{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:25:08Z","timestamp":1780079108748,"version":"3.54.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_24","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"417-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":70,"title":["Bottom Up\u00a0Top Down\u00a0Detection Transformers for\u00a0Language Grounding in\u00a0Images and\u00a0Point Clouds"],"prefix":"10.1007","author":[{"given":"Ayush","family":"Jain","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Gkanatsios","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ishita","family":"Mediratta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katerina","family":"Fragkiadaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Abdelreheem, A., Upadhyay, U., Skorokhodov, I., Yahya, R.A., Chen, J., Elhoseiny, M.: 3DRefTransformer: fine-grained object identification in real-world scenes using natural language. In: Proceedings of the WACV (2022)","DOI":"10.1109\/WACV51458.2022.00068"},{"key":"24_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-58452-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Achlioptas","year":"2020","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: ReferIt3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25"},{"key":"24_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"24_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"24_CR5","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":"24_CR6","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":"24_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T.A., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"24_CR8","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 ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: Proceedings of the CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Feng, M., et al.: Free-form description guided 3D visual graph network for object grounding in point cloud. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"24_CR11","doi-asserted-by":"crossref","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 EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"24_CR12","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: Proceedings of the NeurIPS (2020)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"He, D., et al.: TransRefer3D: entity-and-relation aware transformer for fine-grained 3D visual grounding. In: Proceedings of the ACMMM (2021)","DOI":"10.1145\/3474085.3475397"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: Proceedings of the ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"24_CR15","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), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR17","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: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Lee, H.H., Chen, H.T., Liu, T.L.: Text-guided graph neural networks for referring 3D instance segmentation. In: Proceedings of the AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"24_CR19","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver: general perception with iterative attention. In: Proceedings of the ICML (2021)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the CVPR (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y.A., Misra, I., Synnaeve, G., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"24_CR23","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: Proceedings of the EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123 (2016)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"24_CR25","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 abs\/1908.03557 (2019)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"24_CR27","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":"24_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"24_CR29","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv abs\/1907.11692 (2019)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"24_CR31","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Proceedings of the NeurIPS (2019)"},{"key":"24_CR32","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: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O.M., Yuille, A.L., Murphy, K.P.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"24_CR35","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. In: Proceedings of the NIPS (2011)"},{"key":"24_CR36","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: Proceedings of the ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"24_CR37","unstructured":"Qi, C., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the NIPS (2017)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"24_CR39","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 NIPS (2015)"},{"key":"24_CR40","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: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"24_CR41","unstructured":"Roh, J., Desingh, K., Farhadi, A., Fox, D.: LanguageRefer: spatial-language model for 3D visual grounding. In: Proceedings of the CoRL (2021)"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00479"},{"key":"24_CR43","doi-asserted-by":"crossref","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 ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"24_CR44","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":"24_CR45","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 ICCV (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, S., Wang, L., Luo, J.: SAT: 2D semantics assisted training for 3D visual grounding. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"24_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Yan, X., Liao, Y., Zhang, R., Li, Z., Cui, S.: InstanceRefer: cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"24_CR50","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of the ICLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T13:11:09Z","timestamp":1678453869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","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)"}}]}}