2019)"},{"key":"1_CR47","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"1_CR48","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10031\u201310040 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Luo, R., Shakhnarovich, G.: Comprehension-guided referring expressions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.333"},{"key":"1_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"1_CR53","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. ArXiv abs\/1912.01703 (2019)"},{"key":"1_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-01258-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"BA Plummer","year":"2018","unstructured":"Plummer, B.A., Kordas, P., Kiapour, M.H., Zheng, S., Piramuthu, R., Lazebnik, S.: Conditional image-text embedding networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 258\u2013274. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_16"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Qi, W., et al.: ProphetNet: predicting future N-gram for sequence-to-sequence pre-training. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 2401\u20132410 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.217"},{"key":"1_CR56","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"1_CR57","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"1_CR58","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. ArXiv abs\/1910.10683 (2020)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. ArXiv preprint (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"1_CR60","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1_CR62","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ArXiv abs\/1804.02767 (2018)"},{"key":"1_CR63","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, NIPS 2015, vol. 1, pp. 91\u201399. MIT Press, Cambridge (2015)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Rezatofighi, S.H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. ArXiv abs\/1511.03745 (2016)","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00479"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7262\u20137272, October 2021","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"1_CR69","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=SygXPaEYvH"},{"key":"1_CR70","doi-asserted-by":"publisher","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 6418\u20136428. Association for Computational Linguistics, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1644. https:\/\/aclanthology.org\/P19-1644","DOI":"10.18653\/v1\/P19-1644"},{"key":"1_CR71","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, vol. 139, pp. 10347\u201310357, July 2021"},{"key":"1_CR72","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"issue":"2","key":"1_CR73","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. TPAMI 41(2), 394\u2013407 (2019)","journal-title":"TPAMI"},{"key":"1_CR74","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., van den Hengel, A.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00206"},{"key":"1_CR75","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, October 2020. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"1_CR76","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00427"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00474"},{"key":"1_CR78","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58568-6_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Chen, T., Wang, L., Luo, J.: Improving one-stage visual grounding by recursive sub-query construction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_23"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00478"},{"key":"1_CR80","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: ERNIE-ViL: knowledge enhanced vision-language representations through scene graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 3208\u20133216, May 2021. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16431","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00142"},{"key":"1_CR82","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. ArXiv abs\/1608.00272 (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3521\u20133529 (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"1_CR84","doi-asserted-by":"publisher","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3521\u20133529 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.375","DOI":"10.1109\/CVPR.2017.375"},{"key":"1_CR85","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. ArXiv abs\/1805.03508 (2018)","DOI":"10.24963\/ijcai.2018\/155"},{"key":"1_CR86","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"1_CR87","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 (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00437"},{"key":"1_CR88","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: pre-training with extracted gap-sentences for abstractive summarization (2019)"},{"key":"1_CR89","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"},{"key":"1_CR90","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., van den Hengel, A.: Parallel attention: a unified framework for visual object discovery through dialogs and queries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00447"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25085-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T14:53:14Z","timestamp":1710255194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25085-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250842","9783031250859"],"references-count":90,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25085-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}