{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:40:09Z","timestamp":1776883209892,"version":"3.51.2"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784552","type":"print"},{"value":"9783031784569","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78456-9_19","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:25:33Z","timestamp":1733138733000},"page":"292-307","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Harlequin: Color-Driven Generation of Synthetic Data for Referring Expression Comprehension"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8574-4997","authenticated-orcid":false,"given":"Luca","family":"Parolari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1105-4162","authenticated-orcid":false,"given":"Elena","family":"Izzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0819-851X","authenticated-orcid":false,"given":"Lamberto","family":"Ballan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Amoroso, R., Morelli, D., Cornia, M., Baraldi, L., Bimbo, A.D., Cucchiara, R.: Parents and children: Distinguishing multimodal deepfakes from natural images. CoRR abs\/2304.00500 (2023)","DOI":"10.1145\/3665497"},{"key":"19_CR2","unstructured":"Arora, S., Narayan, A., Chen, M.F., Orr, L.J., Guha, N., Bhatia, K., Chami, I., R\u00e9, C.: Ask me anything: A simple strategy for prompting language models. In: Proc. of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"19_CR3","unstructured":"Blender Online Community: Blender - a 3D modelling and rendering package (2024), http:\/\/www.blender.org"},{"key":"19_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. In: Proc. of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, P., Ma, L., Wong, K.K., Wu, Q.: Cops-ref: A new dataset and task on compositional referring expression comprehension. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Shahbaz\u00a0Khan, F., Felsberg, M., Van\u00a0de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.143"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: Transvg: End-to-end visual grounding with transformers. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"19_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2019)"},{"key":"19_CR9","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: CARLA: an open urban driving simulator. In: Proc. of the Conference on Robot Learning (CoRL) (2017)"},{"issue":"4","key":"19_CR10","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., Hern\u00e1ndez, C.A., Gonz\u00e1lez, J.A., L\u00f3pez-L\u00f3pez, A., Montes-y-G\u00f3mez, M., Morales, E.F., Sucar, L.E., Pineda, L.V., Grubinger, M.: The segmented and annotated IAPR TC-12 benchmark. Comput. Vis. Image Underst. 114(4), 419\u2013428 (2010)","journal-title":"Comput. Vis. Image Underst."},{"key":"19_CR11","unstructured":"Feng, W., Zhu, W., Fu, T., Jampani, V., Akula, A.R., He, X., Basu, S., Wang, X.E., Wang, W.Y.: Layoutgpt: Compositional visual planning and generation with large language models. CoRR abs\/2305.15393 (2023)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. CoRR abs\/1605.06457 (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, H., Lin, Y., Han, D., Song, S., Huang, G.: Pseudo-q: Generating pseudo language queries for visual grounding. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Jin, J., Ye, J., Lin, X., He, L.: Pseudo-query generation for semi-supervised visual grounding with knowledge distillation. In: Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)","DOI":"10.1109\/ICASSP49357.2023.10095558"},{"key":"19_CR16","unstructured":"Juliani, A., Berges, V., Vckay, E., Gao, Y., Henry, H., Mattar, M., Lange, D.: Unity: A general platform for intelligent agents. CoRR abs\/1809.02627 (2018)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: Referitgame: Referring to objects in photographs of natural scenes. In: Proc. of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Le, H., Mensink, T., Das, P., Karaoglu, S., Gevers, T.: EDEN: multimodal synthetic dataset of enclosed garden scenes. In: Proc. of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00162"},{"key":"19_CR20","unstructured":"Li, M., Sigal, L.: Referring transformer: A one-step approach to multi-task visual grounding. In: Proc. of Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., Lee, Y.J.: GLIGEN: open-set grounded text-to-image generation. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Proc. of the European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR24","unstructured":"Lu, J., Rao, J., Chen, K., Guo, X., Zhang, Y., Sun, B., Yang, C., Yang, J.: Evaluation and enhancement of semantic grounding in large vision-language models. In: Proc. of the AAAI Workshop on Responsible Language Models (ReLM) (2024)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Lu, M., Li, R., Feng, F., Ma, Z., Wang, X.: LGR-NET: Language Guided Reasoning Network for Referring Expression Comprehension. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) in press (2024)","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"19_CR27","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: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"19_CR28","unstructured":"Rigoni, D., Parolari, L., Serafini, L., Sperduti, A., Ballan, L.: Weakly-supervised visual-textual grounding with semantic prior refinement. In: Proc. of the British Machine Vision Conference (BMVC) (2023)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Proc. of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_CR31","unstructured":"Roovere, P.D., Moonen, S., Michiels, N., Wyffels, F.: Dataset of industrial metal objects. CoRR abs\/2208.04052 (2022)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Su, W., Miao, P., Dou, H., Wang, G., Qiao, L., Li, Z., Li, X.: Language adaptive weight generation for multi-task visual grounding. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Tanaka, M., Itamochi, T., Narioka, K., Sato, I., Ushiku, Y., Harada, T.: Generating easy-to-understand referring expressions for target identifications. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00589"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Specia, L.: Phrase localization without paired training examples. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00476"},{"key":"19_CR35","doi-asserted-by":"publisher","first-page":"9330","DOI":"10.1109\/TMM.2023.3251111","volume":"25","author":"W Wang","year":"2023","unstructured":"Wang, W., Pagnucco, M., Xu, C., Song, Y.: InterREC: An Interpretable Method for Referring Expression Comprehension. IEEE Transactions on Multimedia (TMM) 25, 9330\u20139342 (2023)","journal-title":"IEEE Transactions on Multimedia (TMM)"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Yang, L., Xu, Y., Yuan, C., Liu, W., Li, B., Hu, W.: Improving visual grounding with visual-linguistic verification and iterative reasoning. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gan, Z., Wang, J., Hu, X., Ahmed, F., Liu, Z., Lu, Y., Wang, L.: Unitab: Unifying text and box outputs for grounded vision-language modeling. In: Proc. of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"19_CR38","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: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Gan, Z., Li, L., Lin, K., Wu, C., Duan, N., Liu, Z., Liu, C., Zeng, M., Wang, L.: Reco: Region-controlled text-to-image generation. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Ye, J., Tian, J., Yan, M., Yang, X., Wang, X., Zhang, J., He, L., Lin, X.: Shifting more attention to visual backbone: Query-modulated refinement networks for end-to-end visual grounding. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"19_CR41","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics (TACL) 2, 67\u201378 (2014)","journal-title":"Transactions of the Association for Computational Linguistics (TACL)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Yu, L., Lin, Z., Shen, X., Yang, J., Lu, X., Bansal, M., Berg, T.L.: Mattnet: Modular attention network for referring expression comprehension. In: Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proc. of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"19_CR44","first-page":"1","volume":"61","author":"Y Zhan","year":"2023","unstructured":"Zhan, Y., Xiong, Z., Yuan, Y.: RSVG: exploring data and models for visual grounding on remote sensing data. IEEE Trans. Geosci. Remote Sens. 61, 1\u201313 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proc. of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:12:31Z","timestamp":1733141551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}